第27卷4 期第.pdfVIP

第 27 卷 　第 4 期 纺 　织 　学 　报 Vol. 27 　No. 4 2006 年 4 月 Journal of Textile Research Apr. 　2006 ( ) 文章编号 2006 基于神经网络的织物疵点识别技术 陈俊杰 ,谢春萍 (江南大学 纺织服装学院 ,江苏 无锡 　214122) 摘 　要 　因织物组织繁多 ,表面特征各异 ,很难建立一个统一的织物疵点识别模型 。为了解决这一问题 ,实现 自动 验布 ,提出采用双层神经网络和小波变换来识别织物疵点的方法 。先对正常织物进行训练 ,得到织物的特征 ,应用 第 1 层简单 BP 网络来分辨正常织物和疵点 。然后对疵点图像进行二维离散小波变换 ,并去除织物本身的特征 ,利 用已训练的BP 网络进行具体疵点识别 。试验证明 ,这种方法的准确性较高 ,速度快 ,基本接近 自动验布系统的 要求 。 关键词 　疵点识别 ; 小波变换 ; 神经网络 ; 质量检测 中图分类号 :TS10197 　　　文献标识码 :A 　　　 Fabric defect detection technique based on neural network CHEN Junjie , XIE Chunping ( School of Textile and Garment , Southern Yangtze University , Wuxi , Jiangsu 　214122 , China) Abstract 　Owing to numerous kinds of fabric weaves and varied characteristics of fabric surface , it is very difficult to establish a universal fabric defect detection model. In order to solve this problem and realize automatic inspection of fabric , a method for identification of the defects on the fabric by using the double layer neural network and wavelet analysis is proposed. To be specific , the first layer BP neural network is utilized to tell the defects of a normal fabric and acquire its characteristics through repeated training , and then , the two dimensional discrete wavelet transformation based on the image of the defects is conducted , wiping off the inherent characteristics of the fabric and identifying the defects by means of the trained BP neural network. The experiments demonstrated that this method is of high accuracy and high speed , satisfying the elemen