Recognition of multiple configurations of objects with limited data |
| |
Authors: | Yuexing Han [Author Vitae] Bing Wang [Author Vitae] [Author Vitae] Hiroyuki Shimai [Author Vitae] |
| |
Affiliation: | a The University of Electro-Communications, 1-5-1, Chofugaoka, Chofu-Shi, Tokyo 182-8585, Japan b Institute of Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Japan |
| |
Abstract: | One of the main goals of image understanding and computer vision applications is to recognize an object from various images. A lot of studies on recognizing objects based on invariable shapes have been explored, however, in reality, there are many objects with multiple configurations, which are very difficult to be recognized. We call this kind of problem as the recognition of multiple configurations of objects (RMCO). To achieve RMCO, firstly we obtain a shortest path (the Geodesic distance path) between two feature vectors in pre-shape spaces; along this obtained path, we can generate a series of data which can be used to recognize the observed objects by using shape space theories. In other words, we may augment the database content with very limited data to recognize more objects. |
| |
Keywords: | Shape space Pre-shape space Landmark The Procrustean distance The Procrustean metric The Geodesic distance Shape contour Manifold The shortest path |
本文献已被 ScienceDirect 等数据库收录! |
|