Category sensitive codebook construction for object category recognition

Chunjie Zhang, Jing Liu, Yi Ouyang, Qi Tian, Hanqing Lu, Songde Ma

Abstract

Recently, the bag of visual words based image representation is getting popular in object category recognition. Since the codebook of the bag-of-words (BOW) based image representation approach is typically constructed by only measuring the visual similarity of local image features (e.g., k-means), the resulting codebooks may not capture the desired information for object category recognition. This paper proposes a novel optimization method for discriminative codebook construction that considers the category information of local image features as an additional term in traditional visual-similarity-only based codebook construction methods. The category sensitive codebook is constructed through solving an optimization problem. Therefore, the category sensitive codebook construction method goes one step beyond visual-similarity-only methods. Besides, the proposed category sensitive codebook construction method can be implemented with k-means clustering very efficiently and effectively. Experimental results on PASCAL VOC Challenge 2006 data set demonstrate the effectiveness of our method.
BibTeX
@inproceedings{zhang2009category,
  author = {Chunjie Zhang and Jing Liu and Yi Ouyang and Qi Tian and Hanqing Lu and Songde Ma},
  title = {{Category sensitive codebook construction for object category recognition}},
  booktitle = {ICIP},
  year = {2009},
  doi = {10.1109/icip.2009.5414450},
}

Loading related content...

Figure