Fabric defect detection based on deep-handcrafted feature and weighted low-rank matrix representation

Abstract

In the process of textile production, automatic defect detection plays a key role in controlling product quality. Due to the complex texture features of fabric image, the traditional detection methods have poor adaptability, and low detection accuracy. The low rank representation model can divide the image into the low rank background and sparse object, and has proven suitable for fabric defect detection. However, how to further effectively characterize the fabric texture is still problematic in this kind of method. Moreover, most of them adopt nuclear norm optimization algorithm to solve the low rank model, which treat every singular value in the matrix equally. However, in the task of fabric defect detection, different singular values of feature matrix represent different information. In this paper, we proposed a novel fabric defect detection method based on the deep-handcrafted feature and weighted low-rank matrix representation. The feature characterization ability is effectively improved by fusing the global deep feature extracted by VGG network and the handcrafted low-level feature. Moreover, a weighted low-rank representation model is constructed to treat the matrix singular values differently by different weights, thus the most distinguishing feature of fabric texture can be preserved, which can efficiently outstand the defect and suppress the background. Qualitative and quantitative experiments on two public datasets show that our proposed method outperforms the state-of-the-art methods.

End-to-end fabric defect detection algorithm using lighter feature fusion network

“…Manual inspection cannot complete the fast and accurate detection of a large number of fabrics. There is an urgent need for technological change to machine intelligence detection [3]. Considering the shortcomings of manual detection, some scholars have begun to try to apply traditional image processing methods to fabric defect detection.…”

Fabric defect detection based on transfer learning and improved Faster R-CNN

“…Automatic defect detection plays a key role in controlling product quality. 1 For some time, the detection process of fabric defects is performed by manual visual inspection. The high costs of manual cloth inspection have affected the detection rate, 2 and even the most skilled cloth inspection workers can only find approximately 70% of defects.…”

“…4 Therefore, automatic detection of fabric defects is needed to reduce waste in both time and costs from manual detection 5 to improve the overall quality of products and strengthen the competitiveness of textile exports. The directional characteristics of fabric defects can be divided into three categories: (1) weft defects; (2) longitudinal defects; and (3) defects without directional features. The purpose of automatic detection is to determine the position and type of defect in fabrics without any human inference.…”