Image Compression by Self-Organized Kohonen Map 邱俊德、劉仁俊
E-mail: [email protected]
ABSTRACT
Image compression is an essential task for image storage and transmission applications. Vector quantization is often used when high compression rates are needed. Self-Organizing Map(SOM) algorithm can be used to generate codebooks for vector quantization.
This thesis presents a compression scheme for digital still images using the SOM algorithm. The processes will not only have the advantages of vector quantization, but also preserve its topological property that generate ordered codebook with substantial
dimension reduction which makes image compression more effective. The method of Discrete Cosine Transform（DCT） is chosen to be the preprocessing scheme in order to identify the image frequency information . And we also used the sub-band scheme to separate the DC and AC coefficients, so as to reduce the neural network learning complexity. Our results show that in this compression scheme, we can earn 33?36dB coding gain in PSNR（peak signal-noise-ratio）with DCT and sub-band preprocess.
Otherwise, the size of codebook is the deterministic factor of compression ratio, and we can only use 6?8 bits to implement the other VQ-based scheme using 7?9 bits.
Keywords : Discrete Cosine Transform ; Vector Quantization ; Self-Organizing Feature Maps ; Codebook Table of Contents
目錄 封面內頁 簽名頁 授權書……….iii 簽署人須知………
……….iv 中文摘要………...………v 英文摘要………
……….vi 誌謝………....vii 目錄………
………viii 圖目錄………...….xi 表目錄…
………...xiii 第一章 緒論………...1 1.1 研究背景………..1 1.2 研究目的………..2 1.3 內容大 綱………..3 第二章 影像轉換編碼………...5 2.1 前言…
………….……….5 2.2 離散傅利葉轉換…….……….6 2.3 離散餘弦轉換
……….……….………7 2.4 低通濾波……….……….…………9 第三章 向量量化...………
………..15 3.1 前言…...……….…….………..15 3.2 純量量化……….…….
………...15 3.3 向量量化……….………16 3.4 編碼簿的產生……….…
………19 3.5 不同類型的向量量化方式………..21 3.6 向量量化的瓶頸………….…………
………23 第四章 自組織映射類神經網路.………25 4.1 前言………
………...25 4.2 SOM類神經網路的基本架構……….……….28 4.2.1 輸入層與輸出層………
….28 4.2.2 網路拓樸與鄰近區域………30 4.3 訓練與分類……….………...32 4.3.1 SOM類神經網路演算法則………..…….32 4.3.2 鄰近函數……….……33 4.3.3 學習 速率………34 4.4 結語………...……….35 第五章 類神經網路 之影像壓縮….………37 5.1 前言……….37 5.2 影像特徵擷取與壓 縮流程…….……….……...37 5.3 分頻編碼……….………...39 5.4 DCT、分頻編碼與SOM的 壓縮流程…..………41 第六章 模擬測試結果與分析……….45 6.1 失真壓縮系統的評估方式……
……….45 6.2 影像特徵擷取……….………...46 6.3 不同類型向量量化方式的效能比較.…
……….……..51 6.4 DCT結合SOM架構下的效能………..………52 6.5 分頻編碼與SOM架構下的模擬結果…………
……53 6.6 子影像大小選擇……….62 第七章 結論與展望………
…….67 7.1 結論……….67 7.2 未來展望……….68 參考文獻……….70
REFERENCES
[1] A. K. Jain, Fundamental of Digital Image Processing, Prestice-Hall, Englewood Cliffs, NJ, 1989.
[2] W. K. Pratt, Digital Image Processing, Wiley-Interscience, New York, 1978.
[3] Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, 1992.
[4] N. S. Jayant and P. Noll, Digital Coding of Waveforms Principles And Applications to Speech And Video, Englewood Cliffs, NJ, Prentice-Hall, 1984.
[5] J. Freeman and D. Skapura, Neural Networks, Algorithms, Applications, and Programming Techniques, Addison Wesley, 1993.
[6] R. M. Gray, "Vector Quantization," IEEE Acoust., Speech, Signal Processing Magazine., pp. 9-31, Apr. 1984.
[7] N. Ahamed, E. Oja, O. and K. R. Rao, "Discrete Cosine Transform," IEEE Trans. Comput., vol. C-23, pp. 90-93, Jan. 1974.
[8] K. R Rao, P. Yip, Discrete Cosine Transform - Algorithms, Advantages, Applications, Academic Press, 1990.
[9] B. Porat, A Course in Digital Signal Processing, John Wiley & Sons, 1997.
[10] R. C. Reininger and J. D. Gibson, "Distributions of The Two-Dimensional DCT Coefficients of Images," IEEE Trans. on Communication, vol. COM-31, pp. 835-839, June 1983.
[11] A. Palau and G. Mirchandani, "Image Coding with Discrete Cosine Transforms Using Efficient Energy-Based Adaptive Zonal Filtering,"
Acoustics, Speech, and Signal Processing, ICASSP-94., IEEE International Conference on Volume: v , vol.5 pp. V/337 -V/340, 1994 [12] G. K.
Wallace, "The JPEG Still Picture Compression Standard," IEEE Trans. on Consumer Electronics, vol. 38, no. 1, Feb. 1992.
[13] N. M. Nasrabadi and R. A. King, "Image Coding Using Vector Quantization: a Review," IEEE Trans. on Communication, vol. 36, no. 8, pp.
957-971, Aug. 1988.
[14] A. Gersho and R. M. Gray, Vector Quantization and Signal Compression, London:Kluwer, 1992.
[15] A. Buzo, A. H. Gray, and J. D. Karkel, "Speech Coding Based upon Vector Quantization," IEEE Trans. Acoust. Speech, Signal Processing, vol. ASSP-28, pp. 562-574, October 1980.
[16] A. Gersho, "On the Structure of Vector Quantizers," IEEE Trans. on Inform. Theory, vol. 28, no. 2, pp. 157-162, Mar. 1982.
[17] Y. Linde, A. Buzo and R. M. Gray, "An Algorithm for Vector Quantizer Design," IEEE Trans. on Communication, vol. COM-28, no. 1, pp.
84-95, Jan. 1980.
[18] Kwok-Tung Loand Wai-Kuen Cham, "New Classified Vector Quantization of Images," Computer, Communication, Control and Power Engineering. Proceedings. TENCON ''93.,IEEE Region 10 Conference on, vol. 3, pp. 373-376, 1993.
[19] D.-S. Kim, and S.-U. Lee, "Image Vector Quantizer Based on a Classification in the DCT Domain," IEEE, Trans. on Communication, vol.
39, no. 4, Apr 1991.
[20] Yong Ho Shin and Cheng-Chang Lu, "Image Compression Using Vector Quantization and Artificial Neural Networks," Systems, Man, and Cybernetics, 1991. Decision Aiding for Complex Systems, Conference Proceedings., IEEE International Conference on , vol. 3, pp. 1487-1491, 1991.
[21] Yong Ho Shin and Cheng-Chang Lu, "A Neural Network Based Image Compression System," IEEE Trans. on Consumer Electronics, vol. 38, no. 1, Feb. 1992.
[22] Nasser M. Nasrabadi, Chang Y. Choo and Yushu Feng, "Dynamic Finite-State Vector Quantization of Digital Images," IEEE Trans. on Communication, vol. 42, no. 5, May 1994.
[23] L. Torres and J. Huguet, "An Improvement on Codebook Search for Vector Quantization," IEEE Trans. on Communication, vol. 42, no.
2/3/4, Feb. 1994.
[24] F. G. B. De Natale, S. Fioravanti and D. D. Giusto, "DCRVQ:A New Strategy for Efficient Entropy Coding of Vector-Quantized Images,"
IEEE Trans. on Communication, vol. 44, no. 6, May 1996.
[25] D. E. Rumelhart, G. E. Hinton and R. J. Williams, "Learning Internal Representation by Error Propagation," in D. E. Rumelhart and J. L.
McClelland, Parallel Distributed Processing, vol. I, Cambridge, Massachusetts: The MIT Press, 1986.
[26] R. P. Lippmann, "An Introduction to Computing with Neual Nets," IEEE ASSP Magazine, pp. 4-22, Apr. 1987.
[27] L. Zhang, B. Zhang and G. Chen, "Generating and Coding of Fractal Graphs by Neural Network and Mathematical Morphology Methods,"
IEEE Trans. on Neural Networks, vol. 7, no. 2, pp. 400-407, March 1996.
[28] C.-C. Lee and J. P. de Gyvez, "Color Image Processing in a Cellular Neural-Network Environment," IEEE Trans. on Neural Networks, vol. 7, no. 5, pp. 1086-1098, Sep. 1996.
[29] T. Kohonen, "The Self-Organizing Map," Proceedings of the IEEE, vol. 78, no. 9, pp. 1464-1480, Sep. 1990.
[30] T. Kohonen, Self-Organizing Maps, Springer, Berlin, Heidelberg, 1995.
[31] R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, N.Y.:Wiley, 1973.
[32] C. W. Therrien, Decision Estimation and Classification. An Introduction to Pattern Recognition and Related Topics, John Wiley and Sons, Inc, 1989.
[33] E.B. Kosmatopoulos, M.M. Polycarpou, M.A. Christodoulou and P.A. Ioannou, "High-Order Neural Network Structures for Identification of Dynamical Systems," IEEE Trans. on Neural Networks, vol. 6, no. 2, pp. 422-431, March 1995.
[34] J. A. Corral, M. Guerrero and P. J. Zufiria, "Image Compression via Optimal Vector Quantization: a comparison Between SOM, LBG and K-means Algorithms," Neural Networks, 1994. IEEE World Congress on Computational Intelligence., IEEE International Conference on, vol. 6, pp. 4113-4118, 1994.
[35] J. Kangas and T. Kohonen, "Developments and Applications of the Self-Organizing Map and Related Algorithms," Mathematics and Computers in Simulation, 41(5-6):3-12, July 1996.
[36] J. Kangas, "Sample Weighting When Training Self-Organizing Maps for Image Compression," Neural Networks for Signal Processing V, Proceedings of the 1995 IEEE Workshop, pp. 343-350, 1995.
[37] O. T.-C. Chen, B. J. Sheu, and W.-C. Fang, "Image Compression Using Self-Organization Networks," IEEE Trans. Circuits Syst. Video Technol., vol. 4, pp. 480-489, Oct. 1994.
[38] E. A. Riskin, L. E. Atlas, and S. R. Lay, "Ordered Neural Maps and Their Applications to Data Compression," in Neural Network for Signal Processing, IEEE Wkshp., pp. 543-551. 1991.
[39] S. Carrato, G. L. Sicuranza, and L. Manzo, "Application of Ordered Codebooks to Image Coding," in Neural Network for Signal Processing, IEEE Wkshp., pp. 291-300. 1993.
[40] G. Burel and J.-Y. Catros, "Image Compression Using Topological Maps and MLP," in Proc. ICNN''93, Int. Conf. On Neural Networks, vol.
2, pp. 727-731, IEEE Service Center, Piscataway, NJ, 1993.
