Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm

Abstract

The invention discloses a surface crack texture extraction method based on fusion of a seepage algorithm and an adaptive Canny algorithm. The method comprises the following steps: getting and preprocessing a surface crack image; processing the preprocessed surface crack image by using an adaptive Canny algorithm and a seepage algorithm respectively to get a first crack image and a second crack image; extracting the low-frequency component and high-frequency component of the first crack image and the low-frequency component and high-frequency component of the second crack image through wavelet transform; superimposing the extracted low-frequency components to get a fused low-frequency part, and superimposing the extracted high-frequency components to get a fused high-frequency part; and getting a reconstructed image through inverse wavelet transform, wherein the reconstructed image is a fused crack image. A more real crack image is obtained by the method. The method is used in a product appearance quality detection assembly line. By using the method, the detection efficiency is improved, time is saved, and the human cost is reduced.

Description

technical field [0001] The invention relates to a method for extracting a crack texture, in particular to a method for extracting a crack texture by combining a penetration algorithm and an adaptive Canny algorithm. Background technique [0002] Nowadays, there are more and more applications to obtain information by analyzing images, and the requirements for restoring the authenticity of image features are getting higher and higher, that is, to retain as many physical features of images as possible during processing, and to extract and analyze detailed information in images. Provide a reliable source. Taking the analysis of surface cracks as an example, in the process of image processing, physical characteristics such as the connectivity of cracks, details of crack edges, small branching burrs on edges, and the direction of crack tracks are preserved, and the authenticity of cracks is restored. It is of great significance to analyze the causes of cracks and prevent the form...

AI Technical Summary

Problems solved by technology

But the Canny operator also has some problems: 1) Since the algorithm guarantees the accuracy of the detection, there are missed judgments in the detection process, resulting in interruptions in the detected cracks, which cannot maintain the connectivity of the original cracks; 2) due to the existence of Misjudgment phenomenon, there is a unilateral detection phenomenon in the detection of crack edges

However, the penetration algorithm corrodes the small burrs on the edge, and the edge of the crack is relatively flat, so it cannot retain more crack edge information

[0004] Although the above detection algorithms have achieved certain results, they will face two problems in the application process: 1) the connectivity of the crack is maintained, but the crack edge location is not accurate; 2) more crack edge information is retained, but The continuity of the crack is not enough

Images