Hybrid bio-inspired lateral inhibition and Imperialist Competitive Algorithm for complicated image matching |
| |
Authors: | Linzhi Huang Haibin Duan Yin Wang |
| |
Institution: | 1. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, PR China;2. College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, PR China |
| |
Abstract: | Bio-inspired intelligent algorithms, such as Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO), have been applied to solve image matching problems. However, due to high computational complexity and premature convergence problems associated with these methods, they have limitations in defining the global optimal matcher efficiently and accurately. To address these problems, we proposed a hybrid bio-inspired optimization approach, coupling the lateral inhibition mechanism and Imperialist Competitive Algorithm (ICA), to solve complicated image matching problems. With the adoption of the lateral inhibition mechanism, the global convergence of conventional ICA algorithms has been greatly improved. We demonstrate the efficiency and feasibility of the proposed approach by extensive comparative experiments. |
| |
Keywords: | Imperialist Competitive Algorithm (ICA) Lateral inhibition Image matching |
本文献已被 ScienceDirect 等数据库收录! |
|