Fabric defect detection method based on texture structure analysis
基于纹理结构分析的织物疵点检测方法

A new fabric defect segmentation was proposed based on texture structure analysis in this paper. Firstly in accordance with the characteristics of the well-regulated texture, texture primitive template was calculated using auto-correlation function and defect image was enhanced using difference between each texture primitive and primitive template. Secondly local roughness of texture image was calculated to locate defect, and defect image was segmented using threshold value gained according to Otsu's approach to detect fabric defect. Lastly validity and robustness of this approach is proved by different fabric defect image segmentation in our experiment.