首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进的小波分解织物疵点检测
引用本文:严平,邓中民,刘童花. 基于改进的小波分解织物疵点检测[J]. 纺织科技进展, 2007, 0(4): 46-47
作者姓名:严平  邓中民  刘童花
作者单位:武汉科技学院,纺织与材料学院,湖北,武汉,430073;武汉科技学院,纺织与材料学院,湖北,武汉,430073;武汉科技学院,纺织与材料学院,湖北,武汉,430073
基金项目:武汉科技学院校科研和教改项目;武汉科技学院创新基金
摘    要:采用小波分解的改进方法,运用二维离散小波变换进行分解,有效地从图像中提取信息,分析织物的纹理特征并进行相应处理,实现目标图像的特征提取和输入LMBP神经网络进行学习训练。实验结果表明,对油污、破洞、断经、断纬能比较准确地识别和定位,可快速有效地进行织物疵点检测。

关 键 词:小波分解  LMBP神经网络  数字图像处理
文章编号:1673-0356(2007)04-0046-02
修稿时间:2007-05-22

Textile defect detection based on improvement wavelet decomposes
YAN Ping,DENG Zhong-ming,LIU Tong-Hua. Textile defect detection based on improvement wavelet decomposes[J]. Progress in Textile Science & Technology, 2007, 0(4): 46-47
Authors:YAN Ping  DENG Zhong-ming  LIU Tong-Hua
Affiliation:Wuhan University of Science and Engineering, Wuhan 430073, China
Abstract:The improved method was put forward, using the 2-D discrete wavelet decomposition and extracting the effective information from the pictures. Then characteristics were obtained by relevant processing, and the LMBP neural network was input to carry on the training. The experimental results indicated that it could recognize and localize accurately, carry on the textile defect detection effectively.
Keywords:wavelet decomposition   LMBP neural network   image processing
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号