An Effective Framework of Automated Visual Surface Defect Detection for Metal Parts

Developing effective automated visual surface defect detection of metal parts is a challenge due to highly reflective surfaces and miscellaneous defect patterns. In this work, an effective framework consisting of an image registration module and a defect detection module is proposed to cope with this challenge. First, an algorithm based on dual weighted principal component analysis is designed for the image registration module. In this algorithm, the visual feature and spatial feature are integrated into a unified principal component to obtain highly accurate image registration results. Then, a defect detection module is constructed using an image difference algorithm with prior constraints. In this module, two categories of constraint bounding boxes are designed to reduce the misdetection due to the susceptible edges and improve the accuracy of surface defect detection of metal parts. Three applications, including a magnetic resonance imaging dataset, a printed circuit board dataset, and an industrial case of the stainless-steel positioning pins are provided to illustrate the superiority of the proposed framework.