Concept-Specific Visual Vocabulary Construction for Object Categorization

Recently, the bag-of-words (BOW) based image representation is getting popular in object categorization. However, there is no available visual vocabulary and it has to be learned. As to traditional learning methods, the vocabulary is constructed by exploring only one type of feature or simply concatenating all kinds of visual features into a long vector. Such constructions neglect distinct roles of different features on discriminating object categories. To address the problem, we propose a novel method to construct a conceptspecific visual vocabulary. First, we extract various visual features from local image patches, and cluster them separately according to different features to generate an initial vocabulary. Second, we formulate the concept-specific visual words selection and object categorization into a boosting framework. Experimental results on PASCAL 2006 challenge data set demonstrate the encouraging performance of the proposed method.