An Image Processing based Fault Detection in Fabrics. Issue 1 (December 2020)

• Record Type: Journal Article
• Authors: Jacintha, V; Shakthi Murugan, K H; Kumar, Karanam Arun; Devi, S; Saravanan, G; Shyam Ganesh, D
• Is Part Of: IOP conference series. Volume 994:Issue 1(2020)
• Publication Date: 2020-12
• Subjects: Fabrics -- K-Means -- FCM -- SVM; Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/994/1/012036
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: There are several defect that are occurring in fabrics they occur in the form of a hole, mark, improper stitch, oil stains, missed threads etc. The common thing about these defect are, they cannot be viewed by the naked eye. Hence we firmly say that they defects cannot be effectively identified by manual inspection. However, a much-automated method of inspection is essential. Hence, we are going for computer vision based defect detection. The primary requirement about computer vision is a full-fledged camera that can capture even minute defects. We use K-means clustering along with FCM segmentation in order to segment the flaws efficiently. The classifier used here is SVM classifier, with sensible classification rates of up to 98.9%.