A novel kernel discriminant transformation (KDT) algorithm based on the concept of canonical differences is presented for automatic face recognition applications. For each individu...
Wen-Sheng Vincent Chu, Ju-Chin Chen, Jenn-Jier Jam...
i Integration of surface normal vectors is a vital component in many shape reconstruction algorithms that require integrating surface normals to produce their final outputs, the de...
Jeffrey Ho, Jongwoo Lim, Ming-Hsuan Yang, David J....
Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...
The ability to construct CAD or other object models from edge and range data has a fundamental meaning in building a recognition and positioning system. While the problem of model...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...