Intelligent image edge detection method based on artificial Slime Mould colony

Abstract

The invention discloses an intelligent image edge detection method based on an artificial Slime Mould colony. The method comprises the following steps: step 1, initializing an image edge detection model; step 2, detecting the edge of the image according to the labor division of the Slime Mould colony; step 3, carrying out cross learning on the edge of the image by the Slime Mould colony; and step 4, outputting an image edge detection result by the Slime Mould colony. According to the method, an image edge detection problem is described as a Slime Mould colony foraging problem under the condition of multiple food source nodes, a point with a relatively large gray gradient in an image is taken as a food source, and the Slime Mould colony continuously updates image edge point or food source information searched by the Slime Mould colony through division detection in the step 2 and cross learning in the step 3, finally, all the Slime Moulds are concentrated on the real image edge points, and all image edge curves of the Slime Mould colony are output. According to the method, the image edge detection problem is solved by simulating the foraging behavior of Slime Moulds, so that the accuracy and efficiency of image edge detection are improved.

Description

technical field [0001] The invention belongs to the technical field of computers, in particular to an image edge detection method based on slime mold swarm intelligence. Background technique [0002] In the past twenty years, scholars at home and abroad have proposed hundreds of image edge detection algorithms, and among these algorithms, the threshold technique is one of the most popular techniques. In the classic threshold edge detection algorithm, an image is usually segmented into object and background according to the selected threshold. However, when the image structure is complex and the gray distribution is wide, the threshold segmentation effect is not ideal. The edge detection technology based on threshold segmentation uses an optimization algorithm to obtain the optimal threshold before edge detection. For example, although the Otsu algorithm can obtain better detection results, the algorithm cannot reflect the spatial correlation information between image pixels...

AI Technical Summary

Problems solved by technology

Third, the accuracy of solving problems by cultivating slime mold is not high enough. Basically, petri dishes are used as maps and oatmeal particles are used as nodes. The space of the petri dish is limited and the oatmeal is large in size, coupled with the influence of the culture medium, it is obvious that Limits the accuracy of the solution

Fourth, cultivating slime molds also needs to occupy valuable space, time and manpower, supporting complex environmental regulation equipment, nutrition and water supply, growth environment control before the experiment, experimental design, data processing and post-experiment cleanup all require cost and professional operation

[0006] But so far, a slime mold image edge detection method based on slime mold swarm intelligence has not been found in the market and various literatures.

Images