Unsupervised Feature Selection and Category Formation for Generic Object Recognition

摘要

This paper presents an unsupervised method for selection of feature points and object category formation without previous setting of the number of categories. For unsupervised object category formation, this method has the following features: selection of target feature points using One Class-SVMs (OC-SVMs), generation of visual words using Self-Organizing Maps (SOMs), formation of labels using Adaptive Resonance Theory-2 (ART-2), and creation and classification of categories for visualizing spatial relations between them using Counter Propagation Networks (CPNs) . Classification results of static images using a Caltech-256 object category dataset demonstrate that our method can visualize spatial relations of categories while maintaining time-series characteristics. Moreover, we emphasize the effectiveness of our method for category formation of appearance changes of objects.