應用類神經模糊系統於影像顏色辨識之研究

IMAGE RECOGNITION STUDY VIA THE NEURAL FUZZY SYSTEM

陳志凱(Jr-Kai Chen)

指導教授 ： 吕虹慶

大同大學/電機資訊學院/電機工程學系所/碩士(2005年)

摘要

在這篇論文中，針對足球機器人影像控制處理，我們使用一個全方位的視覺系統提供給足球機器人具有定位的能力。透過影像處理技術定位球形體的位置，再配合類神經模糊系統辨識影像顏色來得知真正球體的所在位置。全景影像是由CCD鏡頭搭配凸鏡裝設而成，以得到環繞機器人360°的場景。而類神經模糊系統為結合類神經網路以及模糊邏輯理論的架構，其中包括輸入層、輸入歸屬函數層、模糊規則層、輸出歸屬函數層及輸出層等五層架構。從實驗的結果能說明所提出的類神經模糊系統能有效的應用於影像的顏色辨識和球的定位。

關鍵字

影像辨識

並列摘要

In this thesis, an omnidirectional vision system is utilized to provide the soccer robot with a locating capability for dealing with the image process control. By means of the digital image processing techniques and the neural fuzzy system, the ball-shapes and the image color could be located and recognized. In order to obtain the scene that surrounds robot , the panoramic image is installed by matching the convex mirror and CCD lens. The neural fuzzy system that combines both the neural network and fuzzy logic technique is a five-layer network configuration, which includes the input layer, the layer of input membership functions, the layer of fuzzy rules, the layer of output membership functions, and the output layer. The experimental results are given to illustrate the effectiveness of the neural fuzzy system on ball locating and image color recognition.

並列關鍵字

IMAGE RECOGNITION

參考文獻

[1] L. A. Zadeh, “Fuzzy set,” Inform. Contr., Vol. 8, pp. 338-353, 1965.

[2] L. Peng and P. Y. Woo, “Neural-fuzzy control system for robotic manipulators,” IEEE Contr. Syst. Mag., Vol. 22, No. 1, pp. 53-63, Feb. 2002.

[3] J. S. Jang and C. T. Sun, “Neuro-fuzzy modeling and control,” Proc. of the IEEE, Vol. 83, No. 3, Mar. 1995, pp. 378-406.

[4] C. T. Lin and C. S. G. Lee, “Neural-network-based fuzzy logic control and decision system” IEEE Trans. Computers, Vol. 40, No. 12, pp. 1320-1336, Dec. 1991.

[5] H. C. Chang and M. H. Wang, “Neural network-based self-organizing fuzzy controllers for transient stability of multimachine power systems,” IEEE Trans. Energy Conversion, Vol. 10, No. 2, pp. 339-347, June 1995.