In different stages of steel production, many defects appear on the surface of the sheet. Regardless of the causes of failures, accurate detection of their types helps to correctly classify the steel sheet and thus occupies a high percentage of the quality control proce
More
In different stages of steel production, many defects appear on the surface of the sheet. Regardless of the causes of failures, accurate detection of their types helps to correctly classify the steel sheet and thus occupies a high percentage of the quality control process. Quality control of steel sheets is of great importance in order to improve product quality and maintain a competitive market. In this article, while reviewing the used image processing techniques, by using image processing with the help of two-dimensional Gabor wavelet, a fast and high-accuracy solution is presented for revealing textural defects of steel sheets. At first, using Gabor wavelet, it extracts significant textural features from the images, which includes both different directions and different frequencies. Then, using the statistical method, the images that contain the defects are selected more clearly and the location of the defect is determined. By presenting test samples, the accuracy and speed of the method used have been shown.
Manuscript profile
