Robust object recognition using a color co-occurrence histogram and the spatial relations of image patches Export

@article{bang09, abstract = {Abstract\ \ We propose a robust object recognition system where patch-based pyramid images and the spatial relationships among patches are utilized for our image model. In particular, both a color histogram (CH) and a color co-occurrence histogram (CCH) are applied to obtain image features for each patch. The locations of subregions to be tested are decided by a particle filter in our matching process. We show that the performance of object recognition can be improved by using the spatial relationships among patches. To show the validity of our proposed method, we employ input images from various environments as test images.}, author = {Bang, Heebeom and Lee, Sanghoon and Yu, Dongjin and Suh, Il}, citeulike-article-id = {4158124}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s10015-008-0614-5}, citeulike-linkout-1 = {http://www.springerlink.com/content/g06268u004626553}, day = {1}, doi = {10.1007/s10015-008-0614-5}, journal = {Artificial Life and Robotics}, keywords = {by-parts, detection, object, onur2009}, month = {March}, number = {2}, pages = {488--492}, posted-at = {2009-06-26 23:58:47}, priority = {2}, title = {Robust object recognition using a color co-occurrence histogram and the spatial relations of image patches}, url = {http://dx.doi.org/10.1007/s10015-008-0614-5}, volume = {13}, year = {2009} }

TY - JOUR ID - bang09 L3 - citeulike-article-id:4158124 N2 - Abstract  We propose a robust object recognition system where patch-based pyramid images and the spatial relationships among patches are utilized for our image model. In particular, both a color histogram (CH) and a color co-occurrence histogram (CCH) are applied to obtain image features for each patch. The locations of subregions to be tested are decided by a particle filter in our matching process. We show that the performance of object recognition can be improved by using the spatial relationships among patches. To show the validity of our proposed method, we employ input images from various environments as test images. IS - 2 JF - Artificial Life and Robotics EP - 492 TI - Robust object recognition using a color co-occurrence histogram and the spatial relations of image patches VL - 13 SP - 488 KW - by-parts KW - detection KW - object KW - onur2009 AU - Bang, Heebeom AU - Lee, Sanghoon AU - Yu, Dongjin AU - Suh, Il PY - 2009/03/01/ UR - http://dx.doi.org/10.1007/s10015-008-0614-5 ER -