Image edge detection method based on plant community behaviors

Abstract

An image edge detection method based on plant community behaviors optimizes an edge detection image by simulating behaviors of sowing, growth, flowering and results of a plant community, and comprises the following steps: step 1, initializing an image to be detected by the plant community; step 2, performing sowing operation on the plant community in the to-be-detected image, and calculating an edge detection effect evaluation function of a plant individual; step 3, carrying out growth operation on the plant community in the to-be-detected image and carrying out random search on the edge of the image; 4, performing flowering operation on the plant community in the to-be-detected image, and randomly selecting edge detection images of neighbor plant individuals for combination; 5, performing result operation on the plant community in the to-be-detected image and mutually learning edge detection image information; and step 6, outputting an optimal edge detection image by the plant community and ending the algorithm. The algorithm is high in efficiency, high in image edge detection precision and good in expansibility.

Description

technical field [0001] The invention belongs to the field of computer images and artificial intelligence, in particular to an image edge detection method based on plant community behavior. Background technique [0002] Edge detection is an important image processing technology. Image edge detection refers to finding the place where the grayscale change rate is the largest in the image. The position of the grayscale sudden change is the image edge, which usually means the semantic change of the object in the image. Image edge features can describe the underlying features of different semantic changes in the image and discard redundant details, thereby greatly simplifying the image. Edge detection is a key step in image information extraction, and is often used as an auxiliary method for image preprocessing or instructing image detection. At present, image edge detection technology is widely used in various industries, agriculture, production, life, and service industries, i...

AI Technical Summary

Problems solved by technology

[0011] 2. Algorithm efficiency is low

Artificial intelligence algorithms often need to design loop nesting in the design process, and multiple loop nesting will lead to poor time performance and space performance of the algorithm

If the parameter design is not good, it is easy to affect the efficiency of the detection algorithm

In addition, the image edge detection method generally uses the gray gradient feature as the basis for identifying the edge, pays attention to the step change of the image gray level, generally does not consider the image brightness, texture, color and other characteristics, and will also lose some useful information in the image, reducing the Algorithm Computational Efficiency

[0012] 3. Low anti-interference ability

The traditional edge detection algorithm is based on gradient edge detection operators, and its templates are relatively simple. Although it is easy to operate, it is susceptible to noise interference, and the obtained edges are thicker, and traditional operators are sensitive to noise.

The Laplacian operator is more sensitive to noise interference, and even amplifies the adverse effects of noise on the image, and in many cases cannot be directly used for image edge detection

[0013] 4. Poor scalability

However, the Canny operator uses the first differential of the Gaussian function as the convolution kernel, which greatly improves the computational complexity of the algorithm. With the increase of the image size, the computational complexity increases sharply, and the edge type cannot be determined.

Images