本篇論文的研究重點為發展出一套新的運用模糊控制系統在競爭式類神經網路的影像壓縮演算法。
新的競爭式模糊類神經網路演算法當中，主要是採用向量量化為主軸的壓縮方式，再配合競爭式類神經網路來更改其學習率(learning rate)。另外，加入模糊控制系統，利用該系統的平均誤差以及誤差變化率當模糊控制系統的輸入項，搭配模糊控制規則與歸屬函數來調變訓練疊代式之比例函數(scaling function)，作即時訓練碼簿並編碼。不同於傳統的向量量化編碼，此方法將會使訓練碼簿適用於一般各種影像的壓縮性更加提高，同時使得解壓縮後的影像尖峰訊號雜訊比(PSNR)愈佳。在實驗設備上，選擇單色CCD camera與PCI介面的影像擷取卡在個人電腦上進行實驗。若比較傳統的向量量化編碼方式與新的模糊競爭式類神經網路的尖峰訊號雜訊比，經由我們的實驗結果驗證，並以1024 4大小的碼簿為例，顯示新的方法大約提高了10% 的PSNR。

A novel image compression algorithm using fuzzy competitive learning neural network is presented in this thesis.
The proposed image compression scheme is based on vector quantization. Then, competitive learning neural network and fuzzy control system are included in this scheme. It modifies the learning rate and scaling function of updating equation, which is used to train the codebook, with competitive learning neural network and fuzzy control system, respectively. In the proposed scheme, mean-square error and rate of mean-square error are the inputs of the fuzzy control system, using the membership function and control rules to design the codebook instantaneously and encode the source image in the meanwhile. The monochrome-CCD camera and image acquisition board of PCI interference are used to demo the proposed scheme. According to the experimental results, our scheme could greatly improve the quality of codebook. And comparing with conventional vector quantization, taking the 1024 4 codebook size for example, about 10 percentage of PSNR (peak signal-to-noise ratio) is increased in experiments.

[1] Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Transactions on Communications, Vol. 28, No. 1, 1988, pp. 84-95.
[2] N. M. Nasrabadi and R. A. King, “Image coding using vector quantization: a review,” IEEE Transactions on Communications, Vol. 36, No. 8, 1988, pp. 957-971.
[3] C. M. Huang, and R. W. Harris, ”A comparison of several vector quantization codebook generation approaches,” IEEE Transactions on Image Processing, Vol. 2, No. 1, 1993, pp. 108-112.
[4] I. Jee, and R. A. Haddad, “Optimum design of vector-quantized subband codecs,” IEEE Transactions on Signal Processing, Vol. 46, No. 8, 1998, pp. 2239-2243.
[5] M. R. Soleymani, and S. D. Morgera, “An efficient nearest neighbor search method,” IEEE Transactions on Communications, Vol. 35, No. 6, 1987, pp. 677-679.
[6] R. D. Dony, and S. Haykin, “Neural network approaches to image compression,” Proceedings of the IEEE, Vol. 83, No. 2, 1995, pp. 288-302.
[7] J. H. Wang, C. Y. Peng, and J. D. Rau, “Harmonic neural networks for on-line learning vector quantization,” IEE Proceedings, Image Signal Process, Vol. 147, No. 5, 2000, pp. 485-492.
[8] R. Lancini, and S. Tubaro, “Adaptive vector quantization for picture coding using neural networks,” IEEE Transactions on Communications, Vol. 43, No. 234, 1995, pp. 534-544.
[9] A. Namphol, S. Chin, and M. Arozullah, “Image compression with a hierarchical neural network,” IEEE Transactions on Aerospace and Electronic Systems, Vol. 32, No. 1, 1996, pp. 326-337.
[10] S. C. Ahalt, and A. K. Krishnamurthy, “Competitive learning algorithms for vector quantization,” Neural Networks, Vol. 3, No. 3, 1990, pp. 277-290.
[11] D. C. Park, “Centroid neural network for unsupervised competitive learning,” IEEE Transactions on Neural Networks, Vol. 11, No. 2, 2001, pp. 1134-1146.
[12] H. C. Card, G. K. Rosendahl, D. K. McNeill, and R. D. McLeod, “Competitive learning algorithms and neurocomputer architecture,” IEEE Transactions on Computers, Vol. 47, No. 8, 1998, pp. 847-858.
[13] L. Wang, “On competitive learning,” IEEE Transactions on Neural Networks, Vol. 8, No. 5, 1997, pp. 1214-1217.
[14] G. Basil, and J. Jiang., “An improvement on competitive learning neural network by LBG vector quantization,” IEEE International Conference on Multimedia Computing and Systems, Vol. 1, 1999, pp. 244-249.
[15] N. B. Karayiannis, and P. I. Pai, “Fuzzy algorithms for learning vector quantization,” IEEE Transactions on Neural Networks, Vol. 7, No. 5, 1996, pp. 1196-1211.
[16] C. J. Wu, and A. H. Sung, “The application of fuzzy logic to JPEG,” IEEE Transactions on Consumer Electronics, Vol. 40, No. 4, 1994, pp. 976-984.
[17] N. B. Karayiannis, “A methodology for constructing fuzzy algorithms for learning vector quantization,” IEEE Transactions on Neural Networks, Vol. 8, No. 3, 1997, pp. 505-518.
[18] N. B. Karayiannis, and P. I. Pai, “Fuzzy vector quantization algorithms and their application in image compression,” IEEE Transactions on Image Processing, Vol. 4, No. 9, 1995, pp. 1193-1201.
[19] 謬紹綱 編著，數位影像處理活用—Matlab，全華科技圖書，民國八十八年。
[20] 黃國源 編著，類神經網路與圖形識別，維科出版社，民國八十九年。
[21] 張真誠、黃國峰、陳同孝 編著，電子影像技術—Electronic Imaging Techniques，松岡圖書公司，民國八十九年。
[22] 李允中、王小璠、蘇木春 編著，模糊理論及其應用，全華科技圖書，民國九十一年。