期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2015
卷号：8
期号：6
页码：245-252
DOI：10.14257/ijsip.2015.8.6.26
出版社：SERSC
摘要：Weld seam recognition is the key technique in visual tracking research. Based on the weld image features, the image preprocessing and the linear feature extraction method of the weld seam recognition are designed. The extended adaptive median filtering method and modified Otsu adaptive threshold selection method for image segmentation are used in the image pre-processing process, to remove the noise and compress the image data. Through comparing with several other edge operators, the Roberts operator is chosen to achieve the goal of detecting the welding edge. Finally, the weld seam information is extracted through Hough transform and a satisfied result can be acquired. The study provides a theoretical support for the following designing of the weld tracking system
