Bottle cap scratches detection with computer vision techniques

This paper presents a novel method that can detect arbitrary shaped scratches on bottle caps based on a template edge image comparison method. In this method, edge-preserving smoothing based on a guided filter technique is first applied and edge information is extracted. Then modified Hough transform is combined with a hierarchical orientation searching method to locate the position and orientation of the candidate bottle cap in the test image. Finally, rotation compensated edge image is compared with the template edge image in order to determine whether there exist scratches or not in the test image. Experimental results showed that the False Rejection Rate and the False Acceptance Rate are both below 1.5%, which proved the effectiveness of our proposed algorithm.