基于二维小波变换及图像模式识别的焊缝坡口识别

GROOVE RECOGNITION BASED ON 2-D WAVELET TRANSFORM AND MODEL RECOGNITION

采用二维小波变换及二值化方法处理初始条件下管道焊缝坡口图像,获取焊缝坡口纹理信息,作为模板。 对后续坡口图像进行同样的小波变换及二值化处理,利用模式识别方法获取后续图像焊缝坡口及其中心线的基本 位置信息,研究的焊缝坡口识别算法为实现自然光下焊缝坡口实时跟踪提供了理论依据。

Process original groove image with 2-D wavelet transform and binary thresholded algorithm, and the groove texture information got by above image processing is made as template. Process subsequent groove image with the same algorithms, then gain the information of groove position and its centerline via model recognition algorithms. The algorithms afford theoretic grounds for real time track under natural light.