基于主结构提取与签名算法的织物缺陷检测
|
摘要
为解决目前基于图像处理的织物缺陷检测算法中,因织物组织纹理结构复杂、花型繁多造成的检测效果差的问题,提出一种基于主结构提取与图像签名算法的纹理织物缺陷检测方法。首先,使用改进的总变差模型去除织物纹理提取主结构;其次,利用高斯变换对待检测图像进行多尺度分解,构建高斯金字塔;然后根据视觉注意力机制提取颜色特征,通过图像签名算法对疵点进行显著性检测,最后利用自适应阈值的方法分割得到疵点区域。实验结果表明,算法可有效地提取各种织物的主结构,实现不同纹理织物图像的缺陷检测。
Because of the complex texture structure and various patterns,the existing fabric defect detection algorithms based on image processing are low in accuracy. In order to solve the problem,a new method of fabric defect detection based on main structure extraction and the signature algorithm was designed. Firstly,using the total variation model to extract the main structure of the textured fabric.Secondly,the Gaussian transformation is used to obtain the multi-scale image of the image and the Gaussian pyramid is constructed. Then color features are extracted according to the visual observation mechanism,and the defect is detected by the image signature algorithm.Finally,the defect region is segmented by the adaptive threshold method. The experimental results show that the algorithm can effectively extract the main structure of various fabrics,and can realize accurate defect detection for different texture images.
Because of the complex texture structure and various patterns,the existing fabric defect detection algorithms based on image processing are low in accuracy. In order to solve the problem,a new method of fabric defect detection based on main structure extraction and the signature algorithm was designed. Firstly,using the total variation model to extract the main structure of the textured fabric.Secondly,the Gaussian transformation is used to obtain the multi-scale image of the image and the Gaussian pyramid is constructed. Then color features are extracted according to the visual observation mechanism,and the defect is detected by the image signature algorithm.Finally,the defect region is segmented by the adaptive threshold method. The experimental results show that the algorithm can effectively extract the main structure of various fabrics,and can realize accurate defect detection for different texture images.
引文
[1]李明,景军锋,李鹏飞.应用GAN和Faster R-CNN的色织物缺陷识别[J].西安工程大学学报,2018,32(6):663-669.LI M,JING J F,LI P F.Yarn-dyed fabric defect detection based on GAN and faster R-CNN[J].Journal of Xi'an Polytechnic University,2018,32(6):663-669.
[2]JING J F,ZHANG H H,WANG J,et al.Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method[J].Journal of the Textile Institute Proceedings&Abstracts,2013,104(1):18-27.
[3]NGAN Y T H,PANG K H G,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J].Pattern Recognition,2004,38(4):559-576.
[4]LI C,LIU C,GAO G,et al.Robust low-rank decomposition of multi-channel feature matrices for fabric defect detection[J].Multimedia Tools&Applications,2018,78(6):7321-7339.
[5]HUANGPENG Q Z,ZHANG H,ZENG X R,et al.Automatic visual defect detection using texture prior and low-rank representation[J].IEEE Access,2018(6):37965-37976.
[6]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 J F,FAN X T,LI P F,et al.Yarn-dyed fabric defect detection based on deep convolutional neural network[J].Journal of Textile Research,2017,38(2):68-74.
[7]LI Y,ZHAO W,PAN J.Deformable patterned fabric defect detection with fisher criterion-based deep learning[J].IEEE Transactions on Automation Science&Engineering,2017,14(2):1256-1264.
[8]XU L,YAN Q,XIA Y,et al.Structure extraction from texture via relative total variation[J].ACM Transactions on Graphics,2012,31(6):1-10.
[9]张波,汤春明.基于相对总变差模型与自适应形态学的织物瑕疵检测[J].纺织学报,2017,38(5):145-149.ZHANG B;TANG CH M.Fabric defect detection based on relative total variation model and adaptive mathematical morphology,Journal of Textile Research,2017,38(5):145-149.
[10]彭天强,栗芳.哈希编码结合空间金字塔的图像分类[J].中国图象图形学报,2016,21(9):1138-1146.PENG T Q,LI F.Image classification algorithm based on hash codes and space pyramid[J].Journal of Image and Graphics,2016,21(9):1138-1146.
[11]LI J,LEVINE M D,AN X,et al.Visual saliency based on scale-space analysis in the frequency domain[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(4):996-1010.
[12]HOU X,HAREL J,KOCH C.Image Signature:highlighting sparse salient regions[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(1):194.
[13]LI P,ZHANG H,JING J,et al.Fabric defect detection based on multi-scale wavelet transform and Gaussian mixture model method[J].The Journal of The Textile Institute,2015,106(6):587-592.
[14]王传桐,胡峰,徐启永,等.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(3):154-160.WANG CH T,HU F,XU Q Y.Application of algorithm with improved frequency-tuned salient region in fabric defect detection[J].Journal of Textile Research,2018,39(3):154-160.
[15]GUAN S,SHI H.Fabric defect detection based on the saliency map construction of target-driven feature[J].Journal of the Textile Institute,2018,109(9):1133-1142.
[2]JING J F,ZHANG H H,WANG J,et al.Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method[J].Journal of the Textile Institute Proceedings&Abstracts,2013,104(1):18-27.
[3]NGAN Y T H,PANG K H G,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J].Pattern Recognition,2004,38(4):559-576.
[4]LI C,LIU C,GAO G,et al.Robust low-rank decomposition of multi-channel feature matrices for fabric defect detection[J].Multimedia Tools&Applications,2018,78(6):7321-7339.
[5]HUANGPENG Q Z,ZHANG H,ZENG X R,et al.Automatic visual defect detection using texture prior and low-rank representation[J].IEEE Access,2018(6):37965-37976.
[6]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 J F,FAN X T,LI P F,et al.Yarn-dyed fabric defect detection based on deep convolutional neural network[J].Journal of Textile Research,2017,38(2):68-74.
[7]LI Y,ZHAO W,PAN J.Deformable patterned fabric defect detection with fisher criterion-based deep learning[J].IEEE Transactions on Automation Science&Engineering,2017,14(2):1256-1264.
[8]XU L,YAN Q,XIA Y,et al.Structure extraction from texture via relative total variation[J].ACM Transactions on Graphics,2012,31(6):1-10.
[9]张波,汤春明.基于相对总变差模型与自适应形态学的织物瑕疵检测[J].纺织学报,2017,38(5):145-149.ZHANG B;TANG CH M.Fabric defect detection based on relative total variation model and adaptive mathematical morphology,Journal of Textile Research,2017,38(5):145-149.
[10]彭天强,栗芳.哈希编码结合空间金字塔的图像分类[J].中国图象图形学报,2016,21(9):1138-1146.PENG T Q,LI F.Image classification algorithm based on hash codes and space pyramid[J].Journal of Image and Graphics,2016,21(9):1138-1146.
[11]LI J,LEVINE M D,AN X,et al.Visual saliency based on scale-space analysis in the frequency domain[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(4):996-1010.
[12]HOU X,HAREL J,KOCH C.Image Signature:highlighting sparse salient regions[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(1):194.
[13]LI P,ZHANG H,JING J,et al.Fabric defect detection based on multi-scale wavelet transform and Gaussian mixture model method[J].The Journal of The Textile Institute,2015,106(6):587-592.
[14]王传桐,胡峰,徐启永,等.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(3):154-160.WANG CH T,HU F,XU Q Y.Application of algorithm with improved frequency-tuned salient region in fabric defect detection[J].Journal of Textile Research,2018,39(3):154-160.
[15]GUAN S,SHI H.Fabric defect detection based on the saliency map construction of target-driven feature[J].Journal of the Textile Institute,2018,109(9):1133-1142.