Cat Head Detection - How to Effectively Exploit Shape and Texture Features Export

@incollection{citeulike:5199248, abstract = {In this paper, we focus on the problem of detecting the head of cat-like animals, adopting cat as a test case. We show that the performance depends crucially on how to effectively utilize the shape and texture features jointly. Specifically, we propose a two step approach for the cat head detection. In the first step, we train two individual detectors on two training sets. One training set is normalized to emphasize the shape features and the other is normalized to underscore the texture features. In the second step, we train a joint shape and texture fusion classifier to make the final decision. We demonstrate that a significant improvement can be obtained by our two step approach. In addition, we also propose a set of novel features based on oriented gradients, which outperforms existing leading features, e. g., Haar, HoG, and EoH. We evaluate our approach on a well labeled cat head data set with 10,000 images and PASCAL 2007 cat data.}, author = {Zhang, Weiwei and Sun, Jian and Tang, Xiaoou}, citeulike-article-id = {5199248}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-88693-8_59}, citeulike-linkout-1 = {http://www.springerlink.com/content/gq1j447wgw4g0075}, doi = {10.1007/978-3-540-88693-8_59}, journal = {Computer Vision – ECCV 2008}, keywords = {detection, feature, shape, texture}, pages = {802--816}, posted-at = {2009-07-18 22:12:37}, priority = {0}, title = {Cat Head Detection - How to Effectively Exploit Shape and Texture Features}, url = {http://dx.doi.org/10.1007/978-3-540-88693-8_59}, year = {2008} }

TY - CHAP ID - citeulike:5199248 L3 - citeulike-article-id:5199248 N2 - In this paper, we focus on the problem of detecting the head of cat-like animals, adopting cat as a test case. We show that the performance depends crucially on how to effectively utilize the shape and texture features jointly. Specifically, we propose a two step approach for the cat head detection. In the first step, we train two individual detectors on two training sets. One training set is normalized to emphasize the shape features and the other is normalized to underscore the texture features. In the second step, we train a joint shape and texture fusion classifier to make the final decision. We demonstrate that a significant improvement can be obtained by our two step approach. In addition, we also propose a set of novel features based on oriented gradients, which outperforms existing leading features, e. g., Haar, HoG, and EoH. We evaluate our approach on a well labeled cat head data set with 10,000 images and PASCAL 2007 cat data. JF - Computer Vision – ECCV 2008 EP - 816 TI - Cat Head Detection - How to Effectively Exploit Shape and Texture Features SP - 802 KW - detection KW - feature KW - shape KW - texture AU - Zhang, Weiwei AU - Sun, Jian AU - Tang, Xiaoou PY - 2008/// UR - http://dx.doi.org/10.1007/978-3-540-88693-8_59 ER -