|
二维码（扫一下试试看！） |
| Paper Defects Recognition Based on Deep Layer Feature Extraction of CNN |
| |
| DOI：10.11981/j.issn.1000-6842.2019.04.52 |
| Key Words:paper defect detection; difficult paper defect; convolution neural network; deep feature; classifier |
| Fund Project:陕西省教育厅专项科技项目(16JK1105)；陕西省科技攻关项目(2016GY-005)；咸阳市科技计划项目(2017K02-06)。 |
| Author Name | Affiliation | | GAO Lele | School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | ZHOU Qiang | School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 | | WANG Weigang | School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an, Shaanxi Province, 710021 |
|
| Hits: 4179 |
| Download times: 0 |
| Abstract: |
| To solve the bottleneck problems of difficult separation of paper defect feature quantities and difficult construction of the difficult paper defect feature quantities in current paper defect detection methods, a paper defect identification method based on convolution neural network (CNN) was proposed. First of all, according to the characteristics of paper defect image, the CNN network structure of paper defect detection was designed. On this basis, the deep features of paper defect image were extracted automatically by CNN, and the recognition of paper defect was realized by combining with Softmax. The experimental results showed that this method was superior to the existing detection methods, and was able to accurately identify all kinds of paper defect, including difficult paper defect. |
| View Full Text View/Add Comment Download reader HTML |
|
|
|
