Research on Paper Defects Recognition Based on SVM

Abstract

Support Vector Machine (SVM) is a very popular arithmetic, based on SVM, developed a paper defects recognition system. In the stage of paper defects image segmentation, proposed a algorithm based on the SVM, While in the stage of paper defects feature extraction, applied a multi-class SVM to classify the paper defects. Experimental results show that the proposed system yields faster recognition speed and the average recognition rate of 97%,which performance is significantly better than BP neural network algorithm.