Yarn-Dyed Fabric Defect Detection Based On Autocorrelation Function And GLCM

Abstract

In this study, a new detection algorithm for yarn-dyed fabric defect based on autocorrelation function and grey level co-occurrence matrix (GLCM) is put forward. First, autocorrelation function is used to determine the pattern period of yarn-dyed fabric and according to this, the size of detection window can be obtained. Second, GLCMs are calculated with the specified parameters to characterise the original image. Third, Euclidean distances of GLCMs between being detected images and template image, which is selected from the defect-free fabric, are computed and then the threshold value is given to realise the defect detection. Experimental results show that the algorithm proposed in this study can achieve accurate detection of common defects of yarn-dyed fabric, such as the wrong weft, weft crackiness, stretched warp, oil stain and holes.

Automatic fabric defect detection using a deep convolutional neural network

“…Methods of manually designed features include GLCM [15], LBP [9] and RCT [16]. Models for transfer learning include LeNet-5, AlexNet [49] and VGG16 [50].…”

“…Models for transfer learning include LeNet-5, AlexNet [49] and VGG16 [50]. According to [15], the greyscale of the image (Ng), inter-pixel distance (d) and inter-pixel orientation (h) are Ng = 16, d = 3 and h = 0°, respectively. The graphics card type is NVIDIA GeForce GTX 745.…”

“…These methods can be classified into four main categories: (i) statistical; (ii) spectral; (iii) model-based; and (iv) learning-based approaches. Zhu et al [15] combined the AF and the grey level co-occurrence matrix (GLCM) methods to detect yarndyed fabric defects. Zhu et al [15] combined the AF and the grey level co-occurrence matrix (GLCM) methods to detect yarndyed fabric defects.…”

Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY

“…However, this type of method fits for several defect detection problems, due to the high sensitivity to noise interference and the only application capability on patterned textures makes it unsuitable for most of the detection tasks because of their random surface. Zhu et al [23] published a study about a yarn-dyed fabric defect detector, which combines autocorrelation with the GLCM; however, the system was tested only on 16 samples and no detailed results were reported.…”

A Method for Defect Detection of Yarn-Dyed Fabric Based on Frequency Domain Filtering and Similarity Measurement

“…Furthermore, the size selection of the window in the local binary pattern (LBP) detection method is of equal importance, which requires the training of a defect-free image in advance. Zhu et al [10] have used the autocorrelation function and gray-level co-occurrence matrix (GLCM) to extract the defects of yarn-dyed fabric; however, the inherent disadvantage of GLCM in texture feature extraction is that it is computationally intensive.…”