A Novel On-line Paper Defect Classification Method Based on Multi-representatives Classification
Yaqin Zhao · Journal of Information and Computational Science · 2014
Due to mass paper images and large amounts of noise in a paper image for a on-line paper detection system, this paper presents a novel method of on-line paper defect detection based on Multirepresentatives Classification (MRC). First of all, using the background subtraction method is used to rapidly identify those papers with defects from mass on-line papers. Afterwards, pixels of paper defect images are clustered to segmentalize defect regions, and LOG operator is used for edge extraction. On the basis of these, characteristic value of paper defect are extracted. Finally 8 kinds of paper defects are classified by using multi-representatives classification, the classification complexity of which is O(n). The experimental results showed that the method could quickly and accurately classify 8 kinds of paper defects, thus the method can meet the requirement of on-line paper defect detection.