Existing Weld Seam Recognition Based on Image Processing

In this paper, the image processing method is adopted to recognize the weld seam. A set of weld seam recognition system is built. The software part of the system is introduced as steps of image preprocessing, edge detection and image post-processing. The anisotropic filtering is used to remove the image noise, at the same time, it maintains the edge of the image as much as possible. Then the Canny operator is applied to obtain the edge of the weld seam. Finally the morphology operation is performed to extract the weld seam field. The experiment part compares the weld seam recognition accuracy and the average running time in four cases.