WSCG ’2008: Poster Proceedings
Permanent URI for this collection
Browse
Recent Submissions
Item Video high-level semantic recognizing(Václav Skala - UNION Agency, 2008) Zeng, Cheng; Liu, Xiaozhu; Li, Jun; Dan, Feng; Skala, VáclavThis paper presents an event semantic recognizing method based on Markov chain by stages, which takes object semantic as the bridge and is valid for recognizing complex event semantic. Semantic concept mapping mechanism based on semantic template is used to realize the automatic recognition of video semantic. In the experiment contrasting with IMAT system, our method shows more extensive recognition range and higher accuracy. Experimental results are encouraging, and indicate that the performance of the proposed approach is effective.
Item An unified user dynamic interest description model(Václav Skala - UNION Agency, 2008) Zeng, Cheng; Wang, Hui; Cao, Haiping; Zhang, Ying; Skala, VáclavThe amount of information available world-wide and its network-based linkage will continue its rapid growth in the foreseeable future. It is urgent that we need a new retrieval mode to span the gap between information explosion and user requirement. This paper reports an user interest mining method based on cross-media and a unified model which describes user’s dynamic interest changing through time to overcome the contradiction between short-time interest and long-time interest description in traditional methods. We also present a developing personalized retrieval system FizZ which mines user’s interest by installing IE plug-in.Item Classification of cell nuclei using shape and texture indexes(Václav Skala - UNION Agency, 2008) Thibault, Guillaume; Devic, Caroline; Horn, Jean-François; Fertil, Bernard; Sequeira, Jean; Mari, Jean-Luc; Skala, VáclavIn this paper, we present a study on the characterization and the classification of binary digital objects. This study is performed using a set of values obtained by the computation of "shape and texture indexes". To get the shape indexes, we extract a set of data called "measures" from 2D shapes, like for example surface and perimeter. These indexes are then used as parameters of a function returning a real value that gives information about geometrical and morphological features of the shape to analyze. A model characterizing the shape (and the texture) of objects is subsequently built. An application to the classification of cell nuclei (in order to diagnose patients affected by the Progeria syndrome) is proposed.Item 3D-face model reconstruction utilizing facial shape database from multiple uncalibrated cameras(Václav Skala - UNION Agency, 2008) Takeuchi, Toshio; Saito, Hideo; Mochimaru, Masaaki; Skala, VáclavIn recent years, a surveillance camera has come to be attached in various places from a rise of the consciousness to security. Since the surveillance cameras are installed in variety of place, it is possible to take a picture of the same person from multiple uncalibrated cameras though it is asynchronous. In this article, we propose a method for reconstructing a face shape from multiple-view images taken with non - synchronous multiple cameras. In this method, we do not directly reconstruct the shape, but estimate a small number of parameters which represent the face shape. The parameter space is constructed with Principal Component Analysis of database of a large number of anatomical face shapes collected for different people. From the input multiple view images, the region of the face and three feature points on the face are manually extracted. Then the facial pose is estimated by optimizing the evaluation based on the silhouette shape, appearance, and the position of the feature points. According to the facial pose, the parameters representing the facial shape are also estimated by optimizing the same evaluation function. Those optimizing procedures are repeated for obtaining the facial shape for the object face captured with the non-synchronous multiple cameras. The experimental results demonstrate the effectiveness of the proposed method. Since the database used in this paper consists of anatomically aligned shape data, we can obtain anatomical shape of the face, which is suitable to represent the identity of each person.Item Introduction of animation assignment in graphic science education making use of CG application of data describing type(Václav Skala - UNION Agency, 2008) Suzuki, Hirotaka; Skala, VáclavIn Osaka City University, Graphic Science Education has been located not as an entrance of drawing and designing exercise but as design language education. Design language is constructed by knowledge and technique which facilitates intelligible communication making good use of figures and drawings. From academic year 2006, number of lecture units in half year increased 1 unit in Osaka City university. Making use of the unit, we secured 3 units for animation exercise and introduced geometry CG art for further understanding about parametric control method in POV-Ray. Due to these change, we decided to regard animation work as compulsory assignment. Comparing to GUI interface CG modeler, it is difficult to construct animation with parametric modeler. As users have to consider relationship of parameters and produced image manually with parametric CG modeler in return for vast possibility of animation idea. Students submitted a lot of type of animation works. And almost all students evaluated CG animation as “interesting” exercise comparing to other topics. In this paper, the content of the subject and submitted animation works is introduced. And the comparison analysis between result of class evaluation for animation and that for other topics is discussed.Item 3D geo-visualization service for grid oriented applications of natural disasters(Václav Skala - UNION Agency, 2008) Pajorová, Eva; Hluchý, Ladislav; Anthes, Christoph; Skala, VáclavOur basic aim is to design a framework that will define a unified way of cooperation between Grid visualization applications and visualization clients. Working with the Grid technology implies increased complexity on one hand, and user demands for high interactivity on the other. The duration of the computations in the Grid environment being exceedingly long, the user naturally wants to see the intermediate results and requires means to modify the running computations if the intermediate results are not satisfactory. Framework is building of lot of tools. This paper describes concrete only one of tool included in framework – 3D Geo_visualization tool for visualization of the running Grid applications to rendering their intermediate or final results in the client application.Item Virtual scene as a software component(Václav Skala - UNION Agency, 2008) Ošlejšek, Radek; Skala, VáclavGraphics systems use many advanced techniques that enable to model and visualize a virtual scene with varying level of realism. Unfortunately, rendering algorithms significantly differ in the way how they process a virtual scene. Concrete implementations therefore usually lead to monolithic solutions. In this paper we propose the concept of a component-based scene graph, i.e. an independent scene graph, which can be used by many rendering strategies simultaneously and, moreover, which can be easily replaced with another implementation.Item Adaptove templates in biometric authentication(Václav Skala - UNION Agency, 2008) Noval, Ricardo García; López, Francisco Perales; Skala, VáclavBiometric authentication systems are usually based on features extraction. Features are a collection of measurable details, obtained from the biometric trait that defines the identity of a certain person. This collection of data is known as template, and it’s stored in the database. The acquired biometrics quality must be controlled in order to model the identity of the individual in a unique and distinct way. The creation and update of templates is a critical task for the correct use of a biometric application. In this paper we propose the implementation of a model that, using biometric-independent tools, intends to update, select and improve the templates stored in the database, in what we have called “adaptive biometric templates”. It has been tested with a fingerprint biometric database of 60 users. We have obtained an average improvement over traditional templates of 26% for FMR and of 53% for FNMR, we consider these results very successful.Item Effective object sorting technique for developing 3D GUI including translucent objects(Václav Skala - UNION Agency, 2008) Kang, Byungkwon; Cho, Sunghee; Skala, VáclavIn developing a user interface, it is very important to provide usability, intuitiveness and convenience. To accomplish these factors, 3D user interface can be one good solution. Recently, many kinds of embedded devices have been developed and utilized for various areas of human life; for example, Digital TVs, game consoles, MP3 players, etc. A GUI makes these devices easier to use and more effective. But, their poor hardware performances often prevent developing a high quality visual effect on their GUIs. A visual effect using alpha blended object is one of the typical examples of this kind that limits the development of 3D applications on an embedded hardware. In this paper, we propose an effective object sorting technique that can be used to develop a 3D GUI including many translucent objects.Item Optimized Daugman’s algorithm for iris localization(Václav Skala - UNION Agency, 2008) Hebaishy, Mohamed A.; Skala, VáclavIris localization is considered the most difficult part in iris identification algorithms because it defines the inner and outer boundaries of iris region used for feature analysis. Several researches were made in the subject of iris finding and segmentation. The main objective here is to remove any non-useful information, namely the pupil segment and the part outside the iris (sclera, eyelids, skin). R. Wildes used Hough transforms to detect the iris contour. Daugman proposed an integro-differential operator to find both the pupil and the iris contour. Daugman’s method is claimed to be the most efficient one. This paper proposes an implementation for Daugman's algorithm, which was found incompatible with visible light illuminated images. Then this paper proposes new algorithm for solving this problem.
