Weldment contour detection method

Abstract

The invention relates to a weldment contour detection method. The weldment contour detection method comprises the following steps: 1, image enhancement preprocessing, 2, image histogram equalization processing, 3, image denoising, 4, image background interference removal and 5, image edge improvement. According to the invention, the weldment image is preprocessed in an image enhancement mode, so that the edge detection precision of the weldment image is improved; According to the invention, histogram equalization is introduced to improve the gray level dynamic range of the image, the image contrast is improved, and the image is clearer; According to the invention, the median filtering technology is adopted to carry out denoising processing on the image, operation is simple, implementation is convenient, and edge information of the image is protected while isolated noise points are filtered out; The invention adopts the probabilistic Hough transform method to judge and connect the pixel points disconnected from the edge of the image, and is small in calculation amount, high in practicability and high in efficiency.

Description

technical field [0001] The invention relates to a weldment contour detection method, which belongs to the technical field of weldment contour detection. Background technique [0002] In the automatic welding system based on vision and model matching, the accuracy of the weld seam and contour information extraction of the workpiece to be welded directly affects the quality of automatic welding. Due to the influence of light intensity, etc., the collected weldment images may have problems such as uneven illumination, overexposure and underexposure. The change of the degree value is not obvious and the gradient is small, which makes the edge difficult to be detected. If the traditional edge detection operator is directly used to detect the edge of the image, the edge line is very easy to break. Usually, the welding environment is relatively complex and harsh, and the uneven weldment material, stains on the surface of the weldment, and other objects in the background will form...

AI Technical Summary

Problems solved by technology

Due to the influence of light intensity, etc., the collected weldment images may have problems such as uneven illumination, overexposure and underexposure. The change of the degree value is not obvious and the gradient is small, which makes the edge difficult to be detected

If the traditional edge detection operator is directly used to detect the edge of the image, the edge line is very easy to break

Usually, the welding environment is relatively complex and harsh, and the uneven weldment material, stains on the surface of the weldment, and other objects in the background will form corresponding noise in the image, which will seriously interfere with the edge detection of the weld

If the Canny operator is directly used to detect the weld seam and outer contour of the weldment, the detected edge line will have the following three problems: 1. The unevenness of the surface color of the weldment, the pollution of stains and the characters on the surface of the weldment Serial coding etc. introduce many irregular interference edges inside the weldment; 2. When the exposure is too high or too low, the discrimination between the weldment and the background in some areas is low, the gray value gradient is too small, and the corresponding edge It is difficult to be detected, and there is a problem of fracture on the edge of some weldment contours; 3. Other texture information in the background introduces too many interference edges, resulting in most of the detected edges being useless edges

Excessive interfering edges and edge breakage will seriously affect the accuracy of model matching, enough to cause failure of model matching, making it difficult to automate the welding process

[0003] The Canny edge detection operator is a high-performance optimized edge detection operator. This algorithm is difficult to obtain satisfactory results in weldment image detection, so it will be difficult to obtain complete and accurate results by directly using other traditional edge detection algorithms. outline edge of

Images