影像壓縮(image compression)為了通訊或儲存目的，位元率(bit rate)降低後，影像仍需保持令人滿意的保真度(fidelity)或品質。向量量化(vector quantization)技術為一受歡迎之影像壓縮方法，其目的(goal)在於建立一編碼簿(codebook)使得介於訓練向量(training vectors)與編碼簿中之編碼向量(codevector)的平均誤差最小。神經網路(neural network)由於他們大量地平行( parallel)以及分散式的(distributed)結構非常適合用於影像壓縮問題上。亦即神經網路高度地平行結構，提供了神經網路向量量化即時(real-time)性的可能。
　　本篇論文主要描述兩類具有灰關聯(grey relation)及乏晰群集(fuzzy clustering)策略之非監督式(un-supervised)向量量化神經網路。這些新的訓練演算法一個強有力(powerful)的特點是量化編碼字(codeword)被適應性(adaptive)的決定，不像廣受喜愛的LBG訓練演算法需用整批模式(batch mode)來處理全部的訓練資料。首先本論文提出植基於灰關聯(grey-based)之神經網路，其中灰色理論(grey theory)被應用於兩維的競爭(competitive)霍普菲爾(Hopfield)神經網路(取名為GHNN)及兩層競爭學習(learning)網路(取名為GCLN)以產生向量量化之最佳解(optimal solution)。依照訓練向量與碼向量間之相似性，灰關聯分析被用來測量其間之關聯程度。
　　其次，本文提出了乏晰(fuzzy)神經網路結構，其編碼簿設計概念上被視為群集問題。在這點上，它是一種神經網路模型加上乏晰群集策略，使在相同類別(class)間任意兩個訓練向量其平均失真測量所定義之目標函數(objective function)為最小。為了產生可行的(feasible)結果，我們組合了神經網路，乏晰群集技術以及具懲罰項(Penalized term)之乏晰群集方法來完成(取名為FCLN及PFHNN)。
　　然而這GCLN、GHNN、FCLN以及PFHNN演算法並不保證達到整體最佳值(global optimum)，而可能收斂到區域最佳值(local optimum)。因此，本論文繼續使用遺傳基因演算法(genetic algorithm)嘗試以獲致向量量化器(vector quantizer)設計的最佳目標函數。其中按自然法則的競爭(competition)、選擇(selection)以及再生(reproduction)操作來結合GCCN及PFHNN去產生一較好的遺傳灰關聯競爭學習網路(GGCLN)，以及遺傳乏晰霍普菲爾神經網路(GFHNN)以達成向量量化影像壓縮之最佳(optimal)編碼簿設計。由模擬結果(simulation results)證明了建構遺傳基因演算法、灰關聯以及乏晰群集技術於神經網路，提供了向量量化影像壓縮技術中搜尋全域最佳(globally optimal)或幾近最佳(near-optimum)編碼簿的方法。
　　彩色影像(color image)廣泛地使用於我們的日常生活中，彩色影像壓縮和密碼系統(cryptosystem)於網際網路多媒體應用中也是密不可分的。本論文最後提出一種結合混合型密碼系統(hybrid cryptosystem)及彩色影像壓縮使用具懲罰項乏晰神經網路技術之虛擬(virtual)彩色影像系統架構。其目的在提供網路上一種安全彩色影像資訊交換的工具。在架構上，首先利用本論文提出的具有懲罰項之彩色向量量化神經網路(稱為SPFNN)將彩色祕密影像(color stego-image)轉換成位元資料流，然後將其嵌入(embedded)至掩飾彩色影像(cover color image)的Hadamard轉換係數中。在彩色秘密位元嵌入的過程中，Data Encryption Standard (DES) 和Rivest、shamir and Adleman (RSA)加密解密的機制用來達成在網際網路上的秘密通信。我們的系統架構擁有兩項優點，一是由結合DES和RSA技術的使用使得在網際網路上送收彩色影像資訊既方便又安全。另一是優良的藏密(steganography)結果可以經由我們提出的向量量化神經網路壓縮方法來獲得。

　　A fundamental goal of image compression is to reduce the bit rate for transmission or data storage while maintaining an acceptable fidelity or image quality. Vector Quantization (VQ) is a popular method for image compression. The purpose of vector quantization is to create a codebook such that the average distortion between training vectors and their corresponding codevectors in the codebook is minimized. Neural networks are well suited to the problem of image compression due to their massively parallel and distributed architecture. The use of neural networks for vector quantization has a significant advantage, that is neural networks are highly parallel computing architecture and, thus, offer the potential for real-time VQ.
　　This dissertation describes the use of neural networks for vector quantization (VQ), two un-supervised neural network with grey relation and fuzzy clustering schemes for training the vector quantizer. A powerful feature of these new training algorithms is that the VQ codewords are determined in an adaptive manner, as compared to the popular LBG training algorithm, which requires that the entire training data be processed in a batch mode. In the first proposed grey-based neural network schemes, the grey theory is applied to a 2-D competitive Hopfield neural network (named GHNN) and two layer competitive learning network (named GCLN) in order to generate optimal solution for VQ. In accordance with the degree of similarity measure between training vectors and codevectors, the grey relational analysis is used to measure the relationship degree among them.
　　In most cases, unsupervised training algorithms attempt to “cluster” or average portions of the training data into representative groups. In the second proposed fuzzy neural network schemes, the codebook design is conceptually considered as a clustering problem. Here, it is a kind of neural network model imposed by the fuzzy clustering strategy working toward minimizing an objective function defined as the average distortion measure between any two training vectors within the same class. In order to generate feasible results, its implementation consists of neural networks and fuzzy clustering with penalty term methods (named FCLN and PFHNN).
　　While the GCLN, GHNN, FCLN and PFHNN algorithms converge to a local optimum, it is not guaranteed to reach the global optimum. The Genetic Algorithm (GA) is used in an attempt to optimize a specified objective function related to vector quantizer design. The physical processes of competition, selection and reproduction operating in populations are adopted in combination with GCLN and PFHNN and to produce a superior Genetic Grey-based Competitive Learning Network (GGCLN) and Genetic Fuzzy Hopfield Neural Network with penalty term (GFHNN) for codebook design in image compression. Simulation results illustrate that embedding GA, grey relation and fuzzy clustering techniques into neural networks provides an approach for search of globally optimal or near-optimum codebook to image compression.
　　Color images are widely used in our daily lives, and color image compression and cryptosystem are closed related for secure internet multimedia application. In this dissertation an invisible virtual color image system based on Interpolative Vector Quantization (IVQ) using a spread neural network with Penalized Fuzzy C-Means (PFCM) clustering technology (named SPFNN) is proposed. The goal is to offer safe exchange of a color stego-image in the internet. In the proposed scheme, is first compressed the secret color image by a spread-unsupervised neural network with PFCM based on IVQ, then the block cipher Data Encryption Standard (DES) and the Rivest, Shamir and Adleman (RSA) algorithms are hired to provide the mechanism of a hybrid cryptosystem for secure communication and convenient environment in the internet. In the SPFNN, the PFHNN algorithm is modified into spread neural network in order to generate optimal solution for color IVQ. Then we encrypted color IVQ indices and sorted codebooks of secret color image information and embedded into the frequency domain of the cover color image by Hadamard Transform (HT). Our proposed method has two benefits. One is the highly secure and convenience offered by the hybrid DES and RSA cryptosystems to exchange color image data in the internet. The other benefit is the excellent results can be obtained using our proposed color image compression scheme SPFNN method.

References

[1] N. M. Nasrabadi and R. A. King, “ Image Coding Using Vector Quantization: A
Review,” IEEE Trans. Commun., vol. 36, no. 8, pp. 957-971, 1988.
[2] F. Madeiro, R. M. Vilar, and B. G. Aguiar Neto, “A Self-Organizing Algorithm
for Image Compression,” Brazilian Symposium on Neural Networks, pp. 146-150,
1998.
[3] S. C. Tai, C. C. Lai, and Y. C. Lin, “Two Fast Nearest Neighbor Searching
Algorithms for Image Vector Quantization,” IEEE Transactions on
Communications, vol. 44, no. 12, pp. 1623-1628, 1996.
[4] M. Lightstone and S. K. Mitra, “Image-Adaptive Vector Quantization in an
Entropy-Constrained Framework,” IEEE Transactions on Image Procession, vol.
6, no. 3, pp. 441-450, 1997.
[5] Y. Linde, A. Buzo, and R. M. Gray, “An Algorithm for Vector Quantizer
Design,” IEEE Trans. Commun., vol. COM-28, pp. 85-94, Jan., 1980.
[6] A. Gersho, and R. M. Gray, “Vector Quantization and Signal Compression,”
Kluwer Academic Publishers, Norwell, Ma, 1992.
[7] E. A. Riskin, T. Lookabaugh, P. A. Chou, and R. M. Gray, “Variable Rate
Vector Quantization for Medical Image Compression,” IEEE Trans. Med.
Imaging, vol. 9, pp. 290-298, 1990.
[8] E. Yair, K. Zeger, and A. Gersho, “Competitive Learning and Soft Competiton
for Vector Quantizer Design,” IEEE Trans. Signal Processing, vol. 40, pp.
294-309, 1992.
[9] K. Zeger, J. Vaisey, and A. Gersho, “Globally Optimal Vector Quantizer
Design by Stochastic Relaxation,” IEEE Trans. Signal Processing, vol. 40,
pp. 310-322, 1992.
[10] L. L. H. Andrew, and M. Palaniswami, “A Unified Approach to Selecting
Optimal Step Lengths for Adaptive Vector Quantizers,” IEEE Trans. Commun.,
vol. 44, pp. 434-439, 1996.
[11] T. Denk, K. Parhi, V. Cherkassky, “Combining Neural Networks and the
Wavelet Transform for Image Compression,” IEEE Proceedings of ASSP, vol. 1,
pp. 637-640, 1993.
[12] J. Jiang, “Neural Network Technology for Image Compression,” International
Conference on Broadcasting Convertion, no. 413, pp. 250-257, 1995.
[13] K. H. Wu, C. H. Chen, and J. D. Lee, “A Fuzzy Potential Approach with the
Cache Genetic Learning Algorithm for Robot Path Planning,” IEEE
International Conference on Systems, Man and Cybernetics, vol. 1, 22-25, pp.
478-482, 1995.
[14] J. S. Lin, K. S. Cheng, and C. W. Mao, “Segmentation of Multispectral
Magnetic Resonance Image Using Penalized Fuzzy Competitive Learning
Network,” Computers and Biomedical Research 29, 314-326, 1996.
[15] W. J. Hwang, M. R. Leou, B. Y. Ye, and S. C. Liao, “Entropy-Constrained
Vector Quantizer Design Algorithm Using Competitive Learning Technique,”
IEEE Global Telecommunications Conference, GLOBECOM 98. The Bridge to Global
Integration., vol. 3, 8-12, pp. 1715-1721, 1998.
[16] C. Y. Lin and J. S. Lin, “The Application of Penalized Fuzzy Competitive
Learning Network to Image Compression,” The Fourth Symposium on Computer and
Communication Technology, pp. 199-204, 1998.
[17] 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, pp. 244-249, 1999.
[18] D. C. Park, “Centroid Neural Network for Unsupervised Competitive
Learning,” IEEE Trans. on Neural Networks, vol. 11, no. 2, pp. 520-528,
2000.
[19] A. Bouzerdoum, “A Stochastic Competitive Learning Algorithm,”
International Joint Conference on Neural Networks, vol. 2, pp. 908-913, 2001.
[20] T. C. Lin and P. T. Yu, “A New Unsupervised Competitive Learning Algorithm
for Vector Quantization,” Proceedings of the 9th International Conference on
Neural Information Processing, vol. 2, pp. 944-948, 2002.
[21] S. Hatami, M. J. Yazdanpanah, B. Forozandeh, and O. Fateml, “A Modified
Method for Codebook Design with Neural Network in VQ-based Image
Compression,” Proceedings of the 2003 International Symposium on Circuits
and Systems, vol. 2, pp. 612-615, 2003.
[22] Y. M. Huang and R. M. Chen, “Scheduling Multiprocessor Job with Resource
and Timing Constraints Using Neural Networks,” IEEE Transaction on System,
Man, and Cybernetics, vol. 29, no. 4, pp. 490-502, 1999.
[23] J. S. Lin, K. S. Cheng, and C. W. Mao, “Multispectral Magnetic Resonance
Images Segmentation Using Fuzzy Hopfield Neural Network,” J. Biomed.
Comput., vol. 42, pp. 205-214, 1996.
[24] J. S. Lin, K. S. Cheng, and C. W. Mao, “A Fuzzy Hopfield Neural Network for
Medical Image Segmentation,” IEEE Trans. Nucl. Sci., vol. 43, pp. 2389-2398,
1996.
[25] P. C. Chung, C. T. Tsai, E. L. Chen, and Y. N. Sun, “Polygonal
Approximation Using a Competitive Hopfield Neural Network,” Pattern
Recognition, vol. 27, pp. 1505-1512, 1994.
[26] K. S. Cheng, J. S. Lin, and C. W. Mao, “The Application of Competitive
Hopfield Neural Network to Medical Image Segmentation,” IEEE Trans. Med.
Imaging, vol. 15, pp. 560-567, 1996.
[27] J. S. Lin, “Annealed Hopfield Neural Network with Moment and Entropy
Constraints for Magnetic Resonance Image Classification,” IEICE Trans. on
INF. & SYST., vol. E83-D, no. 1, pp. 100-108, 2000.
[28] J. S. Lin and S. H. Liu, “Classification of Multispectral Images Based on a
Fuzzy-Possibilistic Neural Network,” IEEE Trans. on Systems, Man, and
Cybernetics, vol. 32, no. 4, pp. 499-506, 2002.
[29] J. S. Lin, “Annealed Chaotic Neural Network with Nonlinear Self-Feedback
and Its Application to Clustering Problem,” Pattern Recognition, vol. 34,
pp. 1093-1104, 2001.
[30] S. H. Liu and J. S. Lin, “A Compensated Fuzzy Hopfield Neural Network for
Codebook Design in Vector Quantization,” International Journal of Pattern
Recognition and Artificial Intelligence, vol. 14, no. 8, pp. 1067-1079, 2000.
[31] S. H. Liu and J. S. Lin, “Vector Quantization in DCT Domain Using Fuzzy
Possibilistic C-Mean Based on Penalized and Compensated Constraints,”
Pattern Recognition, vol. 35, pp. 2201-2211, 2002.
[32] J. S. Lin, “An Annealed Chaotic Hopfield Network to Interpolative Vector
Quantizer System,” Journal of The Chinese Institute of Electrical
Engineering, vol. 9, no. 3, pp. 259-267, 2002.
[33] N. M. Nasrabadi, “Use of Vector Quantizers in Image Coding,” in Proc. IEEE
Int. Conf. Acoust., Speech, Signal Processing, pp. 125-128, 1985.
[34] C. C. Jou, “Fuzzy Clustering Using Fuzzy Competitive Learning Networks,”
International Joint Conference on Neural Networks, Vol. 2 , pp. 714 –719,
1992.
[35] R. B. David and W. R. David, “Optimization of Image Coding Algorithms and
Architectures Using Genetic Algorithms,” IEEE Trans. on Industrial
Electronics, vol. 43, no. 5, pp. 549-558, 1996.
[36] S. C. Tai, W. J. Chen, and P. J. Cheng, “Genetic Algorithm for Single
Bitmap Absolute Moment Block Truncation Coding of Color Images,” Opt. Eng.
vol. 37, no. 9, pp. 2483-2490, 1998.
[37] J. L. Deng, “Introduction to Grey Systems Theory,” The Journal of Grey
System, vol. 1, no. 1, pp. 1-24, 1989.
[38] Y. P. Huang and C. H. Huang, “A Genetic-Based Fuzzy Grey Prediction
Model,” IEEE Int. Conf. on Systems, Man and Cybernetics, vol. 2, pp.
1051-1056, 1995.
[39] B. R. Chang, “An Optimal Relational Measurement,” IEEE Int. Joint Conf. on
Neural Networks, vol. 3, pp. 1609-1614, 2001.
[40] H. C. Huang and J. L. Wu, “Grey System Theory on Image Processing and
Lossless Data Compression for HD-media,” The Journal of Grey Theory &
Practice, vol. 3, no. 2, pp. 9-15, 1993.
[41] Y. Dang, “Valuation of Grey Clustering with Human Experience,” The Journal
of Grey System, vol. 7, no. 2, pp. 119-184, 1995.
[42] Y. T. Hsu, J. Yeh, and H. C. Chang, “Image Coding Using Grey-based Codebook
Generation Algorithm,” TAAI 2000, pp. 282-285, 2000.
[43] L. Bobrowski and J. C. Bezdek, “C-means Clustering with the and
Norms,” IEEE Trans. Syst. Man. Cybern., vol. 21, pp. 545-554, 1991.
[44] P. Y. Yin and L. H. Chen, “A New Noniterative Approach for Clustering,”
Pattern Recog. Lett., vol. 15, pp. 125-133, 1994.
[45] J. C. Dunn, “A Fuzzy Relative of the ISODATA Process and Its Use in
Detecting Compact Well-Separated Clusters,” J. Cybern., vol. 3, no 3, pp.
32-57, 1974.
[46] J. C. Bezdek, “Fuzzy Mathematics in Pattern Classification,” Ph.D.
Dissertation, Applied Mathematics. Cornell University, Ithaca, New York,
1973.
[47] E. J. Delp and O. R. Mitchell, “Image Compression Using Block Truncation
Coding,” IEEE Trans. on Commun. vol. COM-27, pp. 1335-1342, 1979.
[48] V. Udpikar and J. P. Raina, “A Modified Algorithm for Block Truncation
Coding of Monochrome Images,” Electron. Lett., vol. 21, pp. 900-902, 1985.
[49] S. A. Mohamed and M. M. Fahmy, “Image Compression Using VQ-BTC,” IEEE
Trans. on Commun. vol. 43, no. 7, pp. 2177-2182, 1995.
[50] C. C. Wang, C. H. Chen and I. H. Chen, “Modified VQ-BTC Algorithm for Image
Compression,” Electronics Letters, vol. 34, no. 14, pp. 1390-1392, 1998.
[51] Moltedo L., Nappi M., Vitulano D. and Vitulano S., “Color Image Coding
Combining Linear Prediction and Iterated Function Systems,” Signal
Processing, 63, 157-162, 1997.
[52] K. S. NG and L. M. Cheng, “Artificial Neural Network for Discrete Cosine
Transform and Image Compression,” IEEE Proceedings of Fourth Int. Conf. on
Document Analysis and Recognition, vol. 2, pp. 675-678, 1997.
[53] G. K. Wallace, “The JPEG Still Picture Compression Standard,” IEEE Trans.
on Consumer Electronics, vol. 38, no. 1, 1992.
[54] M. S. Yang, “On a Class of Fuzzy Classification Maximum Likehood
Procedures,” Fuzzy Sets and Systems 57, 365, 1993.
[55] M. S. Yang and C. F. Su, “On Parameter Estimation for Normal Mixtures Based
on Fuzzy Clustering Algorithms,” Fuzzy Sets and Systems 68, 13, 1994.
[56] J. S. Lin, “Fuzzy Clustering Using a Compensated Fuzzy Hoppfield Neural
Network,” Neural Processing Letters, vol. 10, pp. 35-48, 1999.
[57] J. S. Lin, K. S. Cheng, and C. W. Mao, “Segmentation of Multispectral
Magnetic Resonance Image Using Penalized Fuzzy Competitive Learning
Network,” Computers and Biomedical Research 29, 314-326, 1996.
[58] S. C. Tai, Data Compression, 紳藍出版社 2002.
[59] J. H. Holland, Adaptation in Natural and Artificial Systems, An Introductory
Analysis with Applications to Biology, Control and Artificial Intelligence.
MIT Press, Cambridge, Massachusetts, 1992.
[60] D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine
Learning, Addison-Wesley, Reading, Massachusetts, 1989.
[61] S. M. Bhandarkar, Y. Zhang and W. D. Potter, “An Edge Detection Technique
Using Genetic Algorithm-Based Optimization,” Pattern Recognition, vol. 27,
no. 9, pp. 1159-1180, 1994.
[62] P. Andrey and P. Tarroux, “Unsupervised Image Segmentation Using a
Distributed Genetic Algorithm,” Pattern Recognition, vol. 27, no. 5, pp.
659-673, 1994.
[63] N. R. Harvey and S. Marshall, “The Use of Genetic Algorithms in
Morphological Filter Design,” Signal Process. Image Commun., vol. 8, pp.
55-71, 1996.
[64] J. S. Pan, F. R. McInnes and M. A. Jack, “Application of Parallel Genetic
Algorithm and Property of Multiple Global Optima to VQ Code Vector Index
Assignment for Noisy Channels,” Electron. Lett., vol. 32, no. 4, pp.
296-297, 1996.
[65] K. H. K. Chow, and M. L. Liou, “Genetic Motion Search Algorithm for Video
Compression,” IEEE Trans. Circuits Syst. Video Technol., vol. 3, no, 6, pp.
440-445, 1993.
[66] V. Delport and M. Koschorreck, “Genetic Algorithm for Codebook Design in
Vector Quantization,” Electron. Lett., vol. 31, no. 2, pp. 84-85, 1995.
[67] J. S. Pan, F. R. Mcinnes and M. A. Jack, “VQ Codebook Design Using Genetic
Algorithms,” Electron. Lett., vol. 31, no. 17, pp. 1418-1419, 1995.
[68] D. R. Bull and D. W. Redmill, “Optimization of Image Coding Algorithms and
Architectures Using Genetic Algorithms,” IEEE Trans. Ind. Electron, vol. 43.
no. 5, pp. 549-558, 1996.
[69] P. Scheunders, “A Genetic C-means Clustering Algorithm Applied to Color
Image Quantization,” Pattern Recognition, vol. 30, no. 6, pp. 859-866, 1997.
[70] C. H. Chen, C. Y. Lin, and J. S. Lin, “A Compensated Fuzzy Competitive
Learning Network Applied on Image Compression,” The Fifth Symposium on
Computer and Communication Technology, pp. 199-204, 2000.
[71] C. Y. Lin, C. H. Chen, and J. S. Lin, “VQ Codebook Design Using a Genetic
Competitive Learning Network,” The 13th IPPR Coferenceon Computer Vision,
Graphics and Image Processing, pp. 362-369, 2000.
[72] J. C. R. Barrientos, M. A. L. Binue, A. A. Rodriguez, F. D'Alvano, and L.
Urbano, “Image Coding Using Wavelet Transform, Vector Quantization, and
Zerotrees,” Proceedings of The Second IEEE International Caracas Conference,
pp.166 –171, 1998.
[73] S. Lin, and E. Salari, “Image Coding Using Wavelet Transform and Classified
Vector Quantisation,” IEE Proceedings, Image and Signal Processing, vol. 143
issue: 5, pp. 285 –291, 1996.
[74] N. Bourbakis and C. Alexopoulos, “Picture Data Encryption Using Scan
Patterns,” Pattern Recognition, vol. 25, pp. 567-581, 1992.
[75] T. S. Chen, C. C. Chang, and M. S. Hwang, “A Virtual Image Cryptosystem
Based upon Vector Quantization,” IEEE Trans. on Image Processing, vol. 7,
no. 10, pp. 1485-1488, 1998.
[76] P. P. Dang and P. M. Chau, “Image Encryption for Secure Internet Multimedia
Applications,” IEEE Transactions on Consumer Electronics, vol. 46, no. 3,
pp. 395-403, 2000.
[77] C. C. Chang, M. S. Hwang, and T. S. Chen, “A New Encryption Algorithm for
Image Cryptosystems,” Journal of Systems and Software, pp. 83-91, 2001.
[78] J. Fridrich, M. Goljan, and R. Du, “Detecting LSB Steganography in Color
and Gray-Scale Images,” IEEE Trans. on Multimedia, vol. 8, no. 4, pp. 22-28,
2001.
[79] R. Chandramouli and N. Memon, “Analysis of LSB Based Image Steganography
Techniques,” Proceeding of Image Processing, vol. 3, pp. 1019-1022, 2001.
[80] L. M. Marvel, C. G. Boncelet, and C. T. Retter, “Spread Spectrum Image
Steganography,” IEEE Trans. on Image Processing, vol. 8, no. 8, pp.
1075-1083, 1999.
[81] Data Encryption Standard, Federal Information Processing Standard (FIPS) 46,
National Bureau of Standards, Jan. 1977.
[82] C. S. Laih, L. Harn, and C. C. Chang, Contemporary Cryptography and It’s
Application, Flag, 2003.
[83] R. Rivest, A. Shamir and L. Adleman, “A Method for Obtaining Digital
Signatures and Public-Key Cryptosystems,” Commun. ACM, vol. 21, pp. 120-126,
1978.
[84] K. R. Castleman, Digital Image Processing, Pretice-Hall, New York, 1996.
[85] W. Y. Chen and S. Y. Huang, “Digital Watermarking Using DCT
Transformation,” Chin-Yi Journal, vol. 18, pp. 173-183, 2000.
[86] C. Y. Lin and C. H. Chen, “Color Image Hiding Using Neural Networks with
Grey Relation Based on Interpolative Vector Quantization,” 2003 National
Computer Symposium, pp. 1398-1405, 2003.