A Dictionary Learning Approach for Classification: Separating the Particularity and the Commonality^*

Shu Kong and Donghui Wang

Abstract. Empirically, we find that, despite the class-specific 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 pattern pool (the commonality) and class-specific dictionaries (the particularity) for classification. We call our method DL-COPAR, which can learn the most compact and most discriminative class-specific dictionaries used for classification. The proposed DL-COPAR is extensively evaluated both on synthetic data and on benchmark image databases in comparison with existing DL-based classification 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.

Keywords: Dictionary Learning, Classification, Commonality, Particularity

^*This work is financially supported by 973Program (No.2010CB327904) and Natural Science Foundations of China (No.61071218).

LNCS 7572, p. 186 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012