Image edge processing method and device, electronic equipment and storage medium

Abstract

The invention provides an image edge processing method and device, electronic equipment and a storage medium, and the method comprises the steps: segmenting a target image layer by layer, generating a tree diagram of the target image, and determining a tree data structure of the target image, the tree data structure comprising node information of each node in the tree diagram, the node information comprises edge key points of the target; determining a minimum cost path of the edge key points, and obtaining a target key point on the minimum cost path; performing data fusion on the target key points according to the target key points and the node information to generate fusion data of the target key points; and finally, determining an edge contour line of the target according to the fusion data of the target key points. According to the method, data structuring is carried out on the edge pixel points of the image, when the edge contour line of the target is determined according to the fusion data, the category of the recognized target is not required, and the universality and the image edge processing efficiency and accuracy are improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an image edge processing method, device, electronic equipment and storage medium. Background technique [0002] In the process of intelligent human-computer interaction and the research of computer image edge detection, the edge detection of images can effectively distinguish the target from other objects (such as the background). An important basis for image analysis such as region shape extraction. So far, edge detection technology has played an increasingly important role in the fields of scientific research, industrial production, military technology and health, and people have paid more and more attention to the research on edge detection technology. [0003] Because in a digital image, the difference in gray value of each pixel on the edge of the image is relatively small and the change is gentle, and the pixels on the edge of the image and the pixel...

AI Technical Summary

Problems solved by technology

Among them, the sobel operator is not accurate for edge positioning, and can only be applied to edge detection requirements that do not require high precision.

Although the Canny operator has strong anti-interference ability, it is very easy to misidentify noise points as boundaries

The Prewwitt operator is a 3*3 operator template, which uses the gray level difference between the upper and lower pixels and the left and right neighbors to reach the extreme value detection edge at the edge, remove some false edges, and use the average filter to smooth the noise, but for the mixed For images with complex noise, the processing effect is difficult to achieve the desired effect

Moreover, for different recognition requirements, the image edge detection operator needs to define the code business level and set the threshold. For example, the threshold setting for the target is a person, which cannot be applied to identify targets such as fruits or tables and chairs.

[0004] However, in the prior art, since image edge detection operators have their own advantages and disadvantages, the sobel operator can be used for edge detection requirements with low precision requirements, and the Canny operator can be used for detection requirements that require strong anti-interference. The Prewwitt operator can be used for the edge detection requirements of non-mixed and complex noise images. Therefore, in the prior art, the edge detection of image objects usually selects the appropriate detection algorithm from various image edge detection operators according to the scene type and object category. , resulting in poor versatility of the detection operator, and because of the image edge detection operator, when performing target edge detection, it is by performing edge detection on multiple targets in the original image, and then by performing edge detection on the detected edge pixels Carry out clustering instantiation and a noise reduction method suitable for the target to perform subsequent operations on the target edge, resulting in poor noise reduction ability of target edge detection, resulting in low accuracy

Images