Automatic Visual Defect Detection Using Texture Prior and Low-Rank Representation

Automatic Visual Defect Detection Using Texture Prior and Low-Rank Representation
复制标题

使用纹理先验和低阶表示的自动视觉缺陷检测

DOI:
10.1109/access.2018.2852663
复制
发表时间:
2018-07
期刊:
影响因子:
3.9
通讯作者:
Wenwei Huang
Wenwei Huang
中科院分区:
计算机科学3区
文献类型:
--
作者:
Qizi Huangpeng;Hong Zhang;Xiangrong Zeng;Wenwei Huang

文献摘要

参考文献

被引文献

相似文献

用于质量控制的自动表面检测在很大程度上采用了图像处理技术,例如在钢材和织物缺陷检查中。质量控制行业对缺陷图像分析的需求不断增长,以发挥其在视觉检测中的重要作用。在本文中,我们介绍了一种使用基于纹理先验的低秩表示来检测自然表面上的缺陷的无监督方法,并将检测过程制定为一种新颖的加权低秩重建模型。该方法的第一步是通过构建纹理先验图来估计给定图像之前的纹理,其中较高的值表示较高的异常概率。该方法的第二步借助纹理先验通过低秩分解来检测缺陷。对合成图像和真实图像的实验表明,与表面缺陷检测研究中最先进的方法相比,该方法在检测精度和计算效率方面具有优越性。这一贡献对于缺陷检测很大程度上依赖于手动检查的制造商(例如钢铁和织物)特别感兴趣。
Automatic surface detection for quality control has largely employed image processing techniques, for example in steel and fabric defect inspection. There are rising demands in the quality control industry for defective image analysis to fulfill its vital role in visual inspection. In this paper, we introduce an unsupervised method using a low-rank representation based on texture prior for detection of defects on natural surfaces and formulate the detection process as a novel weighted low-rank reconstruction model. The first step of the proposed method estimates the texture prior to a given image by constructing a texture prior map where higher values indicate a higher probability of abnormality. The second step of the proposed method detects the defect via low-rank decomposition with the help of the texture prior. Experiments on synthetic and real images show that the proposed method is superior in terms of detection accuracy and competitive in computational efficiency with respect to the state-of-the-art methods in surface defect detection research. This contribution is of particular interest for manufacturers (e.g., steel and fabric) for which defect detection largely relies on manual inspection.
DOI: 10.1109/icassp.2001.940645
发表时间: 2001-05
期刊: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
影响因子: --
作者:
Y. Zhi;G. Pang;N. Yung
通讯作者: Y. Zhi;G. Pang;N. Yung
DOI: 10.1108/ec-04-2015-0092
发表时间: 2016-05
影响因子: 1.6
作者:
Qi Peng;Tianyu Liu;Quan Sun;Wenwei Huang
通讯作者: Qi Peng;Tianyu Liu;Quan Sun;Wenwei Huang
DOI: --
发表时间: 1997
期刊: --
影响因子: --
作者:
L. Ouis
通讯作者: L. Ouis
DOI: 10.1109/tii.2016.2522191
发表时间: 2016-01
影响因子: 12.3
作者:
Yunwon Park;In-So Kweon
通讯作者: Yunwon Park;In-So Kweon
DOI: 10.5555/1756006.1859931
发表时间: 2010-03
期刊: Journal of machine learning research : JMLR
影响因子: --
作者:
R. Mazumder;T. Hastie;R. Tibshirani
通讯作者: R. Mazumder;T. Hastie;R. Tibshirani