Biological lateral inhibition and Electimize approach to template matching

Abstract Template matching is an important topic in the field of image processing and it is widely used in image fusion and image registration. In this paper, a hybrid biological method of Electimize and lateral inhibition (LI) is proposed to complete the task of template matching. The proposed biological image processing technique is named LI-Electimize. Electimize is an innovative multi-level evolutionary algorithm that mimics the phenomenon of flow of electrons and the electric current and has been successfully used to solve NP-hard optimization problems, such as cash flow optimization problem. Electimize demonstrates higher capabilities in searching the solution space extensively and identifying global optimal alternatives. Furthermore, lateral inhibition mechanism, which is verified to have good effects on image edge extraction and image enhancement, is employed for image pre-processing. In this work, the proposed biological LI-Electimize incorporates both advantages of Electimize and lateral inhibition which could make better performance. The detailed process of biological LI-Electimize is also given. Series of comparative experimental results of particle swarm optimization (PSO), PSO based on lateral inhibition (LIPSO), Electimize and LI-Electimize demonstrate the better feasibility and effectiveness of the proposed LI-Electimize in solving the template matching problems.