基于Adaboost改进算法的铸坯表面缺陷检测方法

Surface Defect Detection of Slab Based on the Improved Adaboost Algorithm

针对钢铁铸坯表面检测及缺陷识别问题,从图像处理及机器学习角度,提出一种基于Adaboost算法的进行钢铁铸坯表面缺陷检测,并结合Gabor小波和Canny边缘检测进行处理,排除伪缺陷的新方法。大量试验表明:该方法能够较好地检出具有缺陷的钢铁铸坯,且具有准确率高、速度快、易实施等优点。

Aiming at problems of the steel slab surface defect detection and identification,from image processing and machine learning point of view,the new method to detect surface defect of steel slab,which was combined with Gabor wavelet and Canny edge-detection processing to remove pseudo-defect,was proposed based the improved Adaboost algorithm.Experimental results show that: the method has high accuracy,fast,easy implement.