Image Processing of steel sheets for Defect Detection by using Gabor Wavelet
Subject Areas : Special
masoud shafiee
1
,
mostafa sadeghi
2
1 -
2 -
Keywords: Cell counting, Color segmentation, CIElab color space, Fuzzy c-means, Immunohistochemistry, K-means, Meningioma, Mitosis index, Ultra erosion,
Abstract :
In different steps of steel production, various defects appear on the surface of the sheet. Putting aside the causes of defects, precise identification of their kinds helps classify steel sheet correctly, thereby it allocates a high percentage of quality control process. QC of steel sheet for promotion of product quality and maintaining the competitive market is of great importance. In this paper, in addition to quick review of image process techniques used, using image process by means of Gabor wavelet, a fast and precise solution for detection of texture defects in steel sheet is presented. In first step, the approach extracts considerable texture specification from image by using Gabor wavelet. The specification includes both different directions and different frequencies. Then using statistical methods, images are selected that have more obvious defects, and location of defects is determined. Offering the experimental samples, the accuracy and speed of the method is indicated.
