<title>Detection of local defects in textile webs using Gabor filters</title>

Abstract

A method of image analysis is proposed for detection of local defects in materials with periodic regular texture. A general improvement and enlargement of vision system capabilities for versatility, full automatism, computational efficiency, and robustness in their application to the industrial inspection of periodic textured materials is pursued. In the proposed method, a multiscale and multiorientation Gabor filter scheme that imitates the early human vision process is applied to the sample under inspection. The designed algorithm automatically segments defects from the regular texture. A variety of examples of fabric inspection are presented. In all of them defects are successfully segmented from the texture background.

Real-Time Vision-Based System for Textile Fabric Inspection

“…Table 3. Geometric features from Table 1 for defects from Figure 5, obtained from Figure 5 Black horizontal error c 6 White horizontal error c 7 Black spot c 8 White spot…”

“…However, the influence of noise and the classification problem are not considered. In [8] a variety of defects are analyzed for different fabrics and the flaws are finally segmented from the background. Gabor functions are used for feature extraction.…”

A note on neurofractal-based defect recognition and classification in nonwoven web images

“…* Corresponding author. Email: latifi@aut.ac.ir Escofet, Navarro, Millan, and Pladellorens (1996) analyze a variety of defects in different fabrics and in each case flaws are finally segmented in the background, while Gabor functions are used for feature extraction. Mueller and Nicolay (1994) apply morphological image processing for gray-level inspections.…”

A Model for African Fabrics Analysis and Recognition

“…Gabor filters was applied to automatically segment defects on nonsolid fabric images having variety of interlacing patterns [4]. Though, Gabor filter is a widely feature extraction method, especially in image texture analysis, the selection of optimal filter parameters is usually problematic and unclear.…”