Application of wavelet transform in optical thin film defect automatic inspection system

This paper applied digital image processing technology to the defect inspection of optical thin film products. It first used wavelet transform on the image for two times to reduce the size. Then the edge of the defect would be found out through the screening of the isotropic results after 45 degrees and 90 degrees increment of Laplace operator, and then used the statistic threshold method to separate the defect image, and in the end used Hough transform to distinguish the defect. The experimental result showed that it could test all the flaws on the 100 sheets of images, and successfully distinguished the spot defect and line defect, the distinguish rate is 96%, and it only cost 0.9 sec to detect a sheet. Therefore it has clear that this paper has successfully developed a set of real time defect inspection system applicable to the optical thin film.