Previous research has shown that aggregated predictors improve the performance of non-parametric function approximation techniques. This paper presents the results of applying aggregated predictors to a computer vision problem, and shows that the method of bagging signi cantly improves performance. In fact, the results are better than those previously reported on other domains. This paper expla...

i Acknowledgments iii List of Figures viii List of Tables xi

| This paper summarises the rst session of the Vision Milestones'95 workshop. Key questions concerning the topic of the session are formulated. Personal views of the author|the session chairman| on some general problems facing computer vision are presented in a rather informal way. The main issues addressed are the ultimate goal of computer vision, computer versus human vision, heuristics versu...

For most real applications of computer vision, variations in operating conditions result in poor reliability. As a result, real world applications tend to require lengthy set-up and frequent intervention by qualified specialists. In this paper we describe how autonomic computing can be used to reduce the cost of installation and enhance reliability for practical computer vision systems. We begi...

Digital media are rapidly replacing their analog counterparts. This development is accompanied by (i) the increasing amount of images present on the Internet, (ii) the availability of the Internet for an increasing number of people, (iii) a decline in digital storage costs, and (iv) the developments in personal digital video/photo cam-era's [1, 2, 3]. In anticipation of these developments, the ...

Computer vision is a hot research topic. The goal is to empower a computer or robot with vision, similar to the human visual system. Some of the typical subproblems are: reconstruction of a three-dimensional scene from a set of images, recognition of previously seen objects, and calculation of camera motion relative to the scene. This has proved to be an extremely difficult task. However, some ...

Computers looking through a camera at people is a potentially powerful technique to facilitate human-computer interaction. The computer can interpret the userś movements, gestures, and glances. Fundamental visual algorithms include tracking, shape recognition, and motion analysis. We describe several vision algorithms for interactive graphics, and present various vision controlled graphics appl...