Paper Defects Detection via Visual Attention Mechanism

作     者：JIANG Ping~1,GAO Tao~(2,3) 1.School of Control Science & Engineering,University of Jinan,Jinan 250022,P.R.China 2.Electronic Information Products Supervision and Inspection Institute of Hebei Province,Shijiazhuang 050071,Hebei,P.R.China 3.Industry and Information Technology Department of Hebei Province,Shijiazhuang 050051,Hebei,P.R.China 

会议名称：《第三十届中国控制会议》

会议日期：2011年

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by China‘863’High-Tech Program(No 2007AA04Z219) the National Natural Science Foundation of China(No 6087053,60802051) the Program for New Century Excellent Talent in University(NCET) 

关 键 词：Defect Detection Visual Attention Mechanism Saliency Map Watershed Segmentation 

摘      要：正An improved paper defects detection method based on visual attention mechanism computation model is ***,multi-scale feature maps are extracted by linear ***,the comparative maps are obtained by carrying out center-surround difference ***,the saliency map is obtained by combining the conspicuity maps, which is gained by combining the multi-scale comparative ***,the seed point of watershed segmentation is determined by competition among salient points in the saliency map and the defect regions are segmented from the *** results show the efficiency of the approach for paper defects detection.