|
二维码（扫一下试试看！） |
| Paper Defects Classification Based on Multi-scale Image Enhancement Combined with Convolution Neural Network |
| |
| DOI：10.11980/j.issn.0254-508X.2018.08.009 |
| Key Words:image enhancement convolution neural network（CNN） multi-scale morphological gradient image classification |
| Fund Project:国家自然科学基金（61461025）；国家自然科学基金（61811530325）；中国博士后科学基金项目（2016M602856）。 |
| Author Name | Affiliation | | LI Guang-ming | College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | XUE Ding-hua | College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | JIA Xiao-hong | College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | LI Yun-tong | College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | LEI Tao* | College of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 |
|
| Hits: 11543 |
| Download times: 3306 |
| Abstract:In paper industry， traditional approaches of paper defects classification depend on the selection of feature descriptors and the selector.To address the problem， an approach of paper defects classification based on multi-scale image enhancement combined with convolution neural network(CNN） was proposed in this paper-Firstly， multi-scale morphological gradient was computed and used to enhance the edge contour information of paper image， the gradient features of defects in a paper image was highlighted.Then， CNN was applied to learn image features and employed to classify paper defects images.Finally， paper defects classification with a high accuracy was achieved.The experimental results showed that the proposed approach obtained a higher accuracy， 98.44%， 99.23%， and 99.64% on Caltech101， KTH-TIPS， and our datasets， respectively， was significantly superior to the methods of HOG+SVM， LBP+SVM， and traditional CNN.Compared to current methods for paper defects classification， the proposed approach did not require to extract defects features using feature descriptors． |
| View Full Text HTML View/Add Comment Download reader |
|
|
|