论文部分内容阅读
在焊接条件下，用工业摄像机获取的焊缝的实时图像中常含有各种干扰信息，导致传统的图像边缘检测的方法很难准确地检测出焊缝的边缘。为了提高焊缝实时图像处理的准确性，提出了宏观处理与微观检测相结合的思想。分形理论被引入了图像处理，建立了焊缝图像的分形数学模型，对其性质进行了讨论与证明。最后给出了图像综合处理的方法。这种图像处理思想不仅可用于焊接图像处理，对图像处理向智能处理方向发展也有重要的启发意义。
Under welding conditions, real-time images of weld seams obtained with industrial cameras often contain various kinds of interference information, which leads to the difficulty of accurately detecting the edge of the weld by the conventional image edge detection method. In order to improve the accuracy of the real-time image processing of the weld, a combination of macroscopic processing and microscopic inspection is proposed. Fractal theory was introduced into image processing and a fractal mathematical model of weld image was established. Its properties were discussed and proved. Finally, the method of image processing is given. This kind of image processing idea can not only be used for welding image processing, but also has important enlightenment significance for the image processing to the direction of intelligent processing.