The goal of the study was to find the best way to detect the edges of welds in images. The researchers used a method called the Canny operator to accurately identify the weld edges. They compared this method to other edge-detecting techniques like the Kirsch, Prewitt, Robert, Sobel, and Gauss-Laplace operators. The results showed that the Canny operator was the most effective in detecting weld edges and is suitable for tracking seams using vision sensors.