Optimal Gabor Filtering for the Inspection of Striped Fabric
As an important part of products’ quality control, automatic fabric inspection has attracted much attention in the past. Compared with manual inspection, automatic inspection can achieve not only more accurate detection results but also a higher efficiency. With the diversified fabric texture and patterns, it is very necessary to develop distinctive detection methods for different types of fabric. In this paper, based on optimal Gabor filters, a novel defect detection model is proposed to address the inspection of striped fabric, which is commonly used in our daily dresses. In the framework of the detection model, Gabor filters perpendicular to the stripe pattern are optimized to minimize the variance of the image but enhance the features of defects. Thereafter, an adaptive thresholding is set to accurately segment the defective image area. The evaluation of the proposed detection model is conducted using samples of the TILDA database. It is revealed that the common fabric defects as well as the pattern variants could be successfully detected through the proposed detection model.
KeywordsFabric inspection Optimal Gabor transformation Stripe fabric
This work was supported in part by the Natural Science Foundation of China under Grant 61703283, 61773328, 61672358, 61703169, 61573248, in part by the Research Grant of The Hong Kong Polytechnic University (Project Code:G-YBD9 and G-YBD9), in part by the China Postdoctoral Science Foundation under Project 2016M590812, Project 2017T100645 and Project 2017M612736, in part by the Guangdong Natural Science Foundation under Project 2017A030310067, Project with the title Rough Sets-Based Knowledge Discovery for Hybrid Labeled Data and Project with the title The Study on Knowledge Discovery and Uncertain Reasoning in Multi-Valued Decisions.
- 9.Li, P., Liang, J., Shen, X., Zhao, M., Sui, L.: Textile fabric defect detection based on low-rank representation. Multimedia Tools Appl. 1–26 (2017)Google Scholar