电子学报 ›› 2012, Vol. 40 ›› Issue (3): 611-616.DOI: 10.3969/j.issn.0372-2112.2012.03.034

• 科研通信 • 上一篇    下一篇

一种基于改进型PCNN的织物疵点图像自适应分割方法

祝双武1, 郝重阳2   

  1. 1. 西安工程大学纺织与材料学院,陕西西安 710048;2. 西北工业大学电子信息学院,陕西西安 710072
  • 收稿日期:2011-03-04 修回日期:2011-10-26 出版日期:2012-03-25
    • 基金资助:
    • 陕西省教育厅专项基金项目 (No.08JK303); 博士启动基金 (No.BS1004)

An Approach for Fabric Defect Image Segmentation Based on the Improved Conventional PCNN Model

ZHU Shuang-wu1, HAO Chong-yang2   

  1. 1. College of Textile and Material,Xi'an Polytechnic University,Xi'an,Shaanxi 710048,China;2. College of Electronic Information,Northwestern Polythenical University,Xi'an,Shaanxi 710072,China
  • Received:2011-03-04 Revised:2011-10-26 Online:2012-03-25 Published:2012-03-25

摘要: 针对传统脉冲耦合神经网络(Pulse Coupled Neural Network,PCNN)模型中网络参数多、不易自动选取的问题,本文在对PCNN模型进行改进的基础上,提出了一种基于改进型PCNN织物疵点图像自适应分割方法.采用了一种基于分割区域内均匀度差异最小作为最佳迭代次数判断标准,从而有效地满足了PCNN对织物疵点图像的自动分割要求.通过对不同疵点图像分割实验证明了算法对疵点分割的准确性和有效性.

关键词: 脉冲耦合神经网络, 织物疵点, 图像分割, 区域内均匀度

Abstract: An approach is proposed for fabric defect detection based on the improved conventional pulse coupled neural network (PCNN) model.For these too many parameters of conventional PCNN,it is difficult to get the adaptive parameters.The problem can be solved in the proposed way,in which optimal number of iteration to segment fabric defect image automatically is determined based on minimum difference of uniformity within region.Segmentations on various defect images are implemented with the proposed approach and the experimental results demonstrate its reliability and validity.

Key words: pulse coupled neural network(PCNN), fabric defect, image segmentation, uniformity within region

中图分类号: