Learning Optimal Compact Codebook for Efficient Object Categorization

Representation of images using the distribution of local features on a visual codebook is an effective method for object categorization. Typically, discriminative capability of the codebook can lead to a better performance. However, conventional methods usually use clustering algorithms to learn codebooks without considering this. This paper presents a novel approach of learning optimal compact codebooks by selecting a subset of discriminative codes from a large codebook. Firstly, the Gaussian models of object categories based on a single code are learned from the distribution of local features within each image. Then two discriminative criteria, i.e. likelihood ratio and Fisher, are introduced to evaluate how each code contributes to the categorization. We evaluate the optimal codebooks constructed by these two criteria on Caltech-4 dataset, and report superior performance of object categorization compared with traditional K-means method with the same size of codebook.

[1]  Frédéric Jurie,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2006, NIPS.

[2]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  David G. Stork,et al.  Pattern Classification , 1973 .

[4]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[5]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[7]  Cordelia Schmid,et al.  Selection of scale-invariant parts for object class recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  In-So Kweon,et al.  Simultaneous Classification and VisualWord Selection using Entropy-based Minimum Description Length , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[9]  Frédéric Jurie,et al.  Latent mixture vocabularies for object categorization and segmentation , 2006, Image Vis. Comput..

[10]  In-So Kweon,et al.  Object Categorization Robust to Surface Markings using Entropy-guided Codebook , 2007, 2007 IEEE Workshop on Applications of Computer Vision (WACV '07).

[11]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[12]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[13]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[14]  Frédéric Jurie,et al.  Sampling Strategies for Bag-of-Features Image Classification , 2006, ECCV.

[15]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[16]  B. Schiele,et al.  Interleaved Object Categorization and Segmentation , 2003, BMVC.

[17]  Gabriela Csurka,et al.  Adapted Vocabularies for Generic Visual Categorization , 2006, ECCV.

[18]  Antonio Criminisi,et al.  Object categorization by learned universal visual dictionary , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[19]  Frédéric Jurie,et al.  Creating efficient codebooks for visual recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.