Surface Defect Inspection for Vehicle Heat Exchangers Based on LBP and SVM

Abstract

To tackle the problems appeared in traditional surface defect inspection for vehicle heat exchangers which is mainly depended on manual execution, machine vision has been introduced due to its unparalleled characteristics of on-line, fast, high precision and non-contact. In this paper, an automatic surface defect detection algorithm employing machine vision technology has been presented. Treating the surface defect detection as a texture discrimination problem, the proposed method first uses an LBP (Local Binary Pattern) descriptor to represent the image of the heat exchanger, which has efficiently alleviated the effect of uneven illumination. Then the whole texture image has been partitioned into several non-overlapped 32×32 blocks and each block is subject to classification by an SVM (Support Vector Machine) to judge if it is a defect area. The experiments have been performed and the results have demonstrated the effectiveness and the efficiency of the proposed method.