Flaw Detection Using Image Registration and Fusion Techniques

The inspection of polished metal contoured surfaces, such as silverware pieces, is much more difficult than for a flat surface, considering the complex curved surface, reflections, and shadows. It is hard to detect flaws when they overlap with shadows and specular reflections, which is typically the case. In this paper, this problem is solved using image registration and image fusion techniques. A continuous-inspection system is developed to take two images sequentially under different lighting conditions when the object is passing under the camera. Shadows and reflections shift, while the flaws do not. From the differences of these two images, flaws can be distinguished from shadows and reflections, and the lost information due to specular reflections can be made up. Fused images without specular reflections were obtained, and a new feature based image registration algorithm is developed to compare these two fused images to detect the surface flaws.