International Conference on Computer and Computer Intelligence (ICCCI 2011)
43 Car Body Paint Defect Detection and Classification
Download citation file:
Quality inspection is an important aspect of modern industrial manufacturing. In automotive industry, automatic paint inspection is of crucial importance to maintain the paint quality. In most worldwide automotive industries, the inspection process is still mainly performed by human vision, and thus, is insufficient and costly. Therefore, automatic paint defect inspection is required to reduce the cost and time waste caused by defects. In this paper a new approach is proposed for detection of defects on painted car body through serial paint images and subsequent classifying of the localized defect types. Initially, defects are detected and localized by using a rotation invariant measure of the local variance (VAR) operator and next, then classified by using learning vector quantization (LVQ) neural network.