Visual categorization with bags of keypoints Export

@inproceedings{csurka-dance-2004, abstract = {Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches. We propose and compare two alternative implementations using different classifiers: Na\"{i}ve Bayes and SVM. The main advantages of the method are that it is simple, computationally efficient and intrinsically invariant. We present results for simultaneously classifying seven semantic visual categories. These results clearly demonstrate that the method is robust to background clutter and produces good categorization accuracy even without exploiting geometric information. 1.}, author = {Csurka, Gabriella and Dance, Christopher R. and Fan, Lixin and Willamowski, Jutta and Bray, C\'{e}dric}, booktitle = {In Workshop on Statistical Learning in Computer Vision, ECCV}, citeulike-article-id = {4007958}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.604}, keywords = {learning\_based\_vision}, pages = {1--22}, posted-at = {2009-02-04 16:11:23}, priority = {0}, title = {Visual categorization with bags of keypoints}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.604}, year = {2004} }

TY - CONF ID - csurka-dance-2004 L3 - citeulike-article-id:4007958 N2 - Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches. We propose and compare two alternative implementations using different classifiers: Naïve Bayes and SVM. The main advantages of the method are that it is simple, computationally efficient and intrinsically invariant. We present results for simultaneously classifying seven semantic visual categories. These results clearly demonstrate that the method is robust to background clutter and produces good categorization accuracy even without exploiting geometric information. 1. EP - 22 TI - Visual categorization with bags of keypoints T2 - In Workshop on Statistical Learning in Computer Vision, ECCV SP - 1 KW - learning_based_vision AU - Csurka, Gabriella AU - Dance, Christopher AU - Fan, Lixin AU - Willamowski, Jutta AU - Bray, Cédric PY - 2004/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.604 ER -