Vision system for on-loom fabric inspection

Fabric defect detection using morphological filters

“…However, the reliability of manual inspection is limited by boredom and inattentiveness. Indeed, Sari-Sarraf and Goddard [2] found that only about 70% of fabric defects could be detected by the most highly trained inspectors. Therefore, automated detection of fabric defects, which results in the production of high-quality products at a high production speed is definitely desirable.…”

“…However, they cannot inspect fabrics with very large and complex patterns. Other examples include a fuzzy wavelet analysis system for process control in the weaving process [24], a vision system for onloom fabric inspection [2], a vision system for on-circular knitting machine [25] and a vision system for fabric detection based on different Gabor filters [26,27]. These systems are rather expensive which prevent them from being widely adopted by small to medium sized factories.…”

“…However, a suitable window function is needed for this approach to work accurately, which may not be an easy task. Another popular approach is to apply the wavelet transform was used instead [2,21]. Being a special type of wavelet which has an optimal localization in both the spatial domain and the spatial-frequency domain, the Gabor wavelet has been widely used in the field of fabric defect detection [5,6,22].…”

Statistic learning-based defect detection for twill fabrics

“…Approximately 80% of more than 50 identified categories of fabric defects have a preferred orientation [3] .…”

The GIMP Retinex Filter Applied to the Fabric Fault Detection

“…The researches immediately evidenced the difficulties of such a task, difficulties that are intrinsic to the fact that fabric faults are often very small and hardly detectable, having a visibility strongly dependent on illumination (front or back lighting) and reduced by the vibrations of the mounting devices [11][12][13][14][15].…”