Multiscale image quality measures for defect detection in thin films

Manufacturing defects in flat surface products such as thin films, paper, foils, aluminum plates, steel slabs, fabrics, and glass sheets result in degradation of the visual quality of the product image. This leads to less satisfied customers, waste of material, and bad company reputation. This research presents a novel application of image visual quality measures such as the multiscale structural similarity index (MS-SSIM). A novel algorithm has been implemented for fast detection and location of defects in many flat surface products. Comparison of the proposed algorithm with the state-of-the-art approaches indicate promising results. A defect detection accuracy of 99.1 % has been achieved with 98.62 % precision, 97.7 % recall/sensitivity, and 100 % specificity. The discriminant power shows how well the MS-SSIM discriminates very effectively between normal and abnormal surfaces. The MS-SSIM has resulted in much better performance than the single-scale SSI approach but at the cost of relatively lower processing speed. The major advantages of the presented approach are as follows: scale invariance, avoiding the problem of parameter selection in the case of the state-of-the-art Gabor filter banks based approach, the higher detection accuracy, and the quasi real-time processing speed.