A Novel Autonomous Feature Clustering Model for Image Recognition
In order to realize human-like image recognition system, we introduce an architecture with separation of extracting and clustering features from detecting features. We also propose a novel autonomous clustering model that attaches an adaptive cluster determination algorithm, which enables superior cluster determination even for higher dimension vectors like real world images, on the Kohonens Self-Organizing feature Map (SOM). By this algorithm, SOM weight vectors are converted to extremely lower dimensional vectors, which just consist of meaningful components to describe clusters. Therefore, we can execute autonomous determination of cluster boundaries easily. As a result, our proposed clustering model shows better performance than conventional techniques. Furthermore, feature detectors in our architecture is self-organized by the clustered sets of features which is autonomously clustered in our model.
Hitoshi Ikeda Hirotsugu Kashimura Noriji Kato Masaaki Shimizu
Fuji Xerox Corporate Research Center, 430 Sakai,Nakai-machi, Ashigarakami-gun, Kanagawa 259-0157, Japan
国际会议
8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)
上海
英文
743-748
2001-11-14（万方平台首次上网日期，不代表论文的发表时间）