Surface defect detection by a texture analysis with a neural network

In this paper a neural algorithm for defect detection in industrial inspection is proposed. One of the most difficult problems in process control and automated inspection is the identification, description and classification of surface defects and anomalies. A critical role in surface inspection is played by texture because most of the defects are rich in textural content. The goal of this work is to propose a quantitative and qualitative technique to detect surface defects with oriented texture structure. The neural algorithm, that the authors propose to classify an oriented flow field, can classify each kind of defect with textural characteristics: once the system has been set to recognize a limited number of patterns, it is able to identify and analyze a broader family of patterns. To the surface image to be analyzed is associated a vector field which computes the dominant local orientations of the gradients of the image smoothed with a Gaussian filter. The different defective surface regions are recovered and classified minimizing an energy function by means of a neural network. Experimental results of tests performed on ferromagnetic surfaces show as the proposed neural at algorithm works