Unifying discriminative visual codebook generation with classifier training for object category recognition

The idea of representing images using a bag of visual words is currently popular in object category recognition. Since this representation is typically constructed using unsupervised clustering, the resulting visual words may not capture the desired information. Recent work has explored the construction of discriminative visual codebooks that explicitly consider object category information. However, since the codebook generation process is still disconnected from that of classifier training, the set of resulting visual words, while individually discriminative, may not be those best suited for the classifier. This paper proposes a novel optimization framework that unifies codebook generation with classifier training. In our approach, each image feature is encoded by a sequence of "visual bits" optimized for each category. An image, which can contain objects from multiple categories, is represented using aggregates of visual bits for each category. Classifiers associated with ...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Liu Yang, Rong Jin, Rahul Sukthankar, Frédéric Jurie
• Keywords: Codebook Generation, Computer Vision, CVPR 2008, Discriminative Visual Codebook, Discriminative Visual Codebooks, Visual Bits, Visual Words