Abstract

Empirically, we find that, despite the class-speci fic features owned by the objects appearing in the images, the objects from different categories usually share some common patterns, which do not contribute to the discrimination of them. Concentrating on this observation and under the general dictionary learning (DL) framework, we propose a novel method to explicitly learn a common pat- tern pool (the commonality) and class-specific dictionaries (the particularity) for classi fication. We call our method DL-COPAR, which can learn the most com- pact and most discriminative class-speci fic dictionaries used for classi fication. The proposed DL-COPAR is extensively evaluated both on synthetic data and on benchmark image databases in comparison with existing DL-based classi fi- cation methods. The experimental results demonstrate that DL-COPAR achieves very promising performances in various applications, such as face recognition, handwritten digit recognition, scene classification and object recognition.