期刊
OPTICAL ENGINEERING
卷 56, 期 9, 页码 -出版社
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.OE.56.9.093104
关键词
yarn-dyed fabric; defect classification; convolutional neural network; AlexNet
类别
资金
- Scientific Research Program - National Natural Science Foundation of China [61301276]
- Shaanxi Technology Committee [2015GY034]
- Key Research & Development plan of Shaanxi Province [2017GY-003]
Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据