Title :
Research on Paper Defects Recognition Based on SVM
Author :
Shubo, Qiu ; Shuai, Gu ; Tongxing, Zhang
Author_Institution :
Shandong Inst. of Light Ind., Autom. Res. Inst., Jinan, China
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.
Keywords :
document image processing; feature extraction; image classification; image segmentation; support vector machines; BP neural network algorithm; multiclass SVM; paper defect classification; paper defect feature extraction; paper defect image segmentation; paper defect recognition system; support vector machine; Artificial neural networks; Classification algorithms; Image recognition; Image segmentation; Support vector machine classification; Training; BP neural network; SVM; feature extraction; image segmentation; multi-class SVM; paper defects;
Conference_Titel :
Information Engineering (ICIE), 2010 WASE International Conference on
Conference_Location :
Beidaihe, Hebei
Print_ISBN :
978-1-4244-7506-3
Electronic_ISBN :
978-1-4244-7507-0
DOI :
10.1109/ICIE.2010.49
