Wang Hongan

Shape Filling Rate for Silhouette Representation and Recognition

Research on complex shape recognition showed that the shape context algorithm is sensitive to relative position variation of articulation. Aimed at this problem, a shape recognition method is proposed based on local shape filling rate of various object silhouettes. We take each landmark point as a circle center and use as its radius. Then, under a particular radius, the ratio between the covered silhouette pixels and the total pixels is defined as local shape filling rate. Thus, different radius may form different local shape filling rates. All landmark points with different radius will constitute a characteristic matrix which can effectively reflects the entire statistical property of the object shape. Experiments on a variety of shape databases show that the novel method is insensitive to articulation and less influenced by the number of landmark points, so our algorithm has strong power in describing object details.

Design and implementation of a graphical programming tool for children

Since the computer is more widely used by children, the existing software for childrens amusement and study are not able to satisfy their needs any longer. To solve this problem, a kind of graphical programming language for children is proposed in the paper. We analyze the design principles of graphical programming language for children, and implement ten types of common graphical blocks, integrating the basic knowledge of object oriented programming. We also provide the function to bridge the gap between graphical and text programming. Additionally, we designed and developed a graphical programming tool - KidPipe based on Pen Interaction. Finally, a user study is carried out to verify reliability and usability of KidPipe.

Video sketch summarization, interaction and cognition analysis

Video, as one typical digital media, is important for message communication. For efficient video content visualization and natural interaction such as video browsing and searching, we propose a sketch-based video summarization with fluent sketch interaction in this paper. Firstly, we present the sketch representation for video semantics, which takes the advantages of abstractness and generality of sketches. The concept of semantic sketch is proposed, which supports annotating video contents with sketches. Furthermore, an optimized layout algorithm for sketch summarization is presented. Secondly, we present the interaction techniques for sketch summarization and natural sketch gesture operations. From the viewpoint of cognitive psychology, we analyze the sketch representation, as well as the effects and relations of cognitive units in sketch interaction. Finally, user studies show that the proposed sketch summarization and sketch interaction improve user efficiency in terms of acquiring the main video content and reduce users’ cognitive load.

Synthesis Vis: A Web Site Supporting Collaborative Information Visualization

This paper describes the design and deployment of Synthesis Vis, an intranet web site where various users may contribute data, create interactive visualizations, and share visualizations. The goal of the site is to support collaboration around information visualizations at a large scale by fostering a social style of design process. Moreover, the site serves as a collaborative information visualization tool for individuals, providing a medium to share visualizations among users. To support this goal, the site includes novel mechanisms for enduser creation of visualizations and collaboration in the design process of those visualizations. The early usage of Synthesis Vis verifies the design and deployment of Synthesis Vis for collaborative information visualization.

A model for natural human-computer interaction based on semiotic triangle

In the development and application of cognitive science and ubiquitous computing, the method of building and evaluating a natural user interface has become increasingly important. In this paper, based on the definition of natural human-computer interaction, we highlight the necessity of the use of natural language between user and computers and its comprehension. Moreover, based on the semiotic triangle model of linguistics, we propose a model for natural human-computer interaction. The model can provide an explanation of how information is transmitted between the user and computers and understood. Finally, we present an approach for evaluating the user interface based on interaction naturalness, continuity, and learnability.

Multimodal aided neurological disease diagnosis with synergy of cloud and client

The dominating physiological characteristics of neurological diseases are reflected in patients daily behaviors. The aided diagnosis and early warning of neurological diseases will benefit from obtaining and analyzing related physiological information generated during the interaction process. Traditional systems for detecting neurological conditions only analyze a single interaction modal, which may lose important features contained in other modalities. Based on the above, we propose a multi-modal aided neurological disease diagnosis system with synergy of cloud and client. First, we propose an automatic disease diagnosis method based on multi-modal information; users physiological information collected from multiple modals is then analyzed and the results are integrated to improve accuracy and robustness. Second, a framework of cloud-client synergy is proposed that stores the users physiological information from different regions and different times in the cloud, thus reducing the geographical restrictions and time constraints of data collection. Third, based on the powerful computing capacity, the system can make real-time and precise automatic diagnosis by analyzing multi-modal physiological information produced by users during natural interaction. Finally, the effectiveness of this multi-modal method for diagnosing aided neurological diseases based on cloud-client synergy is verified by using a hybrid diagnostic system of voice and pen.