The Community for Technology Leaders
Green Image
A new descriptor for symbol recognition is proposed. 1) A histogram is constructed for every pixel to figure out the distribution of the constraints among the other pixels. 2) All the histograms are statistically integrated to form a feature vector with fixed dimension. The robustness and invariance were experimentally confirmed.
Symbol recognition, graphics recognition, descriptor, feature extraction, feature representation.
Su Yang, "Symbol Recognition via Statistical Integration of Pixel-Level Constraint Histograms: A New Descriptor", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 27, no. , pp. 278-281, February 2005, doi:10.1109/TPAMI.2005.38
108 ms
(Ver 3.1 (10032016))