Optimization of the Process of Parameter Adjustment: Image Processing as a Case Study

Abstract

Selecting optimal parameters' values in a computer vision task is a challenge for users because of the multitude of possible cases. This paper discusses the use of artificial intelligence methods and techniques to optimize the process of finding the best values for parameters in image processing applications. We propose an automatic method based on multi-agent system and reinforcement learning. The proposed solution is proved by an experimentation of object extraction from an image.