UDC 004.932.4:004.421
APPLICATION OF GENETIC ALGORITHMS FOR THE FORMATION OF ALGORITHM CHAINS FOR IMAGE IMPROVING
V. V. Belov, Dr. Sc. (Tech.), full professor, RSREU, Ryazan; This email address is being protected from spambots. You need JavaScript enabled to view it.
A. K. Lopatin, post-graduate student, SUHSS, Kolomna; This email address is being protected from spambots. You need JavaScript enabled to view it.
The task of forming gradient images of products located on a conveyor belt in the process of implementing automatic verification of their geometric dimensions is considered. The aim of the work is to develop a method for automatic synthesis of an algorithm for obtaining high-quality gradient images. The algorithm is synthesized as the chain of necessary procedures (operators) used in practice of solving image processing problems. Structural and parametric identification of the synthesized chain is carried out automatically using a modified genetic algorithm. Input parameters of the synthesized chain are: the image of inspected product in RGB format and binary image-standard. The synthesized chain adapts to shooting conditions (camera type, its resolution, surface illumination), the image formed by it is intended for the subsequent selection
of product edges in order to evaluate its geometric parameters. In the process of chain synthesis, the vector of its operators and their parameters is formed
Key words: genetic algorithms, image processing, algorithms compositions, set of algorithms, image filtering, edge detecting.