期刊文献+

基于对偶范数低秩分解的织物疵点检测方法 预览

Fabric Defect Detection Method Basedon Dual Norm Low-rank Decomposition
在线阅读 下载PDF
收藏 分享 导出
摘要 研究一种基于对偶范数低秩分解模型的模式织物疵点检测方法。通过Log-Gabor滤波器提取织物图像的纹理特征,进而构造高度低秩的特征矩阵;采用基于对偶范数的低秩分解模型将特征矩阵分为低秩部分(背景)与非低秩部分(疵点),采用核范数的对偶范数作为正则项来替代原有低秩分解模型中的“稀疏”约束,使背景和疵点的相关度最小,从而实现疵点的有效分离;最后采用改进的自适应阈值算法对由非低秩部分生成的显著图进行分割,从而定位出疵点区域。认为:该算法具有较高的检测率及鲁棒性,且优于现有的疵点检测方法。 A pattern of fabric defect detection method based on dual norm low-rank decomposition model was studied.The textural features of the fabric image was extracted with Log-Gabor filter.The height low-rank characteristic matrix was then built.The low-rank decomposition model based on dual dorm was adopted to divide the characteristic matrix into low-rank part and non-low-rank part.The dual norm of nuclear norm was used as the regular terms to replace the sparse constraint in the original low-rank decomposition model to minimize the relevancy between background and defect.So the effective separation of defects could be achieved.In the end,the algorithm of modified self-adaption threshold value was used to segment the saliency map generated by low-rank part.Thus,the defect area could be located.It is considered that the algorithm has higher detection rate and robustness.It is better than the existing defect detection methods.
作者 李春雷 王珺璞 刘洲峰 杨艳 杨瑞敏 LI Chunlei;WANG Junpu;LIU Zhoufeng;YANG Yan;YANG Ruimin(Zhongyuan University of Technology,Henan Zhengzhou,450007)
机构地区 中原工学院
出处 《棉纺织技术》 CAS 北大核心 2019年第1期5-10,共6页 Cotton Textile Technology
基金 国家自然科学基金项目(61772576) 河南省自然科学基金重点项目(162300410338) 河南省高校科技创新人才项目(17HASTIT019) 河南省科技创新杰出青年项目(184100510002).
关键词 疵点检测 LOG-GABOR滤波器 对偶范数 低秩分解 非精确拉格朗日乘子法 Defect Detection Log-Gabor Filter Dual Norm Low-rank Decomposition Imprecise Lagrange Multiplier Method
作者简介 李春雷(1979-),男,副教授,lichunlei1979@sina.com
  • 相关文献
投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈