Wavelet versus contourlet features for automatic defect detection on hot rolled steel sheet

Abstract

The automatic visual inspection systems (AVIS) are being obvious now-a-days in modern manufacturing industries for quality control, ease of documentation and reduced labor cost. The automatic detection of hot rolled steel surface defects in a real process is challenging due to the localization of it on a large surface and its rare occurrences. In this work an effort has been made to extract a set of features that can effectively address the problem of defect detection on hot rolled steel surface by using machine learning algorithm. It is intended to extract two types of features, namely wavelet and contourlet features with two and three resolution levels separately, and then make a comparison of performance of classification accuracy using these features. Here it is proposed to use state-of-the art support vector machine (SVM) classifier as the machine learning algorithm for detecting the defect surface and normal (defects free) surface. Experimental results on 14 different types of steel surface defects show that `haar' wavelet features with three decomposition levels performs better than two levels `haar' feature set or two and three decomposition levels contourlet feature set.