Visual categorization with bags of keypoints
Chris Dance, Jutta Willamowski, Lixin Fan, Cedric Bray, Gabriela Csurka
ECCV International Workshop on Statistical Learning in Computer Vision, Prague, 2004.
We present a method for generic visual categorization. This technique exploits an analogy with learning
methods for text categorization based on the simple bag of words approach. Two key novel aspects of this
approach are that it handles multiple image categories simultaneously and that it is intrinsically invariant to
affine image transformations. Results are presented for simultaneously classifying seven semantic visual
categories using Naive Bayes techniques.
2004_010.pdf (798.13 kB)