An optimization approach of parameters in image processing based on PSO: Case of quality control

Industrial vision is highly related to production problems. Mostly, it deals with problems of quality control or guiding in an automated line of production. Imaging is increasingly used as a tool of control and management. Further, it takes a hand in maintenance and enhances knowledge about the quality of products. Furthermore, it offers the advantage of being able to interfere at several levels. Implementation of a vision system is highly depending on settings of used tools, which is a very crucial point. In this work, we are interested in operators used in image processing. We propose to determine the best values of operator parameters. An optimization approach based on the Particle swarm algorithm (PSO) is used. It is an optimization model where particles (solutions) converge to the best solution for a given problem (here the best parameter values).