基于模糊--神經(jīng)網(wǎng)絡(luò)混合系統(tǒng)的圖象分割方法
AN IMAGE SEGMENTATION APPROACH BASED ON FUZZY-NEURAL-NETWORK HYBRID SYSTEM
-
摘要: 本文提出了一種基于模糊-神經(jīng)網(wǎng)絡(luò)混合系統(tǒng)(FNNHS)的圖象分割方法。它可以利用人的經(jīng)驗(yàn)知識(shí)和神經(jīng)網(wǎng)絡(luò)從樣本數(shù)據(jù)中學(xué)習(xí)知識(shí)的能力,得到性能良好的模糊規(guī)則,并且可以通過(guò)神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)實(shí)現(xiàn)模糊推理。分割過(guò)程由基于區(qū)域生長(zhǎng)的預(yù)分割和基于FNNHS的區(qū)域合并兩步構(gòu)成。實(shí)驗(yàn)表明,該方法用于復(fù)雜圖象分割具有很好的效果。Abstract: This paper presents an image segmentation approach which is based on fuzzy-neural-network hybrid system(FNNHS). This approach can use the empirical 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. The segmentation process consists of pre-segmentation based on region growing algorithm and region merging based on FNNHS. The experiments illustrate the power and efficiency of this method used for complicated image.
-
Nazif A H, Levine M D. Low level image segmentation: An expert system. IEEE Trans. on PAMI,[2]84, PAMI-6(1): 555-577.[3]Zadeh L A,Fuzzy Logic. Neural networks and soft computing[J].Communication of the ACM.1994,37(3):77-84[4]田村秀行等著,赫榮威譯.計(jì)算機(jī)圖象處理技術(shù).北京:北京師范大學(xué)出版社,1988,111-115.[5]Sugeno M, Nishida M. Fizzy control of model car[J].Fizzy Sets Systems.1985, 16(1):103-113[6]Qian Yun-tao, Zheng Nan-ning. An approach to image segmentation with neural nets and fuzzy[7]logic. ISITA90, Hawaii, USA: Nov. 27-30, 1990, 723-726.[8]Rumelhate D E, Hinton G E, et al. Parallel distributed processing Vol 1, Cambridge: MIT Press, 1986, 318-362. -
計(jì)量
- 文章訪問(wèn)數(shù): 2327
- HTML全文瀏覽量: 131
- PDF下載量: 400
- 被引次數(shù): 0
下載:
