应用非负字典学习的机织物瑕疵检测算法

纺织学报 ›› 2016, Vol. 37 ›› Issue (3): 144-149.

应用非负字典学习的机织物瑕疵检测算法

收稿日期:2014-12-22 修回日期:2015-10-09 出版日期:2016-03-15 发布日期:2016-03-16

Woven fabric defect detection based on nonnegnative dictionary learning

Received:2014-12-22 Revised:2015-10-09 Online:2016-03-15 Published:2016-03-16

摘要/Abstract

摘要：

为进一步提高织物瑕疵检测算法对瑕疵类型的通用性，提出一种基于字典学习的机织物疵点检测方法。首先对正常机织物图像进行窗口分割，将每个子窗口按列展开成列向量，所有列向量联合组成一个矩阵；然后对该矩阵进行非负字典学习，得到个数最佳的非负字典，也就是基向量；最后应用该字典对待检测样本进行近似，在重构误差的基础上进行疵点检测。重点探讨了窗口大小和字典个数对检测效果的影响。对4864个样本的实验结果表明，所提算法能在误检率小于10%情况下，取得90%的检出率。

关键词: 非负字典学习, 子窗口尺寸, 字典大小, 机织物瑕疵, 检测

Abstract:

In order to improve the versatklity of detection algorithm on varying fabric defect types, an algorithm for woven fabric defect detection using dictionary learning (DL) is proposed. Firstly, normal fabric image is divided into small image patches and unfloded into a column vector, then all the column vectors are combined into a matrix. Secondly, the matrix composed of column vectors is solved by DL, and then the optimal dictionary(basis vectors) are extracted. Finally the dictionary is applied to reconstruct testing samples, where the reconstruction error between original and reconstruction image is used for defect detection. Effect of the patch size and number of dictionary is also investigated. Experiments on 4864 samples show that the proposed method can achieve 90% of detection rate with false detection rate below 10%.

Key words: non-negative dectionary learning, patch size, dictionary size, fabric defect, detection

毛兆华汪军周建卜佳仙陈霞李立轻. 应用非负字典学习的机织物瑕疵检测算法[J]. 纺织学报, 2016, 37(3): 144-149.

参考文献

相关文章 15

[1]	高畅刘基宏. 基于奇部Gabor滤波器的纱管余纱量检测[J]. 纺织学报, 2018, 39(10): 138-142.
[2]	赵树志狄岚何锐波. 基于改进判别性完整局部二值模式与格分割的织物瑕疵检测方法[J]. 纺织学报, 2018, 39(09): 57-64.
[3]	常永和薛元韩晨晨杨瑞华高卫东张毅. 环锭纺导纱板受力信号在线检测及纺纱张力分析[J]. 纺织学报, 2018, 39(09): 146-152.
[4]	孙卫红　陈宇　邵铁锋　梁曼　马冠宇. 混合式生丝断丝检测传感器设计[J]. 纺织学报, 2018, 39(09): 134-138.
[5]	田明伟李增庆卢韵静朱士凤张宪胜曲丽君. 纺织基柔性力学传感器研究进展[J]. 纺织学报, 2018, 39(05): 170-176.
[6]	王雯雯刘基宏. 应用优化霍夫变换的细纱断头检测[J]. 纺织学报, 2018, 39(04): 36-41.
[7]	孟想辛斌杰李佳平. 采用多角度成像技术的纺织品三维轮廓重建算法[J]. 纺织学报, 2018, 39(04): 144-150.
[8]	吕汉明吴擎擎吕鑫马崇启周鹏飞. 基于数据库的环锭纺细纱机细纱断头检测与信息显示[J]. 纺织学报, 2018, 39(04): 123-129.
[9]	王传桐胡峰徐启永吴雨川余联庆. 改进频率调谐显著算法在疵点辨识中的应用[J]. 纺织学报, 2018, 39(03): 154-160.
[10]	袁嫣红马天宇项宏年. 电磁选针器实时检测系统[J]. 纺织学报, 2018, 39(03): 143-147.
[11]	吴莹汪军. 基于K-SVD学习字典的机织物纹理表征及应用[J]. 纺织学报, 2018, 39(02): 165-170.
[12]	牟新刚蔡逸超周晓陈国良. 基于机器视觉的筒子纱缺陷在线检测系统[J]. 纺织学报, 2018, 39(01): 139-145.
[13]	邢乐张杰梁惠娥李忠健刘姣姣. 传统服饰云肩实物图像主色的智能检测[J]. 纺织学报, 2017, 38(11): 110-115.
[14]	郭隽侠陶建峰刘成良. 应用改进蚁群算法的同心分布喷丝孔检测路径规划[J]. 纺织学报, 2017, 38(11): 124-130.
[15]	杜玉红杨程午蒋秀明刘仁杰蔡文超. 应用聚类神经网络的异纤检测多类光源优化设计[J]. 纺织学报, 2017, 38(10): 104-112.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed