基于相似性定位和超像素分割的织物疵点检测

doi:10.13475/j.fzxb.20200102909

摘要/Abstract

摘要：

为解决周期性纹理织物图像的疵点检测及其轮廓精确分割问题,提出一种基于相似性定位和超像素分割的织物疵点检测方法。将待检测图像进行中值滤波和对数增强,并利用FT算法估计增强图像的显著图实现待检测图像的预处理;将基于归一化局部均值差分的灰度相似性检测参量和结构相似性检测参量结合,构建可测量更多类型周期性纹理织物图像的相似性度量函数,通过阈值化增强图像分块的相似性测量值实现疵点在显著图中的粗定位;最后对显著图粗定位图像分块进行超像素细分割及其二值化处理,并借助连通域分析剔除孤立点,获得完整的疵点轮廓。结果表明,本方法与常规3种方法相比,对周期性纹理织物图像的疵点检测准确率更高,且提取出的疵点轮廓更精确。

关键词: 织物疵点检测, 相似性定位, 超像素分割, 相似性度量函数, 归一化局部均值差分

Abstract:

Aiming at the problem in defect detection and accurate contour segmentation of periodic texture fabric image, a method of fabric defect detection was proposed based on similarity location and superpixel segmentation techniques. The median filter and logarithm enhancement were applied for the detected image, and the saliency image of the enhancement image was estimated by frequency-tuned algorithm to facilitate the preprocessing of the detected image. Combining gray similarity detection parameters based on the normalized local mean difference with structural similarity detection parameters, a similarity metric function capable of measuring more types of periodic texture fabric images was constructed. The rough localization of defects was identified by thresholding the similarity measurement value of the enhancement image blocks. Finally, superpixel fine segmentation and binarization were performed on the rough localization image blocks, and the outliers were eliminated via connected domain analysis to obtain a complete defect contour. The experimental results show that, compared with the three conrentional methods, the proposed method has a higher accuracy in detecting the defects in the periodic texture fabric image, and the extracted defect contour is more accurate.

Key words: fabric defect detection, similarity location, superpixel segmentation, similarity metric function, normalized local mean difference

中图分类号:

TS101.9

朱磊, 任梦凡, 潘杨, 李博涛. 基于相似性定位和超像素分割的织物疵点检测[J]. 纺织学报, 2020, 41(10): 58-66.

ZHU Lei, REN Mengfan, PAN Yang, LI Botao. Fabric defect detection based on similarity location and superpixel segmentation[J]. Journal of Textile Research, 2020, 41(10): 58-66.

图/表 9

图1

图2

图3

图4

图5

表1

本文方法的计算流程"

方法1:基于相似性定位和超像素分割的织物疵点检测方法
输入:织物图像I_r
输出:检测结果B
1:使用式(1)将待检测图像 $I r$ 进行处理得到亮度信息 $I v$
2:对 $I v$ 进行中值滤波和对数增强,得到增强图像 $I$
3: 利用式(4)估计增强图像 $I$ 对应的显著图 $I sm$
4:将 $I$ 分为大小相同且互不重叠的 $N$ 个小块 $P n (n = 1,2, …, N)$ 和以20为步长互相重叠的 $M$ 个小块 $Q i (i = 1,2, …, M)$
5:for $n$ =1: $N$
6: for $i$ =1: $M$
7: if $P n ≠ Q i$
8: S(P_n,Q_i)=α×SSIM(P_n,Q_i)+(1-α)×GRAY(P_n,Q_i)
9: end if
10: end for
11: 使用式(11)对 $P n$ 进行处理,得到相似性粗定位图像 $I c$
12: end for
13:对 $I c$ 进行超像素分割,并使用式(13)对其进行二值化得到 $B c$
14:对 $B c$ 进行连通域分析,得到检测结果 $B$

表1

图6

图7

表2

参考文献 18

[1]	杜帅, 李岳阳, 王孟涛, 等. 基于改进局部自适应对比法的织物疵点检测[J]. 纺织学报, 2019,40(2):44-50.
	DU Shuai, LI Yueyang, WANG Mengtao, et al. Fabric defect detection based on improved local adaptive contrast method[J]. Journal of Textile Research, 2019,40(2):44-50.
[2]	王明景, 白瑞林, 何薇, 等. 图案布匹瑕疵的在线视觉检测[J]. 光电工程, 2014,41(6):19-26.
	WANG Mingjing, BAI Ruilin, HE Wei, et al. Online visual inspection of pattern fabric defects[J]. Opto-Electronic Engineering, 2014,41(6):19-26.
[3]	李文羽, 程隆棣. 基于机器视觉和图像处理的织物疵点检测研究新进展[J]. 纺织学报, 2014,35(3):158-164.
	LI Wenyu, CHENG Longdi. New development of fabric defect detection based on machine vision and image processing[J]. Journal of Textile Research, 2014,35(3):158-164.
[4]	胡克满, 罗少龙, 胡海燕. 应用Canny算子的织物疵点检测改进算法[J]. 纺织学报, 2019,40(1):153-158.
	HU Keman, LUO Shaolong, HU Haiyan. Improved algorithm of fabric defect detection using Canny ope-rator[J]. Journal of Textile Research, 2019,40(1):153-158.
[5]	LI Y, LUO H, YU M, et al. Fabric defect detection algorithm using RDPSO-based optimal Gabor filter[J]. Journal of The Textile Institute, 2018,110(4):487-495. doi: 10.1080/00405000.2018.1489951
[6]	ZHANG B, TANG C M. A method for defect detection of yarn-dyed fabric based on frequency domain filtering and similarity measurement[J]. Autex Research Journal, 2019,19(3):257-262. doi: 10.1515/aut-2018-0040
[7]	CAO J J, WANG N N, ZHANG J, et al. Detection of varied defects in diverse fabric images via modified RPCA with noise term and defect prior[J]. International Journal of Clothing Science & Technology, 2016,28(4):516-529.
[8]	祝双武, 郝重阳. 基于纹理周期性分析的织物疵点检测方法[J]. 计算机工程与应用, 2012,48(21):163-166.
	ZHU Shuangwu, HAO Chongyang. Fabric defect detection method based on texture periodicity ana-lysis[J]. Computer Engineering and Applications, 2012,48(21):163-166.
[9]	HOU X D, ZHANG L Q. Saliency detection: a spectral residual approach[C]// IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis:IEEE, 2007: 18-23.
[10]	ZHANG K B, YAN Y D, LI P F, et al. Fabric defect detection using salience metric for color dissimilarity and positional aggregation[J]. IEEE Access, 2018,6:49170-49181. doi: 10.1109/ACCESS.2018.2868059
[11]	钱晓亮, 张鹤庆, 张焕龙, 等. 基于视觉显著性的太阳能电池片表面缺陷检测[J]. 仪器仪表学报, 2017,38(7):1570-1578.
	QIAN Xiaoliang, ZHANG Heqing, ZHANG Huanlong, et al. Detection of solar cell surface defects based on visual significance[J]. Chinese Journal of Scientific Instrument, 2017,38(7):1570-1578.
[12]	景军锋, 范晓婷, 李鹏飞, 等. 应用深度卷积神经网络的色织物缺陷检测[J]. 纺织学报, 2017,38(2):68-74.
	JING Junfeng, FAN Xiaoting, LI Pengfei, et al. Defect detection of dyed fabrics using deep convolution neural network[J]. Journal of Textile Research, 2017,38(2):68-74.
[13]	王理顺, 钟勇, 李振东, 等. 基于深度学习的织物缺陷在线检测算法[J]. 计算机应用, 2019,39(7):2125-2128.
	WANG Lishun, ZHONG Yong, LI Zhendong, et al. On line detection algorithm of fabric defects based on deep learning[J]. Journal of Computer Applications, 2019,39(7):2125-2128.
[14]	吴志洋, 卓勇, 李军, 等. 基于卷积神经网络的单色布匹瑕疵快速检测算法[J]. 计算机辅助设计与图形学学报, 2018,30(12):2262-2270.
	WU Zhiyang, ZHUO Yong, LI Jun, et al. Fast detection algorithm of single color fabric defects based on convolution neural network[J]. Journal of Computer-Aided Design & Computer Graphics, 2018,30(12):2262-2270.
[15]	CAO J J, ZHANG J, WEN Z J, et al. Fabric defect inspection using prior knowledge guided least squares regression[J]. Multimedia Tools and Applications, 2017,76(3):4141-4157. doi: 10.1007/s11042-015-3041-3
[16]	ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]// 2009 IEEE Conference on Computer Vision and Pattern Recognition, Florida: IEEE, 2009: 1597-1604.
[17]	ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2274-2282. doi: 10.1109/TPAMI.2012.120
[18]	WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004,13(4):600-612. doi: 10.1109/tip.2003.819861 pmid: 15376593

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

检测方法	输入织物图像类型	正确检测数量	错误检测数量	T_PR	F_PR	A_CC	T/s
文献[7]	含疵点	55	15	78.57	64.29	57.14	3.41
文献[7]	不含疵点	25	45	78.57	64.29	57.14	3.41
文献[9]	含疵点	54	16	77.14	71.43	52.86	0.16
文献[9]	不含疵点	20	50	77.14	71.43	52.86	0.16
文献[15]	含疵点	57	13	81.43	57.14	62.14	23.45
文献[15]	不含疵点	30	40	81.43	57.14	62.14	23.45
本文	含疵点	68	2	97.14	1.43	97.86	4.85
本文	不含疵点	69	1	97.14	1.43	97.86	4.85