원문정보
초록
영어
A new detection approach is proposed to detect various uniform and structured fabric defects based on the multiple Gabor filters and Kernel Principal Component Analysis. First of all, images are filtered by multiple Gabor filters with six scales and four orientations to extract feature vectors. After that, the sub-blocks divided from the feature vectors have been fused and the high-dimension data can be reduced by using Kernel Principal Component Analysis. Finally, the similarity matrix is calculated by Euclidean norm and segmented with OTSU threshold method. The experiment has been done by integrating hardware and NI LabVIEW graphical programming language. Experimental results show that proposed algorithm improves feature extraction capability significantly and has high recognition rate.
목차
1. Introduction
2. Description of Method
2.1. Image Inspection
2.2. Calibration Procedure
3. Experiments Results and Analysis
4. Automation for Inspection
4.1. Acquisition System Hardware Selection and Design
4.2. LabVIEW Graphical User Interface Design
5. Conclusion
Acknowledgements
References