The Research of Texture-based Classification of Fabric Surface Defect Image

摘要：

This paper mainly studies the BP neural network and wavelet neural network classifiers,using the BP neural network and wavelet neural network for the defect recognition of defect image.Through the comparative analysis between the results of recognition we know that the wavelet neural network has stronger approximation ability .faster convergence rate,and the selection of the network parameters (the numbers of the hidden layer points and the weights) are on the basis of the theory.

关键词： Defect detection BP neural network Wavelet neural network

作者: Erjin Gao Xiaobing Wu

作者单位: Department of Electrical Engineering & Automation Chongqing Vocational Institute of Engineering Chongqing, China

会议类型: 国际会议

会议名称: 2012 International Conference on Electric Technology and Civil Engineering(2012 电子技术与土木工程国际会议 ICETCE 2012)

会议地点: 三峡

会议语种:英文

页码: 1235-1238

在线出版日期: 2012-05-18（万方平台首次上网日期，不代表论文的发表时间）