Mining heterogeneous class-specific codebook for categorical object detection and classification

We propose a novel model to mine and derive class-specific codebook for categorical object detection and classification. In particular, the codebook is built from a pool of heterogeneous local descriptors using an effective feature selection scheme. The resulting class-specific codebook strengthens the class discriminability by learning the most discriminative part codewords constructed from their preferable local descriptors. The advantage of our class-specific codebook comes from two aspects. 1). As we collect a variety of heterogeneous descriptors during the learning of local codebook, each target object class can always be represented by its most preferable descriptors. Moreover, even each part codeword can also find its suitable descriptors. 2). The feature selection process further picks out the most discriminative object parts that separate the target object class from background and other classes. Experimental results on several widely used datasets show that benefits from our class-specific object codebook which fuses complementary visual cues remarkably improve the detection and classification performance for both rigid and non-rigid articulated objects.