Exploration of the algorithm of automatic recognition of defects in ultrasonic testing image

Abstract. Traditional detection is through a lot of human judgment for defect recognition. The efficiency is low and the accuracy is not high in this way. With the development of digital image processing technology in the industrial filed. Research of automatic recognition on defect image becomes meaningful. In this paper, we puts forward an automatic recognition algorithm on the A defect image sequence. After analyzing the defect image, first of all, we apply k-means cluster segmentation on the original image to get the acoustic images with false alarm. In order to get full acoustic images by preventing the false alarm, we use the projection algorithm and achieved good results. Finally we do the bottom wave and defect wave detection on the acoustic image, and realize the recognition of defect automatically. The experimental results show that the method we proposed has high accuracy