HCI Bibliography Home | HCI Conferences | HCII Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
HCII Tables of Contents: 03-303-407-107-207-307-409-109-209-309-411-111-211-311-411-511-613-113-213-313-413-5

HCI International 2011: 14th International Conference on Human-Computer Interaction, Part I: Design and Development Approaches

Fullname:HCI International 2011: 14th International Conference on Human-Computer Interaction, Part I: Design and Development Approaches
Editors:Julie A. Jacko
Location:Orlando, Florida
Dates:2011-Jul-09 to 2011-Jul-14
Volume:1
Publisher:Springer-Verlag
Series:Lecture Notes in Computer Science 6761
Standard No:ISBN: 978-3-642-21601-5 (print), 978-3-642-21602-2 (online); hcibib: HCII11-1
Papers:75
Pages:693
Links:Online Proceedings | Publisher Book Page | Conference Website
  1. HCII 2011-07-09 Volume 1
    1. HCI International 2011 Keynote Speech
    2. HCI Design
    3. Model-Based and Patterns-Based Design and Development
    4. Cognitive, Psychological and Behavioural Issues in HCI
    5. Development Methods, Algorithms, Tools and Environments
    6. Image Processing and Retrieval in HCI

HCII 2011-07-09 Volume 1

HCI International 2011 Keynote Speech

Technology-Mediated Social Participation: The Next 25 Years of HCI Challenges BIBAKFull-Text 3-14
  Ben Shneiderman
The dramatic success of social media such as Facebook, Twitter, YouTube, blogs, and traditional discussion groups empowers individuals to become active in local and global communities. Some enthusiasts believe that with modest redesign, these technologies can be harnessed to support national priorities such as healthcare/wellness, disaster response, community safety, energy sustainability, etc. However, accomplishing these ambitious goals will require long-term research to develop validated scientific theories and reliable, secure, and scalable technology strategies. The enduring questions of how to motivate participation, increase social trust, and promote collaboration remain grand challenges even as the technology rapidly evolves. This talk invites researchers across multiple disciplines to participate in redefining our discipline of Human-Computer Interaction (HCI) along more social lines to answer vital research questions while creating inspirational prototypes, conducting innovative evaluations, and developing robust technologies. By placing greater emphasis on social media, the HCI community could constructively influence these historic changes.
Keywords: social media; participation; motivation; social network analysis; user-generated content; Open Government; collective intelligence; collective action; community design; wikis; blogs; discussion groups; reader-to-leader framework

HCI Design

Towards a Cognitive-Based User Interface Design Framework Development BIBAKFull-Text 17-24
  Natrah Abdullah; Wan Adilah Wan Adnan; Nor Laila Md. Noor
This paper discusses the theoretical framework underlying the studies of cognitive-based user interface design of heritage tourism website. Multiple Resource Theory under cognitive psychological study is used particularly in developing UI taxonomy of museum website. MRT highlights on three components which are perceptual modality, visual channel and code of processing. Components of MRT are applied extensively into user interface dimensions identification by emphasis on user interface support functions. As a result three components are propose; format, structure and representation. These components can be used to provide insights into area of HCI with taxonomy of UI for museum websites. Cognitive-based UI framework is proposed and presented with aims to assist in the design and development of the taxonomy.
Keywords: User Interface Design; Cognitive
A Design Science Framework for Designing and Assessing User Experience BIBAKFull-Text 25-34
  Sisira Adikari; Craig McDonald; John Campbell
User Experience is a well recognized factor in design and evaluation of artifacts in Human-Computer Interaction. There are many user experience models reported in the literature to reflect this status. Techniques and instruments for managing user experience are still not sufficient. In this paper, we discuss design science research and important user experience models reported in the literature and propose an integrated design science framework for designing and assessing user experience. We also present the results of an experimental study to validate our proposed framework and the instrument employed.
Keywords: Design Science; User Experience
Objective and Subjective Measures of Visual Aesthetics of Website Interface Design: The Two Sides of the Coin BIBAKFull-Text 35-44
  Ahamed AlTaboli; Yingzi Lin
The main purpose of this study is to compare objective layout-based measures of visual aesthetics with subjective questionnaire-based measures. Correlation analysis was used to carry out the comparison. Values for the tested objective measures were calculated for forty-two web pages already used in a previous study, for which subjective questionnaire scores (classical/expressive and VisA WI) were already available. Results showed significant correlations between many of the tested objective screen layout-based measures and subjective questionnaire-based measures related to order and layout of the screen. These findings suggest that the objective layout-based measures tested in this study can be used for overall assessments of visual aesthetics of websites and particularly for assessing aesthetic aspects related to the classical and the simplicity dimensions of website aesthetics.
Keywords: Aesthetics measures; Measure of Website aesthetics; Classical/expressive aesthetics; VisA WI; Visual aesthetics
Interaction Design Teaching Method Design BIBAKFull-Text 45-53
  Chen-Wei Chiang; Kiyoshi Tomimatsu
Recently, Interaction Design became popular. We found that, if we want to improve interaction design, an interaction design education method is indispensable. Especially, interaction design usually consists of two or more different fields of discipline. When members with different backgrounds are working together, there are always cause many problems, mainly during brainstorming processes. In the final, we tried to find out the main cause of the problem and tried to figure out a method for interaction design education. In the end, we also propose the possible solution to improve interaction design teaching design. We except this research can help to improve interaction design education.
Keywords: Interaction Design; workshop
Designing Interaction Concepts, Managing Customer Expectation and Mastering Agile Development in Rich Application Product Development BIBAKFull-Text 54-62
  Marcela Esteves; Vladimir Andrade
The emergence of rich application implementation frameworks, such as WPF and Silverlight, promoted a new collaboration paradigm between developers and designers where ownership of the user interface code is transferred to the user experience team. The implications of this new paradigm for the user centered design process impact its technical, collaborative, and business dimensions. The traditional design prototype can now demonstrate most of the desired user experience and could be directly integrated with the back-end code, significantly reducing the design revision costs. Creating the rich prototypes demand enhanced technical skills from visual designers, who become a member of both the design and implementation teams. The implementation tools provided by the rich application frameworks aim to simplify the prototype creation task for the designer, but can potentially lead customers to expect a lower effort associated with the user centered design process.
Keywords: user centered design process; WPF; Silverlight; visual design; interaction design; rich application
POLVO -- Software for Prototyping of Low-Fidelity Interfaces in Agile Development BIBAKFull-Text 63-71
  Júnia Gonçalves; Caroline Santos
In the process of software development, the ease with which the user can perform his/her tasks in the system -- commonly called usability -- is an important requirement. The prototyping of user interfaces is one of the most widely used techniques to specify this type of requirement. This paper presents the importance and need to improve and increase the agility of prototyping interfaces in agile development processes. The authors propose a software that is able to build low-fidelity prototypes, document them and support user testing, to aid the process of interface building in the Scrum methodology.
Keywords: Low-fidelity Prototype; Interaction Design; Agile Methods; Scrum
Towards a Conceptual Framework for Interaction Design for the Pragmatic Web BIBAKFull-Text 72-81
  Heiko Horst Hornung; Maria Cecília Calani Baranauskas
In the current World Wide Web, useful information on web sites is often mixed with a lot of information that is not relevant to a user at a particular moment, or is presented in a format that is not optimal for a particular person using a specific artifact. In this paper we argue that to solve problems related to information relevance, presentation and flexibility of use, approaches are required that provide users with uniform ways of accessing and using information and services that are relevant to them at a particular moment in a way that suits their competences and needs. Informed by the Pragmatic Web and hence the questions of how and why people actually access information and services, this work proposes to set a basis for a conceptual framework to better understand, reason about, and design interaction in the Web.
Keywords: Interaction Design; Pragmatic Web
Blowing Light: Green-Based Interaction Design BIBAKFull-Text 82-91
  Yu-Chun Annester Huang; Chih-Chieh Tsai; Teng-Wen Chang; Pen-Yan Tsai; Tien-Hsin Hung; Jai-Jung Chen
As green being a significant issue of these years, we want to discuss about how to combine green with technology through ambient design. Not only use intelligent methods but also interact with fun playing interaction. The relationship between people and the feedback of installation can make people help themselves to meet the needs of them. This paper provides an innovation concept of ambient Intelligence. People can help themselves through a wind-blower installation by conventional power-generating method.
Keywords: Ambient Intelligent; Green; Human Power; Wind-Blower; Light; Interactive installation
The Impact of Rich Application Frameworks on User Experience Design BIBAKFull-Text 92-97
  Tobias Komischke
Rich internet and desktop application frameworks provide advanced features like direct object manipulation and advanced animations that can enhance the user experience. This paper traces the history and evolution of rich applications and in front of the background of the T.O.T.E. framework discusses the benefits that rich application capabilities provide for the human-system interaction.
Keywords: User Experience; Design; Rich Interactivity
Axiomatic Design for Biometric Icons BIBAKFull-Text 98-106
  Sheau-Farn Max Liang; Chien-Tsen Lin
Well-designed icons should be visually distinctive and appropriately represent their intended meanings. Through the axiomatic design method, potential design issues about the recognition of a set of biometric icons for a fingerprint capture device have been identified. Two possible solutions, icon redesign and provision of procedure instruction, were proposed. A 2x2 ANOVA experiment was designed to test the main and interaction effects of the two solutions on eighty participants' icon recognition rate. Results showed that either redesigning the icons or providing the procedure instruction could significantly enhance the icon recognition rate. Furthermore, significant interaction effect indicated that the benefit of instruction was minor if redesigned icons were applied. From the perspective of human factors, icon redesign according to the axiomatic design principles may be a predominant solution.
Keywords: Axiomatic Design; Icon; Biometric Device; Fingerprint Capture
A Rapid Prototyping Tool for Interactive Device Development BIBAKFull-Text 107-113
  Mark Merlo; Mark Bachman
Designers need rapid prototyping tools that are embeddable, easily configured and can control a large range of accessories. Current prototyping tools fall short on these requirements by requiring one or more of the following: a tether to a computer, textual programming, and/or limited accessory control. To overcome the limitations of current tools, we have developed Buttercup, a standalone embedded sensor/effector controller that provides a high degree of customization for rapid prototyping interactive devices. The keys to the implementation of Buttercup are its hardware and firmware architecture. By building a system focused on sensor and effector control, the hardware can be small and inexpensive. The firmware utilizes a unique mapping system that lends itself to robust control over its accessories while allowing intuitive configuration by the user through a graphical user interface.
Keywords: Embedded controller; rapid prototyping; graphical programming; physical interactive system; effector controller; sensor controller
Key Requirements for Integrating Usability Engineering and Software Engineering BIBAKFull-Text 114-120
  Karsten Nebe; Volker Paelke
To improve the integration between Software Engineering (SE) and Usability Engineering (UE) this paper identifies areas of overlap and develops proposals for their integration. The focus is on key requirements that were derived using semi-structured interviews and questionnaires. The principles and activities in the standards ISO 13407 and ISO/PAS 18152 were concretized to establish specific quality aspects. The identified requirements provide a foundation for systematic modification of existing development processes with established best practices from both disciplines.
Keywords: Integration; Assessment; Standards DIN EN ISO 13407 and ISO/PAS 18152; Process Models; Process Definition
Message Oriented Middleware for Flexible Wizard of Oz Experiments in HCI BIBAKFull-Text 121-130
  Mirko Otto; Rafael Friesen; Dietmar Rösner
Wizard of Oz (WOZ) systems and WOZ experiments are an important tool for basic and applied research in HCI. We report about using SEMAINE as a flexible component based middleware with a loose coupling of components as software infrastructure for WOZ experiments in human companion interaction. We focus on our experimental WOZ designs, their realisation within the SEMAINE framework and lessons learned from deploying the implemented solutions as the basis for ongoing controlled experiments with 120 subjects.
Keywords: Wizard of Oz; Companion Systems; Emotion; Multimodal; Message Oriented Middleware; SEMAINE
Design and Rich Application Frameworks BIBAKFull-Text 131-135
  Kevin H. Richardson
With the advent of rich application frameworks like Flash and Silverlight as well as the increased exposure to interaction models they make possible (does anyone want a mobile device that doesn't have an iPhone-like interface?) it isn't difficult to imagine that usability and design professionals may be feeling a little vulnerable. After all, until recently, usability and design professionals were the last, best hope in the face of early web design, business systems left over from the 80s and clunky mobile phone menus. We helped create an environment in which users expected more (at least on the web). Today, however, developers have at their disposal an arsenal of tools designed to provide users with experiences that take advantage of asynchronous server calls, high-definition multimedia and slick, natural-feeling interactions. Have we been relegated to the role of usability testing? Surely, our profession has more to offer. The good news is that our role is the same as it has ever been. Like any platform or technology, rich application frameworks are the medium through which design is expressed. As such, they are no different from any previous platform that was ready to revolutionize the manner in which people interact with information, the world or each other. They are the tools through which researchers, designers and technologists enable users to complete tasks and make decisions. They are the paint and canvas, the clay and plastic molds, with which we bring our designs to life. A well-designed system is the result of a well-defined design process. That process includes the expertise of an interdisciplinary team with individual backgrounds in graphic design, fine art, architecture, cognitive psychology, anthropology, human-computer interaction, and other fields. This kind of design team has the training and experience to bridge the gap between business, technology and human requirements. They (we!) practice a design process that is mindful of the features, functions and legacy systems that must be somehow united, implemented and maintained. They are equally mindful of who will be using these systems (from motorcycle enthusiasts to financial analysts, from students to CEOs), their experiences and mental models, where the systems will be used (from hospital emergency rooms to living rooms and executive boardrooms) and what they need from technology to improve rather than impede outcomes. If, at any point, the user must wrestle with the interface, then research and design have failed. Our job, therefore, remains one of understanding the ways in which users need to have information presented to them, the ways in which they need to interact with it and the decisions they must make. The capabilities made available via rich internet applications provide a larger toolset from which to choose in order to meet these requirements.
Keywords: design; design process; research; usability
Enhancing Personas with Their Main Scenarios BIBAKFull-Text 136-141
  Alícia Valls Saez; Muriel Garreta Domingo; Marta López Reyes
The methodology of "personas" is a well-known procedure and very often used for characterizing target users in user-centered design projects. Very often, personas are represented by a picture. This paper introduces a different approach to present the results of a user analysis study with the goal to increase assimilation and comprehension of a project's personas. We believe that creating and developing a new concept enhancing "personas" with their context, giving less importance to the image of the person with a silhouette and adding an image of their main scenarios can make more impact in our organizations. To verify our idea we conducted a study to evaluate which format -- "personas" with a picture and "personas" with their contexts -- worked better.
Keywords: Personas; Persona usage; Context; Scenarios; User research; Design methods
Streamlining User Experience Design and Development: Roles, Tasks and Workflow of Applying Rich Application Technologies BIBAKFull-Text 142-151
  Xianjun Sam Zheng; Mo Wang; Gilberto Matos; Shaopeng Zhang
The adoption of Rich Application Technologies (RATs), such as Windows Presentation Foundation (WPF) or Adobe Flex, not only significantly enriches the user interface (UI) technology, but also can boost the collaborations among user experience (UX) specialists, designers and developers. Many books and plenty of online resources have described and discussed the technical capability and details of various RATs. However, how to effectively incorporate RATs into the process of UX design and development has not been systematically addressed. In this paper, we report our experience of applying RATs to develop several complex enterprise software systems. A new role, integrator, is introduced to support the communications among UX specialists, designers, and developers. We discuss the responsibilities and task assignments for each role, and propose a new workflow to streamline the design and development. We also discuss the challenges and the lessons learned from applying different RATs.
Keywords: User experience; UI design; development; rich application technology; WPF/Silverlight; Flex

Model-Based and Patterns-Based Design and Development

Configurable Executable Task Models Supporting the Transition from Design Time to Runtime BIBAKFull-Text 155-164
  Birgit Bomsdorf; Stefan Grau; Martin Hudasch; Jan-Torsten Milde
Model-based design of user interfaces mostly starts with task and domain modeling. The resulting models are an important input to subsequent development steps. Thus, a thorough evaluation of these specifications is of great importance, e.g. to avoid the implementation of bad or even error prone solutions. Executable task models are in use for several years to evaluate the design time specifications. They are also used at runtime by now as part of the final application. In this paper we propose an executable task model that is configured using the design time model. Kernel concept of this work is a task state machine describing a generic task life cycle assigned to each task. Developers may extend it at design time to describe application dependent behavior. The extensions are automatically transferred to the runtime system. A further focus of the paper is on the specification of temporal relations and their extensibility in terms of model description and execution.
Keywords: task modeling; executable task model; runtime support; temporal relations
Automatic Adaptation of User Workflows within Model-Based User Interface Generation during Runtime on the Example of the SmartMote BIBAKFull-Text 165-174
  Kai Breiner; Kai Bizik; Thilo Rauch; Marc Seissler; Gerrit Meixner; Philipp Diebold
Model-based universal interaction devices are already capable to react on contextual changes by automatically adapting the user interface, but without considering the usefulness of the resulting user interface. Often tasks cannot be executed any more or execution orders will result in dead locks caused by unavailable functionality. We present our approach of investigating this property of adapted models based on the example of the SmartMote in our living lab the SmartFactory KL. Given the task description of the user interaction we determine a dialog model in terms of a state machine -- which is necessary in our process of user interface generation -- to determine possible execution orders leading to the accept state of this state machine. Using these execution orders the initial task model can be adapted, all misleading tasks can be removed and the resulting user interface will only offer valid user interactions.
Keywords: Adaptive User Interfaces; Usage Context; Task Fulfillment; SmartFactory; SmartMote; Model-based User Interface Development
Towards an Automatic Analysis of Interaction Data for HCI Evaluation Application to a Transport Network Supervision System BIBAKFull-Text 175-184
  Selem Charfi; Houcine Ezzedine; Christophe Kolski; Faouzi Moussa
In this paper, we propose a method for the analysis and the interpretation of the interactions between the user and the interactive system to evaluate. The proposed approach is based on the comparison between the user interaction sequences and the sequences average. This confrontation concerns the task execution duration, the realized tasks number and the action sequence used in a defined experimental scenario.
Keywords: Human-Machine Interaction; Automatic Evaluation; Ergonomic Guidelines; Task modeling
A Formal Model of Mixed-Initiative Interaction in Design Exploration BIBAKFull-Text 185-193
  Sambit Datta; Michael Hobbs
Computer-based environments for supporting design are complex software artifacts. These tools need to use sound computational formalisms as well as address issues of human usability. The development of interactive and usable generative systems is a significant research area in design computation. Though classical search techniques play a central role in the generative kernels of these "closed-world" systems, the open-ended exploration of design spaces is the desirable goal. In this paper, we present a formal model of exploration that combines search with user driven exploration. We describe the role of interaction and agency in an experimental mixed-initiative design support system.
Keywords: generative design; mixed-initiative; design exploration
Intertwined Modeling and Implementation of Interactive Systems Using HOPS BIBAKFull-Text 194-203
  Anke Dittmar; Peter Forbrig
The paper investigates the co-evolution of models and implementations of interactive systems within the model-based design paradigm. A view of implementations as pure results of top-down model refinements is rejected. On the one hand, models inform or even drive further design and implementation steps. On the other hand, implementation ideas emerge during the iterative development process. They can be evaluated and further explored by models. In particular, selective modeling allows to focus attention on certain aspects of the interaction.
   Higher-Order Processes Specifications (HOPS) describe interactive systems from different viewpoints and at different levels of granularity. The HOPS tool is used to suggest techniques for intertwining modeling and implementation activities. Object-oriented implementations in Java can be assigned to HOPS models. Their animation results in model-guided proto typing open for both empirical and analytical evaluation.
Keywords: Model-Based Design; Human-Centered Design; Viewpoints; Co-Evolution of Representations
HCI Patterns as a Means to Transform Interactive User Interfaces to Diverse Contexts of Use BIBAKFull-Text 204-213
  Jürgen Engel; Christian Märtin; Peter Forbrig
This paper introduces a pattern-based method for transformation of user interfaces of interactive applications to diverse contexts of use. The method is demonstrated with the help of various examples taken from existing software solutions. The related pattern transformation rules are derived from the samples and in turn expressed in a pattern format, the so-called transformation patterns.
Keywords: HCI patterns; user interface; pattern-based context transformation; transformation patterns; interactive systems; PLML
Process Choreography for Human Interaction Computer-Aided Simulation BIBAFull-Text 214-220
  Carlos Fernandez-Llatas; Juan Bautista Mocholí; Pilar Sala; Juan-Carlos Naranjo
Design errors can suppose a unaffordable load for the production costs. Allowing product designers to de ne behavioral patterns that describe the interaction of future users of the system can reduce the number of design errors. These patterns can be used to simulate how users respond to stimuli of products detecting problems at early stages of product development. Choreography systems to simulate the interaction among devices and services defined using commercially available workflow engines have been used in previous work (as the European project VAALID). However, the complexity of human behavior models requires much more expressive workflow languages for their definition.
   In this work, a highly expressive Workflow engine is presented. This system solves the problem of expressiveness in the representation of the interaction of human behavior models in the VAALID project.
Building Multimodal Interfaces Out of Executable, Model-Based Interactors and Mappings BIBAFull-Text 221-228
  Sebastian Feuerstack; Ednaldo Brigante Pizzolato
Future interaction will be embedded into smart environments offering the user to choose and to combine a heterogeneous set of interaction devices and modalities based on his preferences realizing an ubiquitous and multimodal access. We propose a model-based runtime environment (the MINT Framework) that describes multimodal interaction by interactors and multimodal mappings. The interactors are modeled by using state machines and describe user interface elements for various modalities. Mappings combine these interactors with interaction devices and support the definition of multimodal relations. We prove our implementation by modeling a multimodal navigation supporting pointing and hand gestures. We additionally present the flexibility of our approach that supports modeling of common interaction paradigms such as drag-and-drop as well.
The First Interaction Design Pattern Library for Internet of Things User Created Applications BIBAFull-Text 229-237
  Marc Godon; Mohamed Ali Feki; Marc Roelands; Lieven Trappeniers
In this paper, we report our analysis of extracting relevant existing and new interaction patterns that are candidates as enabling paradigms to facilitate Internet of Thing user created application building. We first define the context and underline what is an internet of thing user created application and what are the main research issues. We stress the focus on Interaction design as a must have paradigm to reach the Internet of thing user created application vision and highlight the research scope. In this paper we contribute with a template based interaction pattern that refers to competitive advantages and limitations with regard to our vision. The research method allowed us to sort out our first library of interaction pattern in this field. We conclude the paper with lab experimentation and lessons learned.
Differentiating between Successful and Less Successful Products by Using MAInEEAC -- A Model for Interaction Characterization BIBAKFull-Text 238-247
  Steffen Hess; Andreas Maier; Marcus Trapp
Today, the success of a software product is defined by a great user experience caused by a well-defined interaction concept rather than features. Therefore we present a new interaction model called MAInEEAC (Model for Accurate Interaction Engineering, Enhancement, Alteration, and Characterization) that is able to show what makes an interaction a great experience and what are the elements of great human-computer-interaction. Having evaluated the ways of entering an address with nine distinct navigation systems, we present several findings which are crucial for making an interaction successful. Thereby it becomes clear that a higher level of detail is required in order to recognize important differences between single interactions. MAInEEAC provides these details and can be seen as a further step towards better understanding of human-computer-interaction.
Keywords: Human Computer Interaction; Human System Interaction; Interaction Design; Interaction Engineering; Interaction Model
Patterns for Usable Accessible Design BIBAFull-Text 248-257
  Homa Javahery; Michael Gower; Daniel Sinnig; Peter Forbrig
Accessibility barriers exist on most websites and systems, making them difficult to use for individuals with disabilities and other functional limitations. Usable Accessible Design aims to design usable software that addresses the potential needs of all users in the user-centered design process with special consideration for users experiencing functional limitations. This paper showcases how accessibility concerns affect us all and that a proper definition of accessibility goes beyond individuals with disabilities. We then identify existing accessibility standards and guidelines, and propose design patterns as a proactive medium to capture and disseminate best accessibility design practices. The patterns provide usable solutions to specific accessibility problems, within a defined context, that take into account the physical, cognitive and functional limitations of users. Finally we propose a classification scheme for patterns based on usability principles and accessibility heuristics.
From Structural Analysis to Scenarios and Patterns for Knowledge Sharing Applications BIBAKFull-Text 258-267
  Claus Kaelber; Christian Märtin
In this paper we present a pragmatic development approach for knowledge sharing applications that encompasses both design and software engineering aspects. It starts from scenarios and leads to patterns that help application developers and user interface designers on the one hand to separate relevant content from unimportant data and on the other hand propose techniques for qualitatively structuring knowledge management and knowledge sharing tasks for enterprises and individuals.
Keywords: HCI patterns; structural patterns; domain patterns; knowledge sharing; knowledge management; design strategy; GUI generation; pattern-based modeling
A Design Patterns Approach to Adaptive User Interfaces for Users with Special Needs BIBAKFull-Text 268-277
  Matthias Peissner; Andreas Schuller; Dieter Spath
Providing truly accessible user interfaces for a great variety of users still presents a major challenge for software developers. Contrasting from a 'design for all' approach, we present a design patterns based approach for the implementation of adaptive user interfaces for users with special needs. This paper gives an overview of essential requirements of adaptive systems, covering aspects for users as well as system developers. The overall structure, adaption mechanisms, distinctive design pattern types and demonstrative examples of the 'MyUI' design patterns approach are described and illustrated.
Keywords: Adaptive user interface; design patterns; accessibility
User Interface Representation Using Simple Components BIBAKFull-Text 278-287
  Javier Rodeiro Iglesias; Pedro M. Teixeira-Faria
There are several user interface specification models, each other covering several design steps considered on a user interface representation. Two of those steps are the composition and the presentation. This paper shows a study about the steps that are covered by the most known techniques to represent Graphical User Interfaces, focusing mainly in composition and presentation steps. After this, an example of a game is made using DGAUI representation. This game representation is useful to show the real problems when an application is made from abstraction level to a prototype level. This example is useful too as a possible reference system for testing between different representation systems. The conclusion of this paper is that is possible to make a real application with an abstract representation of user interface, using visual simple components and make a prototype from user interface representation.
Keywords: Abstract User Interface Representation; Visual Appearance; User Interface Dialog; DGAUI
Model-Based Ubiquitous Interaction Concepts and Contexts in Public Systems BIBAKFull-Text 288-298
  Thomas Schlegel; Christine Keller
Ubiquitous systems and interaction concepts are increasingly finding their way into public systems like shopping malls, airports, public transport or information kiosks. At the same time, these user interfaces also undergo significant changes. Technologies like multi-touch systems or voice-based interaction are now available to the general public and widely used. In ubiquitous systems, these modalities are often combined, sometimes even dynamically at runtime. This leads to new challenges for the conceptualization and development of ubiquitous user interfaces in public systems, especially where this implies adaptive behavior. We present contexts that possibly influence the interaction with such public systems and describe ways of modeling this interaction integrating context-adaptivity already in the interaction models of public systems. Taking into account the context of the public system and its users, we extend the concept of Interaction-Cases to contain model aspects for different interaction contexts in public systems.
Keywords: Interaction Workflow Modeling; Context; Context Models; Context Adaptivity; Public Systems; Use Cases; Interaction Cases; Interaction Models
Towards Pattern-Driven Engineering of Run-Time Adaptive User Interfaces for Smart Production Environments BIBAKFull-Text 299-308
  Marc Seissler; Kai Breiner; Gerrit Meixner
Model-based development of run-time adaptive user interfaces still poses a complex problem since several models have to be specified and interlinked by the developers. In this paper we present a first concept of a pattern driven development methodology that addresses the reuse of user interface aspects. An XML-based pattern notation is introduced that supports the specification of patterns for different UI core models (room-based Use Model, Dialog Model and Presentation). The pattern notation further separates the pattern interface description from the used model fragments via a pattern interface implementation. This enables the light-weight integration of a pattern application process without touching the used core models' specifications.
Keywords: Model-Based User Interface Development; HCI Pattern; Engineering Run-Time Adaptive User Interfaces; Usability Engineering
Complex Components Abstraction in Graphical User Interfaces BIBAKFull-Text 309-318
  Pedro M. Teixeira-Faria; Javier Rodeiro Iglesias
This paper proposes a structure to increase the level of abstraction in building visual user interfaces, establishing an initial set of features and properties that a system for abstract complex components specification must have. Two approaches of AIOs have been studied: Interactors and ADV. The study was focused on the way in which these techniques manage interaction and presentation of interface objects. In the following section an interface complex component definition is proposed. In section 3.1 a basic set of properties and features for interface complex components are showed. In the last section an analogy between classes and objects in object-oriented programming and interface complex components are presented.
Keywords: Complex Components; Abstract Interaction Objects
User-Oriented Accessibility Patterns for Smart Environments BIBAKFull-Text 319-327
  Michael Zaki; Peter Forbrig
One of the main indicators concerning the usability of an application is the corresponding level of accessibility provided by this application. Although a lot of work has been done in the software engineering domain, the accessibility problem has not been enough tackled in the HCI area. In this paper we present an idea to resolve the user-related accessibility problems since the modeling stage of smart environment applications while being assisted by patterns. The proposed idea is to provide two generic patterns used for any accessibility modeling problem, and additionally the creation of two pattern libraries presenting concrete solutions for the most common user-based accessibility problems.
Keywords: Smart Environments; Bidirectional Information Accessibility; Task Models; Patterns

Cognitive, Psychological and Behavioural Issues in HCI

Visual Hierarchy and Viewing Behavior: An Eye Tracking Study BIBAKFull-Text 331-340
  Soussan Djamasbi; Marisa Siegel; Tom Tullis
Empirical evidence suggests that users often exhibit a viewing pattern that favors the top and left sides of web pages. This viewing pattern may cause users to miss a great deal of information. Grounded in the model of visual hierarchy, this study examines the impact of visual complexity on how users view a page. The results show that users' viewing pattern in our study was more scattered than those reported in previous studies, which used pages with a relatively less complex visual hierarchy. We also examined the impact of browsing and information retrieval on viewing pattern. Such an investigation can provide insight for the design of homepages that can effectively serve both those who browse and those who retrieve information. The results also show that eye tracker can serve as a valuable tool for designers to develop and test new designs.
Keywords: Eye Tracking; Design Science; Visual Hierarchy; Viewing Pattern; Fixations; Home Pages
Cognitive Analysis for Knowledge Modeling in Air Traffic Control Work BIBAFull-Text 341-350
  Satoru Inoue; Hisae Aoyama; Keiichi Nakata
Air Traffic Control systems are a kind of service which allows controllers from the ground to keep aircraft safely separated to avoid collisions. It is important to use cognitive systems for the development of this type of critical system. Systems should not only have high performance functions, but also have better user friendly functions and accessibility. It can be said that we have to analyze the functional elements in the work of systems design. To design more reliable interfaces or training programs for the provision of ATC systems, we need to understand the details of basic functions of air traffic controller's tasks within the system. In this research, we discuss the analysis of ATC tasks and modeling of the knowledge of air traffic controllers. And then, we attempt to formalize the basic knowledge of controllers to help them to have a good understanding of the knowledge structure and logical relations.
Individual Differences in Work Load While Doing Multitasking with a Computer BIBAKFull-Text 351-358
  Kari Kallinen; Inger Ekman; Niklas Ravaja
In the present study we examined the individual differences in work load while doing high and low cognitive load multimodal (audive + tactile or visual + tactile) tasks. We found among other things that participants that are characterized as having high information capacity had lower levels of work load and shorter reactions times during easy and difficult multitask as compared to participant that are characterized as having lower level of information processing capacity.
Keywords: Multitasking; multimodal information; context awareness; cognitive task load; individual differences; tactile; audio
Finding a Relationship between Internet Anxiety and Human Behavior BIBAFull-Text 359-367
  Santosh Kumar Kalwar; Kari Heikkinen; Jari Porras
This chapter introduces a relationship between Internet anxiety and human behavior. The Internet has become an avenue for service provision, third-party applications, connectivity and social media. Thus, a clear understanding and comprehensive description of the relationship between Internet anxiety and human behavior becomes essential. The objective of this paper is to provide an assessment of the behavior and anxiety patterns of different age groups on the Internet. The study contributes to knowledge on human behavior and Internet anxiety. The preliminary investigation was realized with a small number of participants using qualitative research methodologies, including a structured themed interview. The result indicates that participants felt more anxiousness on Internet time delay anxiety, Experience anxiety, and Net Search anxiety.
Human Behavioral Simulation Using Affordance-Based Agent Model BIBAKFull-Text 368-377
  Namhun Kim; Jaekoo Joo; Ling Rothrock; Richard A. Wysk; Young-Jun Son
In this paper, we propose a novel agent-based simulation modeling of human behaviors. A conceptual framework of human behavioral simulation is suggested using the ecological definition of affordances in order to mimic perception-based human actions interacting with the environment. A simulation example of a 'warehouse fire evacuation' is illustrated to demonstrate the applicability of the proposed framework. The perception-based human behaviors and planning algorithms are adapted and embedded within human agent models using the Static and Dynamic Floor Field Indicators, which represent the evacuee's prior knowledge of the floor layout and perceivable information of dynamic environmental changes, respectively. The proposed framework is expected to capture the natural manners in which humans participate in systems and enhance the simulation fidelity by incorporating cognitive intent into human behavior simulations.
Keywords: Human Behavior; Affordance Theory; Finite State Automata; Agent-based Modeling; Simulation
Investigating the Effects of Metacognition in Dynamic Control Tasks BIBAKFull-Text 378-387
  Jung Hyup Kim; Ling Rothrock; Anand Tharanathan; Hari Thiruvengada
Metacognition is a broadly studied concept in cognitive science, educational psychology and developmental psychology. Prior research on metacognition shows that successful learning is often based on specific metacognitive activities which have to be frequently monitored during learning [1]. An important limitation in prior studies is that most experimental tasks were designed within static environments. Only rarely have researchers investigated metacognition during dynamic decision making. Therefore, the purpose of this research is to investigate the significance of metacognition while training to execute dynamic control tasks. Findings from this study demonstrate that the experimental group which was provided more focused feedback had higher situation awareness accuracy, relative to the groups which received relatively less focused feedback or no feedback. In addition, results indicated that metacognitive behaviors which were measured using subjective ratings of Pre and Post Meta probes showed different patterns. Preliminary findings provides evidence that enhanced metacognition has a significant impact on actual situation awareness in dynamic control tasks. Detecting causes for these changes is the next step of the research.
Keywords: Metacognition; Human Performance; Human-in-the-loop-simulation; Situation Awareness
The Effects of Personality Type in User-Centered Appraisal Systems BIBAKFull-Text 388-396
  Zacharias Lekkas; Nikos Tsianos; Panagiotis Germanakos; Constantinos Mourlas; George Samaras
The basic objective of this paper is to make an extensive reference of a combination of concepts and techniques coming from different research areas, Psychology and Web personalization technologies, both of which focus upon the user. It has been attempted to approach the theoretical considerations and technological parameters that can provide the most comprehensive user profile, under a common filtering element, supporting the provision of the most apt and optimized user-centered web-based result. It further underpins the significance of the comprehensive user profile that incorporates not only the traditional user characteristics, but other intrinsic values of the user such as user psychological preferences (affect, personality and emotional processing parameters). Eventually, this paper introduces our first experimental results that concern the concept of personality and its effect on decision making and problem solving user profiles.
Keywords: Personality; emotion; personalization; decision-making; problem solving; learning
Measuring Corrective Reaction Time with the Intermittent Illumination Model BIBAKFull-Text 397-405
  Jui-Feng Lin; Colin G. Drury; Chin-Mei Chou; Yu-De Lin; Yi-Quan Lin
The main objective of this research was to develop a methodology based on Drury's [1] intermittent illumination model to directly measure individuals' corrective reaction times, without the two methodology-related issues of Lin & Drury [2]. Six highly-practiced participants performed self-paced circular tracking tasks by using a modified LED monitor in a darkened room. While performing movements, the monitor's backlight was intermittently turned on and off to generate five values of expected delay of visual feedback. Expected delay and measured speed were used with the intermittent illumination model to calculate individuals' corrective reaction times. The results of showed that the model fitted the data very well, accounts for at least 94.6% of the variance. The mean corrective reaction time was 273 milliseconds and ranged from 170 to 460 milliseconds for individual participants. While previous studies only reported group means, this was the first study to report individuals' corrective reaction times.
Keywords: corrective reaction time; intermittent illumination model; hand-control movement; tracking movement
Psychometric Evaluation with Brain-Computer Interface BIBAKFull-Text 406-413
  Paolo Perego; Anna Carla Turconi; Chiara Gagliardi; Giuseppe Andreoni
Brain-Computer Interfaces (BCIs) are systems which can provide people affected by severe neuromuscular diseases with a new and easy way to communicate with the world. The aim of this study is to use a new administration method based on BCI technology to assess cognitive ability in disabled people. The protocol was applied on 15 subjects who can't or have difficult using traditional paper based test. The method, based on a SSVEP BCI system, was previously validated on 20 healthy subjects. The previous validation and the test results on disabled patient show the reliability of BCI in administering cognitive test; BCI doesn't affect results but adds further data that can be used to analyze other cognitive tasks in addition to those measured by the test.
Keywords: Brain Computer Interface (BCI); Steady State Visual Evoked Potential (SSVEP); psychometric assessment; Raven test
An Inductive Inference Model to Elicit Noncompensatory Judgment Strategies BIBAFull-Text 414-422
  Jing Yin; Ling Rothrock
The proposed research developed a noncompensatory policy capturing technique to infer judgment rules (represented in disjunctive normal form) from available human data. The rule induction algorithm employs multiobjective Genetic Algorithm (GA) as its central search mechanism to enhance the induction and classification process. The quality of the induced rule set is measured by two criteria, fidelity (the degree to which the rule set reflects the judgment data they have been extracted from) and compactness (the simplicity of the rule set). An experimental study is conducted to demonstrate the effectiveness of the algorithm on a number of benchmark datasets.
A User-Friendly Tool for Detecting the Stress Level in a Person's Daily Life BIBAKFull-Text 423-431
  Irene Zaragozá; Beatriz Rey; Cristina Botella; Rosa María Baños; Inés Moragrega; Diana Castilla; Mariano Alcañiz Raya
Mental health care represents over a third of the cost of health care to all EU nations and, in USA, it is estimated to be around the 2.5% of the gross national product. Depression and Stress related disorders are the most common mental illnesses. The European project OPTIMI will develop tools to make predictions through the early identification on the onset of the disease. In this paper, we present a user-friendly application developed in the OPTIMI project to detect the stress level in a person's daily life. The results of a first usability study of this application are also presented.
Keywords: mental health; usability; depression; stress detection; prevention
"How Do I Line Up?": Reducing Mental Transformations to Improve Performance BIBAKFull-Text 432-440
  Guy W. Zimmerman; Dale S. Klopfer; G. Michael Poor; Julie Barnes; Laura M. Leventhal; Samuel D. Jaffee
Mobile devices and visual-spatial presentations of information are pervasive, especially for tasks in which the mobile device can be moved to close proximity of the task. This mobility allows the user to offload mental workload by allowing physical transformations of the device. In this study, we compared a fixed mobile device, a non-fixed mobile device, and a fixed desktop display to determine the effects imposed by the mental workload of transforming the frames of reference into alignment. Our results indicate that allowing the user to manipulate the device's position can influence performance by reducing the need for mental transformations.
Keywords: Mobile Device; Usability; 3D Models; Frames of Reference

Development Methods, Algorithms, Tools and Environments

A Middleware Architecture for Designing TV-Based Adapted Applications for the Elderly BIBAFull-Text 443-449
  Carlos Gacimartín; José Alberto Hernández; David Larrabeiti
The elderly are beginning to use more and more new technologies, although several times they find these are difficult to interact with, especially when they are accessed by a keyboard or the screen is too small.
   This work proposes a middleware architecture for TV-based applications for the elderly, with a focus on social interaction services like webmail. The elderly feel very confident with their TVs since it is something they use on a daily basis, and the screen is sufficiently large. The architecture contains a Context Manager with an Ontology that models the elderly user impairments and actual context information collected from sensors located at the user's home, and an Interface Adaptation Engine which generates the adapted interface for a particular user, according to his profile and context of use. This architecture is part of an ongoing EU funded project: MyUI and a first prototype is expected by mid 2011.
Performance Visualization for Large-Scale Computing Systems: A Literature Review BIBAKFull-Text 450-460
  Qin Gao; Xuhui Zhang; Pei-Luen Patrick Rau; Anthony A. Maciejewski; Howard Jay Siegel
Recently the need for extreme scale computing solutions presents demands for powerful and easy to use performance visualization tools. This paper presents a review of existing research on performance visualization for large-scale systems. A general approach to performance visualization is introduced in relation to performance analysis, and issues that need to be addressed throughout the performance visualization process are summarized. Then visualization techniques from 21 performance visualization systems are reviewed and discussed, with the hope of shedding light on the design of visualization tools for ultra-large systems.
Keywords: performance visualization; performance monitoring; information visualization
Developing a User Recommendation Engine on Twitter Using Estimated Latent Topics BIBAKFull-Text 461-470
  Hiroyuki Koga; Tadahiro Taniguchi
In recent years, microblogging is popular among people and informal communication becomes important in various communities. Therefore, a number of Web communication tools are developed to facilitate informal communication. In this paper, focusing on microblogging service, Twitter, we develop a user recommendation engine which extracts latent topics of users based on followings, lists, mentions and RTs. This recommendation algorithm is based on Latent Dirichlet Allocation (LDA) and KL divergence between two users' latent topics. This algorithm hypothesizes that the users have latent connection if the distance calculated by KL divergence is short. Additionally, we performed an experiment to evaluate the effectiveness of the algorithm, and this showed that there is correlation between the distance and user's preference obtained through questionnaire.
Keywords: LDA; Twitter; Information Recommendation
Project and Development of ErgoCoIn Version 2.0 BIBAKFull-Text 471-479
  Marcelo Morandini; Roberto Leite de Moraes Rodrigues; Marcus Vinicius Cerrato; Marcos Lordello Chaim
Usability evaluation (UE) methods may have several purposes: identify and diagnose usability problems; evaluate the implementation, comparing the one under evaluation with other systems, and also perform acceptance test. These methods are usually expensive, time-consuming and complex. In this context, the ErgoCoIn 1.0 has being used as an accessible system that can be used by several people all over the world, even if they are not usability experts or evaluators. This paper aims to present a new version of this environment considering that its basic objective is to propose a higher quality for the questions. Additionally, a new presentation questionnaire window small enough to be used both in web browsers and mobile devices is proposed.
Keywords: Usability Evaluation; Checklist; Automation
A Reference Model for Adaptive Visualization Systems BIBAKFull-Text 480-489
  Kawa Nazemi; Christian Stab; Arjan Kuijper
One key issue of both Information Visualization as well as Adaptive User Interfaces is information overload. While both disciplines have already devised well performing algorithms, methods and applications, a real merging has not taken place yet. Only a few attempts bring the surplus values of both disciplines together, whereas a fine-grained investigation of visualization parameterization is not investigated. Today's systems focus either on the adaptation of visualization types or the parameterization of visualizations. This paper presents a reference Model for Adaptive Visualization Systems (MAVS) that allows the adaptation of both the visualization type and the visualization parameterization. Based on this model, a framework for the adaptive visualization of semantics data will be derived. A use case describing the interaction with an "adaptive visualization cockpit" covering different visualization metaphors concludes the paper.
Keywords: Adaptive Visualization; Information Visualization; Intelligent Visualization; Visualization Reference Model; Ontology Visualization
A Proposal of an Interactive Music Composition System Using Gibbs Sampler BIBAKFull-Text 490-497
  Akira Shirai; Tadahiro Taniguchi
In this paper, we propose a novel method for generating a melody from a generative probabilistic model by using Gibbs sampler. Furthermore, users can modify the composed music by interacting with the generation process. This method enables users to create their favorable melodies. Recently, music composition using computer software is gathering attentions. Many people want to compose their original music. However, musical composition is still too difficult for beginners to obtain their favorable original music. Our system highly supports such people easy to create own music. We also evaluate the probabilistic music composition method by several experiments.
Keywords: automatic music composition; interactive system; probabilistic model
Sensing User Needs: Recognition Technologies and User Models for Adaptive User Interfaces BIBAKFull-Text 498-506
  Barnabás Takács; Lajos Simon; Matthias Peissner
In this paper we introduce the notion of a Virtual User Lab that employs virtual reality tools to simulate End-Users in realistic application scenarios in order to help industrial designers and application developers to create and test adaptive interfaces that evolve as users' preferences and potential handicaps are discovered. We describe key elements of the VUL, discuss computer vision-based algorithms for facial information processing to understand user behavior and present an email-reading scenario to better highlight the system's adaptive capabilities and practical usability.
Keywords: User interface adaptation; facial information processing; virtual human interface
uPlatform: A Customizable Multi-user Windowing System for Interactive Tabletop BIBAKFull-Text 507-516
  Chenjun Wu; Yue Suo; Chun Yu; Yuanchun Shi; Yongqiang Qin
Interactive tabletop has shown great potential in facilitating face-to-face collaboration in recent years. Yet, in spite of much promising research, one important area that remains largely unexplored is the windowing system on tabletop, which can enable users to work with multiple independent or collaborative applications simultaneously. As a consequence, investigation of many scenarios such as conferencing and planning has been rather limited. To address this limitation, we present uPlatform, a multi-user windowing system specifically created for interactive tabletop. It is built based on three components: 1) an input manager for processing concurrent multi-modal inputs; 2) a window manager for controlling multi-user policies; 3) a hierarchical structure for organizing multi-task windows. All three components allow to be customized through a simple, flexible API. Based on uPlatform, three systems, uMeeting, uHome and uDining are implemented, which demonstrate its efficiency in building multi-user windowing systems on interactive tabletop.
Keywords: tabletop; multi-user; windowing system; window management
Synchronization and Fluctuation of Rhythm in Musical Cooperative Performance BIBAKFull-Text 517-526
  Tomohito Yamamoto
A live musical performance gives us better impression than recorded music heard from a portable music player. From player's point of view, live performance also gives better impression than playing music with metronome or recorded music. Thus, the difference exists between the live musical performance and the recorded performance that doesn't change in real time. In this research, to clarify the difference, the cooperative performance of the drum and the bass was analyzed from a rhythmical aspect. The results showed that synchronization error between musical rhythms, and fluctuation of musical rhythm became smaller in cooperated performance than in the performance with recorded music.
Keywords: Music; Rhythm; Synchronization; Fluctuation; Cooperative Performance
GMM Parameter Estimation by Means of EM and Genetic Algorithms BIBAKFull-Text 527-536
  Sergey Zablotskiy; Teerat Pitakrat; Kseniya Zablotskaya; Wolfgang Minker
Most of the state-of-the-art speech recognition systems use Hidden Markov Models as an acoustic model, since there is a powerful Expectation-Maximization algorithm for its training. One of the important components of the continuous HMM we focus on is an emission probability which can be approximated by the weighted sum of Gaussians. Although, EM is a very fast iterative algorithm it can only guarantee a convergence to a local result. Therefore, the initialization process determines the final result. We suggested here two modifications of genetic algorithms for the initialization of EM. They are compared to the results of the EM with the same number of local multi-starts.
Keywords: Hidden Markov Model; Gaussian Mixture Model; Expectation-Maximization

Image Processing and Retrieval in HCI

Shape-Based Human Actions Recognition in Videos BIBAKFull-Text 539-546
  Nitish Amraji; Lin Mu; Mariofanna G. Milanova
The paper presents a system for human action recognition using contour based shape representation. With the rapid progress of computing and communication technology smart user computer interfaces are becoming most widespread. A major goal is to go further than traditional human computer interaction (like mouse or keyboard) and to find more natural means of interaction with computers, including the application of computer games and surveillance. The objective of this work is to achieve representation eigenspace for modeling and classifying actions performed by individuals. Eigenspace is the subspace for each type of action. A representation eigenspace approach based on the Principal Component Analysis (PCA) algorithm is used to train the classifier. Behaviors are classified with respect to a predefined set of learning actions. The key points of this approach include the mode silhouettes are extracted from video, the kind of shape descriptor used, the development of the new eigenspace and the kind of classification used. Performance of the system is expressed in terms of percentage of right or wrong classifications.
Keywords: Human Activity Recognition; Fourier Descriptor; Principal Component Analysis
Dynamic Queries with Relevance Feedback for Content Based Image Retrieval BIBAKFull-Text 547-554
  Murat Birinci; Esin Guldogan; Moncef Gabbouj
A novel relevance feedback scheme utilizing dynamic queries for content based image retrieval systems is proposed, where the retrieval results are updated instantly based on the user's feedback. The user is expected to label at least one image as positive or negative, revealing the gist of the expected retrieval results. Then the retrieval results are updated dynamically, without any further user interaction, based on the similarity of the query and the selected image in different feature spaces increasing the semantic accuracy of the retrieval. The proposed method not only invalidates the drawbacks of current relevance feedback systems in terms of user experience, but also provides an innovative stand point for the relevance feedback scheme as well.
Keywords: dynamic queries; relevance feedback; content based image retrieval
Face Sketch Synthesis via Multivariate Output Regression BIBAKFull-Text 555-561
  Liang Chang; Mingquan Zhou; Xiaoming Deng; Zhongke Wu; Yanjun Han
This paper presents a multivariate output regression based method to synthesize face sketches from photos. The training photos and sketches are divided into small image patches. For each pairs of photo patch and its corresponding sketch patch in training data, a local regression model is built by multivariate output regression methods such as kernel ridge regression and relevance vector machine (RVM). Compared with commonly used single-output regression, multivariate output regression can enforce the synthesized sketch patches with structure constraints. Experiments are given to show the validity and effectiveness of the approach.
Keywords: Face sketch synthesis; multivariate regression
Experimental Studies of Visual Models in Automatic Image Annotation BIBAKFull-Text 562-570
  Ping Guo; Tao Wan; Jin Ma
Semantic image annotation can be viewed as a mapping procedure from image features to semantic labels, by the steps of image feature extraction and image-semantic mapping. The features can be low-level visual features, such as color, texture, shape, etc., and the semantic labels can be related to the knowledge of human on the image understanding. However, these linear representations are insufficient to describe the complex natural scene. In this paper, we study currently existing visual models that are able to imitate the way the human visual system acts for the tasks of object recognition and scene interpretation. Therefore, it is expected to bring a better understanding to the image visual content in human cortex will. In the experiments, there are three state-of-the-art visual models are investigated for the application of automatic image annotation. The results demonstrate that with our proposed strategy, the annotation accuracy is improved comparing to the most used low-level linear representation features.
Keywords: Automatic image annotation; Semantics; Visual models; Human visual system; Low-level features
An Image Segmentation Method for Chinese Paintings by Combining Deformable Models with Graph Cuts BIBAKFull-Text 571-579
  Ning He; Ke Lu
In recent years researchers have developed many graph theory based algorithms for image segmentation. However, previous approaches usually require trimaps as input, or consume intolerably long time to get the final results, and most of them just consider the color information. In this paper we proposed a fast object extraction method. First it combines deformable models information with explicit edge information in a graph cuts optimization framework. we segment the input image roughly into two regions: foreground and background. After that, we estimate the opacity values for the pixels nearby the foreground/background border using belief propagation (BP). Third, we introduce the texture information by building TCP images' co-occurrence matrices. Experiments show that our method is efficient especially for TCP images.
Keywords: Graph cuts; Deformable Model; Traditional Chinese Painting (TCP); Belief Propagation (BP); Po-Occurrence Matrix
Image Skeletonization Based on Curve Skeleton Extraction BIBAFull-Text 580-587
  Xiaoyan Hu; Bo Sun; Huiqin Zhao; Bin Xie; Hao Wu
Skeletonization is a transformation of an object in a digital image into a simplified representation of the original object. The skeleton of an image object is an abstraction of the original object which largely preserves the extent and connectivity of the original region while throwing away most of the boundary and interior pixels. In this paper, we propose a new method to calculate skeleton from 3D space instead of image space which has only two dimensions. Our method start with a contour of an object in an image, then inflate this two dimensional shape to a three dimensional mesh, and then apply a 3D mesh curve skeleton extraction algorithm to this intermediate three dimension mesh model. Finally, we project the resulting 3D curve skeleton back to image space and get the skeleton of the original shape or object in the image. Our method is noise insensitive. A little perturbation on shape would not change the structure of the resulting skeleton. Our method is relatively fast because it only generates a geometry mesh in contrast to compute a Voronoi graph. Our method preserves the topology as well as the shape.
Appearance Similarity Index for Medicinal Ampoule Labels BIBAKFull-Text 588-597
  Masaomi Kimura; Yutaroh Furukawa; Akira Kojo; Hirotsugu Ishida; Keita Nabeta; Michiko Ohkura; Fumito Tsuchiya
Since there are many ampoule injection medicines, it is important to make their labels easily distinguishable because confusing labels may lead to fatal accidents caused by administering the wrong medicine by mistake. In this paper, we utilize Fourier series expansion and wavelet transformation to extract the characteristics in labels and propose an index to measure similarity that we feel toward ampoule labels to prevent confusion in label designs. We also discuss a way of parameterizing colors.
Keywords: Medicinal safety; Ampoule labels; Fourier analysis; Wavelet analysis
A Novel Parallel Clustering Algorithm Based on Artificial Immune Network Using nVidia CUDA Framework BIBAKFull-Text 598-607
  Ruiyi Luo; Qian Yin
In this paper, a novel parallel data clustering algorithm based on artificial immune network aiNet is proposed to improve its efficiency. In consideration of the restrictions of GPU, we carefully designed the data structure, algorithm flow and memory allocation strategy of the parallel algorithm and realized it using NVIDIA's CUDA framework. During the implementation, in order to fully explore its implicit parallelism, we allocated threads on GPU that represent the network cells of aiNet, and modified this algorithm to let those thread operations parallel during the clustering process. We calculated the affinity parallel, combined the random numbers with the local search algorithm to select the first n cell parallel, and did the network suppression parallel. Experimental results show that certain speedup can be obtained by using the proposed method.
Keywords: artificial immune network; aiNet; clustering; parallel; GPU
A Detection Method of Basic Mouth Shapes from Japanese Utterance Images BIBAKFull-Text 608-617
  Tsuyoshi Miyazaki; Toyoshiro Nakashima; Naohiro Ishii
Some distinctive mouth shapes are formed when Japanese words and phrases are uttered. Because people who have acquired a skill of Japanese lip-reading know these characteristics, they can read lips movement. To realize the machine lip-reading, we propose a method which detects the distinctive mouth shapes from Japanese-speaking images based on their techniques. We define six mouth shapes as the distinctive mouth shapes, and the mouth shape images are used as template images. To detect the mouth shapes in utterance images, template matching is applied. Waveforms of similarity which are calculated by the template matching show some characteristic forms. Thus, we detect the mouth shapes from the waveforms. We carry out some experiments using Japanese words, and confirm effectiveness of the proposed method from the results.
Keywords: Lip-reading; Japanese phoneme; Template matching
Improving the Usability of Hierarchical Representations for Interactively Labeling Large Image Data Sets BIBAKFull-Text 618-627
  Julia Moehrmann; Stefan Bernstein; Thomas Schlegel; Günter Werner; Gunther Heidemann
Image recognition systems require large image data sets for the training process. The annotation of such data sets through users requires a lot of time and effort, and thereby presents the bottleneck in the development of recognition systems. In order to simplify the creation of image recognition systems it is necessary to develop interaction concepts for optimizing the usability of labeling systems. Semi-automatic approaches are capable of solving the labeling task by clustering the image data unsupervised and presenting this ordered set to a user for manual labeling. A labeling interface based on self-organizing maps (SOM) was developed and its usability was investigated in an extensive user study with 24 participants. The evaluation showed that SOM-based visualizations are suitable for speeding up the labeling process and simplifying the task for users. Based on the results of the user study, further concepts were developed to improve the usability.
Keywords: Self-organizing map; SOM; user study; image labeling; ground truth data
The Similarity Index of Character Shape of Medicine Names Based on Character Shape Similarity (II) BIBAKFull-Text 628-636
  Keita Nabeta; Akira Hatano; Hirotsugu Ishida; Masaomi Kimura; Michiko Ohkura; Fumito Tsuchiya
The similarity of drug names in Japanese such as 'アマリール' (Amaryl) and 'アルマール' (Almarl) causes confusion over drug names and can lead to medical errors. In order to prevent such errors, methods of computing their similarity have been proposed. However, there are no studies that take account of character shape similarity quantitatively. In a previous study, we calculated the character shape similarity by template matching technique and proposed a method of measuring medicine name similarity based on it. Although we obtained a high correlation coefficient between the medicine name similarity values and subjective evaluation, we observed some character pairs that are not similar. In this study, we improved the method of computing the character shape similarity based on the characteristic points of character and compared it with advanced methods.
Keywords: Medicine name similarity; Medical safety; Character shape similarity
ColoriT: Color Based Image Code Application to Aid in Memory Restoration of Offline Photo Artifacts BIBAKFull-Text 637-642
  James Park; Jonghoon Seo; Ji-Hye Choi; Tack-Don Han
Many areas of research have applied memory aid applications to help users remember experiences or enhance learning abilities. Relatively little study however has been done on the use of color based image code as a memory aid. In fact much of what is in use by mainstream media and businesses use mobile barcodes such as 2D image code like Quick Response (QR) code and Microsoft Tag for accessing online content. Part of the freedom of using mobile code is many formats are freely based image code and have accessible API and development kits. Only few are licensed based and are limited to developing usable applications. We investigate a proprietary licensed color based image code using an application we developed called ColoriT (pronounced Color-ət) in hopes of studying its applicability to enhance memory aid when viewing photo artifacts. ColoriT is a simple photo memory tagging concept used to tag offline photos in a pervasive and natural way. By enhancing the user's ability to tag offline photos with memory artifacts we create a tool inspired by storytelling to improve memory aid and overall enjoyment of looking at photos.
Keywords: Memory aid; 2D barcode; ColorCode; Sound artifacts; Color
A Configurable Photo Browser Framework for Large Image Collections BIBAKFull-Text 643-652
  Frode Eika Sandnes
Image collections are growing at an exponential rate due to the wide availability of inexpensive digital cameras and storage. Current browsers organize photos mostly chronologically, or according to manual tags. For very large collections acquired over several years it can be difficult to locate a particular set of images -- even for the owner. Although our visual memory is powerful, it is not always easy to recall all of one's images. Moreover, it can be very time consuming to find particular images in other peoples image collections. This paper presents a prototype image browser and a plug-in pattern that allows classifiers to be implemented and easily integrated with the image browser such that the user can control the characteristics of the images that are browsed and irrelevant photos are filtered out. The filters can both be content based and based on meta-information. The current version is only employs meta-information which means that large image collections can be indexed efficiently.
Keywords: Photo browsing; content based image retrieval; meta-information
Imaged Based Codes Performance Comparison for Mobile Environments BIBAKFull-Text 653-659
  Jonghoon Seo; Ji-Hye Choi; Tack-Don Han
By spreading of smart phones, mobile barcodes are used widely. However, there are so many 2D barcodes to be available. So, it is important to compare those mobile barcodes. In this paper we performed decoding performance comparison between popular mobile barcodes. ColorCode is using color information to get information. So it shows most improved performance in distance and size. Also, it can provide magnifying decoding mode, and it shows more enhancing result.
Keywords: 2D Barcode; Image based Code
A Global Optimal Algorithm for Camera Calibration with One-Dimensional Objects BIBAFull-Text 660-669
  Liang Wang; Fuqing Duan; Chao Liang
The emergent one-dimensional (1D) calibration is very suitable for multi-camera calibration. However its accuracy is not satisfactory. Conventional optimal algorithms, such as bundle adjustment, do not perform well for the non-convex optimization of 1D calibration. In this paper, a practical optimal algorithm for camera calibration with 1D objects using branch and bound framework is presented. To obtain the optimal solution which can provide ε-optimality, tight convex relaxations of the objective functions are constructed and minimized in a branch and bound optimization framework. Experiments prove the validity of the proposed method.
LSCM Based Non-rigid Registration for Craniofacial Surfaces BIBAKFull-Text 670-676
  Wenkui Xie; Fuqing Duan; Qingqiong Deng; Mingquan Zhou; Zhongke Wu; Liang Chang
The Least Squares Conformal Maps (LSCM) is an approximation of the conformal mapping in the least-squares sense, and it can map the corresponding feature points on two 3D surfaces into the same 2D location. This paper proposes a non-rigid registration method for craniofacial surfaces based on LSCM parameterization. Firstly, craniofacial surfaces are normalized in pose and scale by using a unified coordinate system. Secondly, by pinning six landmarks, which include the outer corners of the eyes, two corners of the mouth, two side points of the nose wing, each craniofacial surface is mapped into a nearly equal 2D domain by using LSCM. Finally, an iso-parameter mesh of each craniofacial surface can be obtained by 2D to 3D mapping, which establishes a unique correspondence among different craniofacial surfaces. To evaluate the proposed method, the target surface is deformed into the reference surface using TPS algorithm with dense correspondences being control points, and then the sum of the distance between two correspondence point sets are computed, and vice versa. According to the average distance, the proposed method is compared with ICP and a TPS based method. The comparison shows that the proposed approach is more accurate and effective.
Keywords: non-rigid registration; LCSM; craniofacial surface
High-Quality Fast Image Upsampling Algorithm Based on CUDA BIBAKFull-Text 677-683
  Qingqing Xu; Xin Zheng; Jie Chen
Although many upsampling methods have been proposed, but no method can get result images with satisfactory quality in real-time. In this paper, we propose a CUDA based image upsampling algorithm, which can generate sharp edges with reduced grid-related artifacts efficiently. By analyzing existing method, we find chock points which confine the efficiency of the algorithm mostly and use CUDA to accelerate our algorithm and improve the implementation model of the algorithm. In this way we not only guarantee the quality of the result image, but also realize the purpose of a real-time human-computer interaction. Experimental results show that our method can get high-quality upsampled images efficiently.
Keywords: image upsampling; CUDA; large-scale data parallel computing; image interpolation; super-resolution
A Cubic Polynomial Model for Fisheye Camera BIBAKFull-Text 684-693
  Haijiaing Zhu; Xiupu Yin; Jinglin Zhou
In this paper, we present a cubic polynomial model for fisheye camera by using the lifting strategy, which point coordinates in low dimensional space is lifted to a vector in high dimensional space. In contrast to the lifting strategies reported, our lifting strategy is to let 3D point coordinates appear in higher order polynomials. This paper displays that the cubic polynomial model can effectively express the fisheye image points as the cubic polynomial of world coordinates. Thus this allows a linear algorithm to estimate the nonlinear models, and in particular offers a simple solution to estimate the nonlinear between 3D point and its corresponding fisheye image points. Experimental results with synthetic data and real fisheye images show that the fisheye camera is modeled approximately through the cubic polynomial.
Keywords: Cubic polynomial model; the lifting strategy; fisheye camera