An image segmentation approach based on fuzzy-neural-network hybrid system
Tóm tắt
This paper presents a new solution to the image segmentation problem, which is based on fuzzy-neural-network hybrid system (FNNHS). This approach can use the experiential knowledge and the ability of neural networks which learn knowledge from the examples, to obtain the well performed fuzzy rules. Furthermore this fuzzy inference system is completed by neural network structure which can work in parallel. The segmentation process consists of pre-segmentation based on region growing algorithm and region merging based on FNNHS. The experimental results on the complicated image manifest the utility of this method.
Tài liệu tham khảo
A. H. Nazif, M. D. Levine, Low level image segmentation: An expert system. IEEE Trans. on PAMI, 6(1984)1, 555–577.
L. A. Zadeh, Fuzzy logic, neural networks and soft computing. Communication of the ACM, 37(1994)3, 77–84.
Xie Wei-xin, Qian Yun-tao, Fuzzy-neural-network hybrid systems and their applications. Chinese Journal of Electronics, 4(1995)4, 78–85.
C. T. Lin, and C. S. G. Lee, Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems. IEEE Trans. on Fuzzy Systems, FS-2(1994)1, 46–63.
T. Pavlidis, Algorithms for Graphics and Image Processing, Computer Science Press Inc., 1982.
M. Sugeno, M. Nishida, Fuzzy control of model car. Fuzzy Sets Systems, 16(1985)1, 103–113.
Qian Yun-tao, Zheng Nan-ning, An approach to image segmentation with neural nets and fuzzy logic. ISITA’90, Hawaii, USA: Nov.27–30, 1990, 723–726.
D. E. Rumelhart, G. E. Hinton et al., Parallel Distributed Processing, Vol.1, Cambridge: MIT Press, 1986, 318–362.