Scalable representation for 3D object recognition using feature sharing and view clustering |
| |
| Authors: | Sungho Kim In So Kweon |
| |
| Affiliation: | 1. Stat-math Unit, Indian Statistical Institute, Kolkata 700108, India;2. Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata 700108, Indian;1. Department of Statistical Science, University College London, London WC1E 6BT, UK;2. Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Ibaraki 305-8573, Japan;1. Department of neurosurgery, Zhujiang Hospital of Southern Medical University, Guangzhou 510282, China;2. Neurosurgery Institute, Key Laboratory on Brain Function Repair and Regeneration of Guangdong Province, Southern Medical University, Guangzhou 510282, China;3. Department of Neurosurgery, the Second Affiliated Hospital, Fujian Medical University, Quanzhou 362000, China |
| |
| Abstract: | Scalability is an important issue in object recognition as it reduces database storage and recognition time. In this paper, we propose a new scalable 3D object representation and a learning method to recognize many everyday objects. The key proposal for scalable object representation is to combine the concept of feature sharing with multi-view clustering in part-based object representation, in particular a common-frame constellation model (CFCM). In this representation scheme, we also propose a fully automatic learning method: appearance-based automatic feature clustering and sequential construction of clustered CFCMs from labeled multi-views and multiple objects. We evaluated the scalability of the proposed method to COIL-100 DB and applied the learning scheme to 112 objects with 620 training views. Experimental results show the scalable learning results in almost constant recognition performance relative to the number of objects. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
