A circular workpiece detection method based on artificial fish swarm algorithm

Abstract

The invention discloses an artificial fish swarm algorithm-based circular workpiece detection method, and belongs to the technical field of computer information image processing. The method comprises the following steps of: firstly pre-processing a to-be-detected image to obtain edge information of a circular workpiece; determining a three-dimensional solution space according to the size of a to-be-detected workpiece image and initiating an artificial fish swarm to ensure that each artificial fish is randomly distributed in the solution space; and finally carrying out continuous interaction and coordination behaviors on the artificial fish swarm by adopting a self-adaptive field of view and a step size, so as to carry out heuristic search on a circle passing through most edge points in the solution space to obtain a circle center and a radius of the workpiece. Compared with the traditional method for detecting circles through Hough Transform, the method disclosed by the invention can realize parallel search in a parameter space without traversing the whole space, so that the space overhead and time overhead are greatly decreased and the detection precision is improved; and the method has the characteristics of being rapid, correct and robust.

Description

technical field [0001] The invention relates to the technical field of computer information image processing, and more specifically, relates to a circular workpiece detection method based on an artificial fish swarm algorithm. Background technique [0002] Circular features are one of the basic features in the field of mechanical design and manufacturing. The precise measurement of the geometric dimensions of circular workpieces can not only ensure the processing quality of parts, but also play a vital role in improving production efficiency. Therefore, the detection of circular workpieces has become a basic and important work. Hough transform is one of the basic methods for recognizing geometric shapes from graphics in image processing. Since Hough was proposed in 1962, it has quickly developed into an effective method for detecting graphics such as lines and circles. [0003] The Hough transform has the characteristics of strong robustness and insensitivity to noise, but ...

AI Technical Summary

Problems solved by technology

[0008] In order to overcome the technical deficiencies such as low measurement accuracy and large amount of calculation in the detection of circular workpieces in the prior art, the present invention proposes a circular workpiece detection method based on the artificial fish swarm algorithm; the present invention can be realized in the parameter space Parallel search in the center does not need to traverse the entire space, which greatly reduces the space and time overhead and improves the detection accuracy; for circular workpieces, the detection process is easily affected by the jagged edges and concave edges of the workpiece, causing the detected center to deviate from the target center Problem, when the present invention calculates the fitness of the circle, that is, the number of edge points on the candidate circle, a larger threshold T is adopted through many experiments to make the target circle have more edge points, so that the fitness of the target circle It is greater than the fitness of other candidate circles and has a large difference, and finally achieves the purpose of eliminating the interference of jagged edges and concave edges of workpieces

Images