Fuzzy image fusion based on modified Self-Generating Neural Network |
| |
| Authors: | Hong Jiang Yufen Tian |
| |
| Affiliation: | 1. School of Computer Science & Engineering, Xi’an University of Technology, Xi’an 710048, China;2. Shaanxi Key Laboratory for Network Computing and Security Technology, Xi’an 710048, China;1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;2. School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China;1. School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072, China;2. School of Computing, Informatics, Decision Systems Engineering, Arizona State University, USA;1. College of Automation, Chongqing University, Chongqing City 400030, China;2. Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing 400030, China;3. College of Computer Science, Chongqing University, Chongqing 400030, China;4. State Key Laboratory of Power Transmission Equipment and System Security and New Technology, College of Automation, Chongqing University, 400030, China;1. School of Software, Yunnan University, Kunming 650091, Yunnan, China;2. School of Electrical Engineering and Intelligentization, Dongguan University of Technology, Dongguan 523000, China;3. Institute of Technology Management, National Chiao Tung University, Hsinchu 30010, China;4. School of Cyber Science and Engineering, Wuhan University, Wuhan 430000, China |
| |
| Abstract: | A new fusion algorithm for multi-sensor images based on Self-Generating Neural Network (SGNN) and fuzzy logic is proposed in this paper. This study is an extension of the work described in Qin and Bao (2005). First, the order and frequency modifications for the current McKusick and Langley (M–L) optimization are proposed; next, by combining optimization and pruning together, the Pruning-And-One-Optimization-Composite (PAOOC) processing method is raised; and finally, a modified fuzzy fusion scheme using improved SGNN is put forward. Experimental results demonstrate that the posed fuzzy fusion scheme outperforms region-based fusion using wavelet multi-resolution (MR) segmentation, and region-based fusion using tree-structure wavelet MR segmentation, both in visual effect and objective evaluation criteria. In the meantime, simulations also show the effectiveness of our modifications for the current optimization and pruning methods, visually and objectively. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
