基于元胞自动机模型的新型图像压缩算法研究
|
摘要
在保证图像质量的条件下,对图像进行压缩处理,实现高效的图像存储、传输是人们一直研究的热点问题。传统的压缩方法已经很难更大幅度的提高压缩率,人们开始对图像压缩技术引入新的理论和方法,探索新的压缩算法。随着人工智能等相关技术的发展,各种智能计算方法在图像压缩方向的应用不断出现,探索智能计算在图像压缩中的应用成为了一个新的研究方向。元胞自动机(CA)是人工生命的重要研究工具和理论方法分支,CA理论在图像压缩领域的应用研究也是一个新的研究热点。
本文利用CA演化状态非线性、多样性、并行性等优点,对基于CA模型的图像压缩算法进行了研究,主要研究工作和创新之处有以下几点。
本文首先简要概述了几种典型的元胞自动机模型的基本理论和发展状况,并对其在图像压缩领域的应用做了相应的理论分析,根据不同模型特点提出了其在图像压缩方向的优势和不足。
其次,根据CA模型自组织行为,变换状态的多样性的并行处理等特点,提出了基于CA模型的二值图像压缩算法的并行压缩方法;不同于传统的基于去相关、去冗余压缩方向的局限性,该压缩方法用遗传算法搜索最优的元胞自动机规则,利用矢量量化的思想,但避开了码本的设计和搜索复杂度高的缺点,达到了类似的压缩效果,实现了更高效的快速编码算法。
第三,研究了基于CA模型的灰度图像矢量量化压缩编码算法,利用多状态CA的并行处理特性,实现快速的码字搜索算法,使搜索时间复杂度大大低于传统的码字搜索算法。
第四,将模糊逻辑引入到元胞自动机模型,探索基于模糊元胞自动机模型的矢量量化中码本训练算法,利用模糊信息的不确定性,并行特点,优化生成的码本,使元胞自动机模型的应用能力更好,更智能,丰富了元胞自动机的理论。
第五,研究了基于元胞神经网络(CNN)模型在图像压缩方面的应用,提出了用CNN模型实现DCT算法,极大的提高了压缩算法效率,并分析了其算法优越性。
最后对论文的研究内容进行了总结,并提出了基于CA模型在图像压缩领域进一步的研究工作。
Image compression becomes increasingly important to support efficient storage, transmission, but the traditional compression algorithms can no longer meet the need of achieving much higher compression. Researchers in the field of image compression have focused their attention on the study of some new kinds of compression model such as artificial life. Theory and applications of the Cellular Automata (CA) as one of the directions of artificial intelligence has become an important research field of data compression in recent years.
CA is dynamical systems exhibiting many notable features, namely, nonlinear, massive parallelism, and discreteness locality of cellular interactions, etc. In this paper,we study Cellular Automata (CA) as a modeling tool successfully using in image compression. The dissertation is organized as follows:
First of all, the theoretic and analysis of some CA modeling are reported in Chapter2. We describe the advantages and disadvantages of the efficient compression algorithm basing on CA modeling compared with the traditional methods. Their potential within image compression is being investigated.
In Chapter3 reports a new Cellular Automata (CA) model for binary image compression. The search for appropriate CA having the desired characteristics to system is an extremely difficult task in view of exponentially large search space, The genetic programming (GP) has been employed to search for optimal non-linear cellular automata rules which performs the binary image compression task. The simulation research proves that the algorithm is feasible and more efficient in compression ratio, compression speed, decompression precision and the code can be compressed using other compression algorithms etc.
Compression of grayscale image data using CA model is also proposed. We presents a new quick code scheme of vector quantization based on CA. The effective- ness of code was evaluated by comparing the other methods.
Chapter4 reports the characterization of fuzzy cellular automata. The analytical study the possible compression using Fuzzy cellular automata has been done and the Algorithm is also proposed and analyzed.
Chapter5 describes the image compression method based on Cellular Neural Networks (CNN). The parallel CNN model is used for DCT image data compression. Finally Chapter 6 concludes the volume, presenting several possible avenues of future research.
本文利用CA演化状态非线性、多样性、并行性等优点,对基于CA模型的图像压缩算法进行了研究,主要研究工作和创新之处有以下几点。
本文首先简要概述了几种典型的元胞自动机模型的基本理论和发展状况,并对其在图像压缩领域的应用做了相应的理论分析,根据不同模型特点提出了其在图像压缩方向的优势和不足。
其次,根据CA模型自组织行为,变换状态的多样性的并行处理等特点,提出了基于CA模型的二值图像压缩算法的并行压缩方法;不同于传统的基于去相关、去冗余压缩方向的局限性,该压缩方法用遗传算法搜索最优的元胞自动机规则,利用矢量量化的思想,但避开了码本的设计和搜索复杂度高的缺点,达到了类似的压缩效果,实现了更高效的快速编码算法。
第三,研究了基于CA模型的灰度图像矢量量化压缩编码算法,利用多状态CA的并行处理特性,实现快速的码字搜索算法,使搜索时间复杂度大大低于传统的码字搜索算法。
第四,将模糊逻辑引入到元胞自动机模型,探索基于模糊元胞自动机模型的矢量量化中码本训练算法,利用模糊信息的不确定性,并行特点,优化生成的码本,使元胞自动机模型的应用能力更好,更智能,丰富了元胞自动机的理论。
第五,研究了基于元胞神经网络(CNN)模型在图像压缩方面的应用,提出了用CNN模型实现DCT算法,极大的提高了压缩算法效率,并分析了其算法优越性。
最后对论文的研究内容进行了总结,并提出了基于CA模型在图像压缩领域进一步的研究工作。
Image compression becomes increasingly important to support efficient storage, transmission, but the traditional compression algorithms can no longer meet the need of achieving much higher compression. Researchers in the field of image compression have focused their attention on the study of some new kinds of compression model such as artificial life. Theory and applications of the Cellular Automata (CA) as one of the directions of artificial intelligence has become an important research field of data compression in recent years.
CA is dynamical systems exhibiting many notable features, namely, nonlinear, massive parallelism, and discreteness locality of cellular interactions, etc. In this paper,we study Cellular Automata (CA) as a modeling tool successfully using in image compression. The dissertation is organized as follows:
First of all, the theoretic and analysis of some CA modeling are reported in Chapter2. We describe the advantages and disadvantages of the efficient compression algorithm basing on CA modeling compared with the traditional methods. Their potential within image compression is being investigated.
In Chapter3 reports a new Cellular Automata (CA) model for binary image compression. The search for appropriate CA having the desired characteristics to system is an extremely difficult task in view of exponentially large search space, The genetic programming (GP) has been employed to search for optimal non-linear cellular automata rules which performs the binary image compression task. The simulation research proves that the algorithm is feasible and more efficient in compression ratio, compression speed, decompression precision and the code can be compressed using other compression algorithms etc.
Compression of grayscale image data using CA model is also proposed. We presents a new quick code scheme of vector quantization based on CA. The effective- ness of code was evaluated by comparing the other methods.
Chapter4 reports the characterization of fuzzy cellular automata. The analytical study the possible compression using Fuzzy cellular automata has been done and the Algorithm is also proposed and analyzed.
Chapter5 describes the image compression method based on Cellular Neural Networks (CNN). The parallel CNN model is used for DCT image data compression. Finally Chapter 6 concludes the volume, presenting several possible avenues of future research.
引文
Langton CG. 1986.Studying articial life with cellular automata[J]. Physica D,22:120-149.
Shaw C, Das S, Sikdar B K. 2006.Cellular Automata Based Encoding Technique for Wavelet Transformed Data Targeting Still Image Compression[J]. Springer-Verlag Berlin Heidelberg 4173:141–146
曹兴芹. 2006.复杂系统的元胞自动机方法研究[D]:[博士].武汉:华中科技大学,32-34
张传武. 2003.细胞自动机在密码学中的应用研究[D]:[博士].西安:电子科技大学,2-5
于志伟,陶波. 1997.图像重建的自适应随机元胞自动机算法[J].计算机学报, 20(10):943-945
刘松涛,杨绍清. 2008.基于元胞自动机的红外弱小目标图像分割[J].海军大连舰艇学院信息与通信工程系,红外与毫米波学报, 27(1):42-45
王仲君,王能超,等. 2007.元胞自动机的演化行为研究[J].计算机应用研究, 24 (08):38-40.
黄雪梅. 2005.基于人工神经网络的图像压缩方法研究[D]:[硕士].重庆:重庆大学, 10-16.
高成锴,王斌,许凤叶,等. 2008.元胞自动机在图像修补中的应用研究[J].计算机工程与应用,44(11):196-197.
宋卫国,范维澄,林其钊. 2001.森林火灾的自组织临界行为及其在中国林火数据中的体现[J]. 自然灾害学报,10(01):38-40.
吴家安. 2009.数据压缩技术及应用[M].北京:科学出版社, 91-92.
陈善学. 2009.矢量量化技术及其在图像信号处理中的应用研究[D]:[博士].西安:电子科技大学,80-85.
张基宏,王晖,Yoshito Ueno. 1998.基于模糊矢量量化图象编码的研究[J].中国图象图形学报,3(04):295-297
薛文通,宋建社,等. 2003.图像压缩技术的现状与发展[J].计算机工程与应用,39(2):65-67.
王培春,朱甫臣. 2005.细胞自动机在密码中的应用[J].信息安全与通信保密,66(07):189-190
Chua L O,Yang L. 1988.Cellular neural networks:Theory[J].IEEE Circuits System,35:1257-1272
Maji P, Chaudhuri PP. 2008.Non-uniform Cellular Automata Based Associative Memory: Evolutionary Design and Basins of Attraction[J].Information Sciences, 178(10):2315—2336.
O.Lafe. 1996.Data Compression and Encryption Using Cellular Automata Transforms[J]. IEEE International Joint Symposia on Intelligence and Systems, 10(6):581-591.
Sipper M. 1997.Evolution of Parallel Cellular Machines: The Cellular Programm Approach[D]: [Ph.D. ]. Switzerland:Lausanne Computer Science. 44-96.
Ganguly N, Maji P, Dhar S ,et al. 2002.Evolving Cellular Automata as Pattern Classifier[J].Lecture Notes In Computer Science, 2493:56– 68.
Ganguly N. 2003.Cellular Automata Evolution: Theory and Applications in Pattern Recognition and Classification, [D]: [Ph.D. ]. India: DeemedUniversity,9-33
Omid E Kia, Doermann David S, et al. 1998.Symbolic Compression and Processing of Document Images[J]. IEEE Computer Society, 70:335-349
Karadimitriou K, Fenstermacher M. 1997.Image compression in medical image databases using set redundancy[J]. IEEE Proceedings of Data Compression Conference, 97: 25-27.
Karadimitriou K, John M.Tyler. 1998.The centroid method for compressing sets of similar images[J]. Pattern Recognition Letters 19:585-593
Maji P, PalChaudhuri P. 2005.Fuzzy Cellular Automata for Modeling Pattern Classifier[J].IEICE Transactionson on Informationand Systems ,E88-D:691-702.
Mitchell M, Hraber PT, Crutchfield JP. 1993.Revisiting the Edge of Chaos:Evolving Cellular Automata to Perform Computations[J]. Complex Systems 7:89-130.
Mitchell M, Crutchfield JP, et al 1994.Evolving Cellular Automata to Perform Computations: Mechanisms and Impediments[J]. Physica D: Nonlinear Phenomena 75:361- 391.
Shaw C, Maji P,et al. 2004.Cellular Automata Based Encompression Technology for Voice Data[R], Proceedings of 6th International Conference on Cellular Automata for Research and Industry, ACRI, Netherland,258-267.
李才伟,胡瑞安. 1997.自组织现象的元胞自动机模拟与图示[J].计算机辅助设计与图形学学报,9(06):532-534.
Tzionas P, TsalidesP, et al. 1994.A New Cellular Automaton-based Nearest Neighbor Pattern Classier and its VLSI Implementation[J].IEEE Trans. on VLSI Implementation, 2:343-353.
Cuifang Zhao,et al. 2008.A Cellular Automaton for Image Compression[J]. IEEE Fourth International Conference on Natural Computation,10:397-399
Mercier G, Mouchot MC, et al. 1999.Joint classification and compression of hyperspectral images[J]. IEEE IGARSS,99:2035-2037.
Ganguly N, Maji P, et al. 2004.Design and characterization of cellular automata based associative memory for pattern recognition[J].IEEE Trans Syst Man Cybern B Cybern,34(1):672-9.
Linde Y, Buzo A, Gray R. 2003.An algorithm for vector quantization design[J]. IEEETrans on Commum, 28(1):84-95.
Suzudo T. 2004.Searching for Pattern-Forming Asynchronous Cellular Automata An Evolutionary Approach[R]. Springer Berlin lecture notes in computer science,3305:151-160.
Tomassini M, Venzi M. 2002.Artificially Evolved Asynchronous Cellular Automata for the Density Task[R].Springer lecture notes in computer science, 2439: 934-943.
Leskes B, Sloot PMA. 2004. Unlearning phenomena in co-evolution of non-uniform cellular automata[R]. Springer Berlin:Lecture Notes in Computer Science, 3305:172-181
Sipper M. 1996.Co-evolving non-uniform cellular automata to perform computations[J]. Physica D,92:193-208.
Suzudo T. 2004. Searching for pattern-forming asynchronous cellular automata-An evolutionary approach[R]. Springer Berlin:Lecture Notes in Computer Science, 3305:151-160.
Barmpoutis V. 2007.A Compact Self-organizing Cellular Automata-based Genetic Algorithm[J]. Neural and Evolutionary Computing,5-8.
Romano ALT, et al. 2006.Evolutionary Modeling of Larval Dispersal in Blowflies Using Non-Uniform Cellular Automata[J]. IEEE Congress on Evolutionary Computation, Vancouver, BC:1127-1134.
Leskes B, Sloot PMA. 2004.Unlearning Phenomena in Co-evolution of Non-uniform Cellular Automata[R]. Springer Berlin lecture notes in computer science,3305:172-181.
Tomassini M, et al. 2004.Evolving Small-World Automata for the Majority Problem[R]. Springer Berlin Lecture Notes in Computer Science,3242:672-681.
Jiménez-Morales F. 2002.An Evolutionary Approach to the Study of Non-trivial Collective Behavior in Cellular Automata[R]. Springer Berlin Lecture Notes in Computer Science, 2493: 32-43
Sahoo S, Nayak BK, et al. 2008.Encompression Using Two-dimensional Cellular Automata Rules[R]. arXiv: 0808.1470.
Sipper M. 1997.Evolution of Parallel Cellular Programming Approach[R]. Springer Lecture Notes in Computer Science, 44-98.
Crutchfield JP, Mitchell M, Das R. 1998.The Evolutionary Design of Collective Computation in Cellular Automata[J]. Machine Learning Journal,3-18.
Adachi S, Peper F, Lee J. 2004.Computation by Asynchronously Updating Cellular Automata [J]. Journal of Statistical Physics,3-5.
Terrier V. 1996.Languages not recognizable in real time by one-dimensional cellular automata[J]. Theoretical Computer Science,156: 281– 287.
Jin'no k, 2001.Analysis of hysteresis cellular automata[J]. IEEE International Symposium, 99:17-23.
Sutner K. 2004.The complexity of reversible cellular automata[J].Theoretical Computer Science, 325:317-328.
Czeizler E. 2004.On the size of the inverse neighborhoods for one-dimensional reversible cellular Automata[J].Theoretical Computer Science,325:273-284.
Maji P, et al. 2003. Theory and Application of Cellular Automata For Pattern Classification[J]. Fundamenta Informaticae,58:3321–354.
Ganguly N, et al. 2001. Evolving Cellular Automata Based Associative Memory for Pattern Recognition [J]. HiPC:115-124.
Ke Zhang, et al.2007.Edge Detection of Images based on Fuzzy Cellular Automata[J]. Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing,2:289-294.
Hong Wang.2009.Image Processing Based on Fuzzy Cellular Automata Model[R]. Fourth International Conference on Innovative Computing, Information and Control, 954-957.
Maji P, Pal P. 2005. Fuzzy cellular automata based associative memory for pattern recognition[J]. Intelligent Sensing and Infor,284-289.
Karayiannis NB, Pai PI. 1995. Fuzzy vector quantization algorithms and their application in image compression[J]. IEEE Trans Image Process. 4(9):1193-201.
Venetianer P.L, Roska T. 1998.Image compression by cellular neural networks[J]. IEEE Transactions on Automatic Control, vol.45, no.3 205 - 215
王怀颖. 2007.细胞神经网络在图像处理中的应用技术研究[D].[博士].南京:南京航空航天大学,14-15
程莹,刘文波. 2008.基于自适应遗传算法的细胞神经网络模板设计[J].计算机技术与发展,18(5):2-3.
Aomori H, Otake T, et al. 2004.Lossless image coding based on lifting wavelet using discrete-time cellular neural network with multi-templates[R]. Proceedings of the 2004 International Symposium on Circuits and Systems, 3:102-104.
Kozek T, et al. 1993.Genetic Algorithm for CNN Template Learning[J]. Circuits and Systems I,40:392– 402.
Shaw C, Das S, Sikdar B K. 2006.Cellular Automata Based Encoding Technique for Wavelet Transformed Data Targeting Still Image Compression[J]. Springer-Verlag Berlin Heidelberg 4173:141–146
曹兴芹. 2006.复杂系统的元胞自动机方法研究[D]:[博士].武汉:华中科技大学,32-34
张传武. 2003.细胞自动机在密码学中的应用研究[D]:[博士].西安:电子科技大学,2-5
于志伟,陶波. 1997.图像重建的自适应随机元胞自动机算法[J].计算机学报, 20(10):943-945
刘松涛,杨绍清. 2008.基于元胞自动机的红外弱小目标图像分割[J].海军大连舰艇学院信息与通信工程系,红外与毫米波学报, 27(1):42-45
王仲君,王能超,等. 2007.元胞自动机的演化行为研究[J].计算机应用研究, 24 (08):38-40.
黄雪梅. 2005.基于人工神经网络的图像压缩方法研究[D]:[硕士].重庆:重庆大学, 10-16.
高成锴,王斌,许凤叶,等. 2008.元胞自动机在图像修补中的应用研究[J].计算机工程与应用,44(11):196-197.
宋卫国,范维澄,林其钊. 2001.森林火灾的自组织临界行为及其在中国林火数据中的体现[J]. 自然灾害学报,10(01):38-40.
吴家安. 2009.数据压缩技术及应用[M].北京:科学出版社, 91-92.
陈善学. 2009.矢量量化技术及其在图像信号处理中的应用研究[D]:[博士].西安:电子科技大学,80-85.
张基宏,王晖,Yoshito Ueno. 1998.基于模糊矢量量化图象编码的研究[J].中国图象图形学报,3(04):295-297
薛文通,宋建社,等. 2003.图像压缩技术的现状与发展[J].计算机工程与应用,39(2):65-67.
王培春,朱甫臣. 2005.细胞自动机在密码中的应用[J].信息安全与通信保密,66(07):189-190
Chua L O,Yang L. 1988.Cellular neural networks:Theory[J].IEEE Circuits System,35:1257-1272
Maji P, Chaudhuri PP. 2008.Non-uniform Cellular Automata Based Associative Memory: Evolutionary Design and Basins of Attraction[J].Information Sciences, 178(10):2315—2336.
O.Lafe. 1996.Data Compression and Encryption Using Cellular Automata Transforms[J]. IEEE International Joint Symposia on Intelligence and Systems, 10(6):581-591.
Sipper M. 1997.Evolution of Parallel Cellular Machines: The Cellular Programm Approach[D]: [Ph.D. ]. Switzerland:Lausanne Computer Science. 44-96.
Ganguly N, Maji P, Dhar S ,et al. 2002.Evolving Cellular Automata as Pattern Classifier[J].Lecture Notes In Computer Science, 2493:56– 68.
Ganguly N. 2003.Cellular Automata Evolution: Theory and Applications in Pattern Recognition and Classification, [D]: [Ph.D. ]. India: DeemedUniversity,9-33
Omid E Kia, Doermann David S, et al. 1998.Symbolic Compression and Processing of Document Images[J]. IEEE Computer Society, 70:335-349
Karadimitriou K, Fenstermacher M. 1997.Image compression in medical image databases using set redundancy[J]. IEEE Proceedings of Data Compression Conference, 97: 25-27.
Karadimitriou K, John M.Tyler. 1998.The centroid method for compressing sets of similar images[J]. Pattern Recognition Letters 19:585-593
Maji P, PalChaudhuri P. 2005.Fuzzy Cellular Automata for Modeling Pattern Classifier[J].IEICE Transactionson on Informationand Systems ,E88-D:691-702.
Mitchell M, Hraber PT, Crutchfield JP. 1993.Revisiting the Edge of Chaos:Evolving Cellular Automata to Perform Computations[J]. Complex Systems 7:89-130.
Mitchell M, Crutchfield JP, et al 1994.Evolving Cellular Automata to Perform Computations: Mechanisms and Impediments[J]. Physica D: Nonlinear Phenomena 75:361- 391.
Shaw C, Maji P,et al. 2004.Cellular Automata Based Encompression Technology for Voice Data[R], Proceedings of 6th International Conference on Cellular Automata for Research and Industry, ACRI, Netherland,258-267.
李才伟,胡瑞安. 1997.自组织现象的元胞自动机模拟与图示[J].计算机辅助设计与图形学学报,9(06):532-534.
Tzionas P, TsalidesP, et al. 1994.A New Cellular Automaton-based Nearest Neighbor Pattern Classier and its VLSI Implementation[J].IEEE Trans. on VLSI Implementation, 2:343-353.
Cuifang Zhao,et al. 2008.A Cellular Automaton for Image Compression[J]. IEEE Fourth International Conference on Natural Computation,10:397-399
Mercier G, Mouchot MC, et al. 1999.Joint classification and compression of hyperspectral images[J]. IEEE IGARSS,99:2035-2037.
Ganguly N, Maji P, et al. 2004.Design and characterization of cellular automata based associative memory for pattern recognition[J].IEEE Trans Syst Man Cybern B Cybern,34(1):672-9.
Linde Y, Buzo A, Gray R. 2003.An algorithm for vector quantization design[J]. IEEETrans on Commum, 28(1):84-95.
Suzudo T. 2004.Searching for Pattern-Forming Asynchronous Cellular Automata An Evolutionary Approach[R]. Springer Berlin lecture notes in computer science,3305:151-160.
Tomassini M, Venzi M. 2002.Artificially Evolved Asynchronous Cellular Automata for the Density Task[R].Springer lecture notes in computer science, 2439: 934-943.
Leskes B, Sloot PMA. 2004. Unlearning phenomena in co-evolution of non-uniform cellular automata[R]. Springer Berlin:Lecture Notes in Computer Science, 3305:172-181
Sipper M. 1996.Co-evolving non-uniform cellular automata to perform computations[J]. Physica D,92:193-208.
Suzudo T. 2004. Searching for pattern-forming asynchronous cellular automata-An evolutionary approach[R]. Springer Berlin:Lecture Notes in Computer Science, 3305:151-160.
Barmpoutis V. 2007.A Compact Self-organizing Cellular Automata-based Genetic Algorithm[J]. Neural and Evolutionary Computing,5-8.
Romano ALT, et al. 2006.Evolutionary Modeling of Larval Dispersal in Blowflies Using Non-Uniform Cellular Automata[J]. IEEE Congress on Evolutionary Computation, Vancouver, BC:1127-1134.
Leskes B, Sloot PMA. 2004.Unlearning Phenomena in Co-evolution of Non-uniform Cellular Automata[R]. Springer Berlin lecture notes in computer science,3305:172-181.
Tomassini M, et al. 2004.Evolving Small-World Automata for the Majority Problem[R]. Springer Berlin Lecture Notes in Computer Science,3242:672-681.
Jiménez-Morales F. 2002.An Evolutionary Approach to the Study of Non-trivial Collective Behavior in Cellular Automata[R]. Springer Berlin Lecture Notes in Computer Science, 2493: 32-43
Sahoo S, Nayak BK, et al. 2008.Encompression Using Two-dimensional Cellular Automata Rules[R]. arXiv: 0808.1470.
Sipper M. 1997.Evolution of Parallel Cellular Programming Approach[R]. Springer Lecture Notes in Computer Science, 44-98.
Crutchfield JP, Mitchell M, Das R. 1998.The Evolutionary Design of Collective Computation in Cellular Automata[J]. Machine Learning Journal,3-18.
Adachi S, Peper F, Lee J. 2004.Computation by Asynchronously Updating Cellular Automata [J]. Journal of Statistical Physics,3-5.
Terrier V. 1996.Languages not recognizable in real time by one-dimensional cellular automata[J]. Theoretical Computer Science,156: 281– 287.
Jin'no k, 2001.Analysis of hysteresis cellular automata[J]. IEEE International Symposium, 99:17-23.
Sutner K. 2004.The complexity of reversible cellular automata[J].Theoretical Computer Science, 325:317-328.
Czeizler E. 2004.On the size of the inverse neighborhoods for one-dimensional reversible cellular Automata[J].Theoretical Computer Science,325:273-284.
Maji P, et al. 2003. Theory and Application of Cellular Automata For Pattern Classification[J]. Fundamenta Informaticae,58:3321–354.
Ganguly N, et al. 2001. Evolving Cellular Automata Based Associative Memory for Pattern Recognition [J]. HiPC:115-124.
Ke Zhang, et al.2007.Edge Detection of Images based on Fuzzy Cellular Automata[J]. Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing,2:289-294.
Hong Wang.2009.Image Processing Based on Fuzzy Cellular Automata Model[R]. Fourth International Conference on Innovative Computing, Information and Control, 954-957.
Maji P, Pal P. 2005. Fuzzy cellular automata based associative memory for pattern recognition[J]. Intelligent Sensing and Infor,284-289.
Karayiannis NB, Pai PI. 1995. Fuzzy vector quantization algorithms and their application in image compression[J]. IEEE Trans Image Process. 4(9):1193-201.
Venetianer P.L, Roska T. 1998.Image compression by cellular neural networks[J]. IEEE Transactions on Automatic Control, vol.45, no.3 205 - 215
王怀颖. 2007.细胞神经网络在图像处理中的应用技术研究[D].[博士].南京:南京航空航天大学,14-15
程莹,刘文波. 2008.基于自适应遗传算法的细胞神经网络模板设计[J].计算机技术与发展,18(5):2-3.
Aomori H, Otake T, et al. 2004.Lossless image coding based on lifting wavelet using discrete-time cellular neural network with multi-templates[R]. Proceedings of the 2004 International Symposium on Circuits and Systems, 3:102-104.
Kozek T, et al. 1993.Genetic Algorithm for CNN Template Learning[J]. Circuits and Systems I,40:392– 402.