用于块截断编码图像信息隐藏的遗传算法研究
|
摘要
遗传算法(Genetic Algorithm,简称GA)是一种模仿生物自然进化过程的随机搜索和优化算法,其优势在于简单易行、鲁棒性强、全局优化性强和易操作,目前被广泛用于函数优化、机器学习、模式识别以及自适应控制系统等众多领域。但遗传算法也存在收敛速度慢、易早熟、局部搜索能力差等缺点,为了尽量克服这些缺点,将遗传算法用于块截断编码图像信息隐藏中解决提高压缩率、加快收敛速度等问题,在对遗传算法进行深入分析的基础上,本文做了如下研究工作:
本文介绍了遗传算法的研究现状。研究了遗传算法各组成要素的具体策略。采用了适合于块截断编码图像信息隐藏的遗传算法方案(BTCIIHGA),该方案包括遗传算法引导搜索的主要依据就是个体的适应度值,适应度函数的选取直接影响到遗传算法的搜索性能,采用基于人眼视觉的适应度函数,并对运行结果进行了详细分析,结果表明基于人眼视觉的适应度函数收敛速度快、搜索能力好。应用复制三基色位图的方式初始化原始种群,采用均匀排序选择算法来促进种群进化。利用神经网络中的构造神经元激活函数Sigmoid函数,该函数在线性和非线性之间显现出较好的平衡,交叉率、变异率按照个体适应度在平均适应度和最大适应度之间随Sigmoid函数非线性调整,因此采用自适应交叉变异的方式有效的防止算法停滞不前,摆脱局部收敛,提高了算法的鲁棒性。在前面研究基础上,采用在遗传算法后期加入进化逆转操作进一步优化种群得到通用位图,从而改善遗传算法局部搜索能力。
本文利用MATLAB软件进行仿真试验,并对实验数据进行了分析、处理,对实验产生的误差进行了讨论。这虽然只是利用遗传算法来提高块截断编码图像信息隐藏压缩率的一个理论探讨,但它对实际信息隐藏有着重要的指导意义。
Genetic Algorithm (Genetic Algorithm, abbreviated as GA) is an imitation of the natural biological process of evolution of random search and optimization algorithm, its advantage lies in simple, robust, strong global optimization and easy to operate, it is being widely used in the function optimization, machine learning, pattern recognition and adaptive control systems and many other fields. However, Because of the standard GA have such disadvantages as premature convergence, low convergence speed and low robustness which generate the large general mean-square error between the original images and the common bitmaps. in order to overcome these shortcomings, genetic algorithm is used to block truncation coding image information hiding to raise the compression ratio, speed up the convergence speed and so on. Based on in-depth analysis, the main contributions in this dissertation are as follows:
The recent status of genetic algorithms is described. The specific strategies of genetic algorithm elements are researched. the scheme of genetic algorithm applying to block truncation coding for image information hiding is used. The scheme includes: The theory for genetic algorithm is mainly based on the individual fitness value and it is found that the selection of the fitness function directly affects the search performance of genetic algorithms. Moreover, proposing fitness function which based on human vision and analysis the detail of the simulation results which showed fast convergence speed and good search capabilities based on human vision fitness function. Proposed the method of copying the three color bitmaps to initialize the original population and also proposed a uniform ranking selection algorithm to promote the evolution of populations. By using the function of sigmoid which constructs the function of neuron activation in neural network activation, we find that it shows a good balance between linear and non-linear. According to individual fitness, the crossover rate, mutation rate are adaptive non-linear adjustment between average fitness and maximum fitness, therefore, an effective way has put forward named adaptive crossover and adaptive mutation to prevent stagnation, break away from the local convergence and improve the algorithm robustness. To improve the local search ability and optimize the population to get the common bitmap, adding evolution reverse operation is presented when genetic algorithm run into the late stage.
This paper focuses on the simulation by using MATLAB, and analyses the experimental data and discusses the experimental errors, Although this is only a theory discussion about the use of genetic algorithm combined with the block truncation coding applying to image information hiding to improve the compression ratio, it has important significance for actual information hiding theory.
本文介绍了遗传算法的研究现状。研究了遗传算法各组成要素的具体策略。采用了适合于块截断编码图像信息隐藏的遗传算法方案(BTCIIHGA),该方案包括遗传算法引导搜索的主要依据就是个体的适应度值,适应度函数的选取直接影响到遗传算法的搜索性能,采用基于人眼视觉的适应度函数,并对运行结果进行了详细分析,结果表明基于人眼视觉的适应度函数收敛速度快、搜索能力好。应用复制三基色位图的方式初始化原始种群,采用均匀排序选择算法来促进种群进化。利用神经网络中的构造神经元激活函数Sigmoid函数,该函数在线性和非线性之间显现出较好的平衡,交叉率、变异率按照个体适应度在平均适应度和最大适应度之间随Sigmoid函数非线性调整,因此采用自适应交叉变异的方式有效的防止算法停滞不前,摆脱局部收敛,提高了算法的鲁棒性。在前面研究基础上,采用在遗传算法后期加入进化逆转操作进一步优化种群得到通用位图,从而改善遗传算法局部搜索能力。
本文利用MATLAB软件进行仿真试验,并对实验数据进行了分析、处理,对实验产生的误差进行了讨论。这虽然只是利用遗传算法来提高块截断编码图像信息隐藏压缩率的一个理论探讨,但它对实际信息隐藏有着重要的指导意义。
Genetic Algorithm (Genetic Algorithm, abbreviated as GA) is an imitation of the natural biological process of evolution of random search and optimization algorithm, its advantage lies in simple, robust, strong global optimization and easy to operate, it is being widely used in the function optimization, machine learning, pattern recognition and adaptive control systems and many other fields. However, Because of the standard GA have such disadvantages as premature convergence, low convergence speed and low robustness which generate the large general mean-square error between the original images and the common bitmaps. in order to overcome these shortcomings, genetic algorithm is used to block truncation coding image information hiding to raise the compression ratio, speed up the convergence speed and so on. Based on in-depth analysis, the main contributions in this dissertation are as follows:
The recent status of genetic algorithms is described. The specific strategies of genetic algorithm elements are researched. the scheme of genetic algorithm applying to block truncation coding for image information hiding is used. The scheme includes: The theory for genetic algorithm is mainly based on the individual fitness value and it is found that the selection of the fitness function directly affects the search performance of genetic algorithms. Moreover, proposing fitness function which based on human vision and analysis the detail of the simulation results which showed fast convergence speed and good search capabilities based on human vision fitness function. Proposed the method of copying the three color bitmaps to initialize the original population and also proposed a uniform ranking selection algorithm to promote the evolution of populations. By using the function of sigmoid which constructs the function of neuron activation in neural network activation, we find that it shows a good balance between linear and non-linear. According to individual fitness, the crossover rate, mutation rate are adaptive non-linear adjustment between average fitness and maximum fitness, therefore, an effective way has put forward named adaptive crossover and adaptive mutation to prevent stagnation, break away from the local convergence and improve the algorithm robustness. To improve the local search ability and optimize the population to get the common bitmap, adding evolution reverse operation is presented when genetic algorithm run into the late stage.
This paper focuses on the simulation by using MATLAB, and analyses the experimental data and discusses the experimental errors, Although this is only a theory discussion about the use of genetic algorithm combined with the block truncation coding applying to image information hiding to improve the compression ratio, it has important significance for actual information hiding theory.
引文
[1] XIANMIN WANG, ZEQUN GUAN, CHENHAN WU. A novel information hiding technique for remote sensing image [J]. Berlin: Springer-Verlag, 2005: 423-430.
[2] FRIDRICH J., GOLJAN M, DU R.. Reliable detection of LSB Steganography in color and grayscale images[C]. Proc. ACM Workshop on Multimedia and Security, 2001:27-30.
[3]孔祥维.信息安全中的信息隐藏理论和方法研究[D].大连理工大学博士学位论文, 2003:44-57.
[4] LEE, YEUAN-KUEN, LING-HWEI CHEN. High Capacity Image Steganographic Model [J]. IEEE Proceedings Vision, Image and Signal Process, June 2000, 147(3): 288-294.
[5] JINGMING GUO, MINGFENG WU. Improved Block Truncation Coding Based on the Void-and-Cluster Dithering Approach [J]. IEEE transactions on image processing, 2009, 18(1):211-213.
[6]张粱斌,周必水等.自适应遗传算法与分形图像压缩结合的新方法[J].计算机应用研究, 2006(7):248-251.
[7] FRIDRICH J., LONG M.. Steganalysis of LSB Encoding in Color Images[C]. IEEE International Conference on Multimedia and Expo, 2000(3):1279-1282.
[8] MILLER B.L., SHAW, M. J.. Genetic algorithms with dynamic niche sharing for multimodal function optimization [C]. IEEE International Conference on Evolutionary computation, 2002:786-791.
[9]邝溯琼.遗传算法参数自适应控制[D].中南大学硕士学位论文, 2009:1-2.
[10]徐小云,顔国正.遗传算法及其在机器人控制中的应用[J].光学精密工程, 2001,9(4):334-338.
[11]储理才.基于MATLAB的遗传算法程序设计及TSP问题求解[J].集美大学学报, 2000,(6):15-19.
[12] CHIN-CHEN CHANG, CHIH-YANG LIN, YI-HSUAN FAN. Lossless data hiding for color images based on block truncation coding [J]. Soft Computing, Springer Berlin, 2008: 8-11.
[13] YANG ZEQING, LIU LIBING, TAN ZHIHONG. Application of Adaptive Genetic Algorithm in flexible inspection path planning [C]. IEEE control conference, 2008: 75-80.
[14]王小平,曹立明.遗传算法:理论、应用与软件实现[M].西安:西安交通大学出版社, 2002.
[15]金晶,苏勇.一种改进的自适应遗传算法.计算机工程与应用[J]. 2005,18:64-69.
[16]申晓宁,胡维礼.一种多目标优化合作型协同进化算法[J].计算机仿真, 2007,24(2):157-161.
[17]牛向阳,倪前月,高成修.基于遗传算法和模拟退火算法的混合算法[J].昆明理工大学学报, 2008,33(2):25-28.
[18]钟宁,何遵文,匡镜明.基于遗传算法的图像水印优化嵌入技术研究[J].兵工学报, 2008,29(9):1054-1058.
[19]徐启玉,梅亚东.遗传模拟退火和小生境遗传算法在水库优化调度中的比较[J].水电自动化与大坝监测, 2008,32(4):1-4.
[20]何江萍,马彦.方块截短编码中同步消除噪声干扰的新算法[J].计算机工程与设计. 2008, 29(20):5256-5259.
[21]杨华芬.一种改进的自适应遗传算法[J].云南民族大学学报, 2009,18(3):264-267.
[22]赖鑫生,冷明伟.变异区间自适应调整的遗传算法[J].计算机应用, 2009,29(6):1566-1568.
[23]帅训波,马书南,欧阳永林.一种基于矩阵遗传算子的优化组合遗传算法[J].小型微型计算机系统, 2009,5(5):951-954.
[24]雷亮,汪同庆,彭军等.改进的自适应遗传算法应用研究[J].计算机科学, 2009,36(6):203-247.
[25]李良敏,温广瑞.遗传算法中遗传操作的改进策略[J].计算机应用与软件,2009,26(6):27-29.
[26]贺巧龙,李东亮.基于遗传算法的函数优化问题研究[J].软件导刊, 2009,6(29):71-72.
[27]李光布,李景辉.遗传算法的分析及其改进[J].计算机仿真, 2009,26(7):228-231.
[28]李钊,古辉.基于遗传算法进化的数字图像处理[J].中国新技术新产品, 2010,2(9):7-8.
[29] JOHNSON J.M., RABMAT-SAMII. Genetic algorithm optimization for aerospace electromagnetic design and analysis [C]. IEEE, Aerospace Applications Conference, 2002: 87-102.
[30] SKOLPADUNGKET, P. DAHAL. Portfolio optimization using multi-objective genetic algorithms [J]. Evolutionary Computation, 2007, 516-523.
[31] ZHAO RUIMING, QIAN DONGPING. Application of Genetic Algorithm in the Optimization of Water Pollution Control Scheme [J]. Intelligent Information Technology Application, 2008:189-191.
[32] TAISHAN YAN, YONG-QING TAO, DUWU CUI. Research on handwritten numeral recognition method based on improved genetic algorithm and neural network [J]. Wavelet Analysis and Pattern Recognition, 2008: 1271-1276.
[33] KAUR, D. MURUGAPPAN. Performance enhancement in solving Traveling Salesman Problem using hybrid genetic algorithm [J]. Fuzzy Information Processing Society, 2008, 1-6.
[34] ABDERRAHIM, A. TALBI. Hybridization of Genetic and Quantum Algorithm for gene selection and classification of Micro-array data [J]. Parallel & Distributed Processing, 2009: 1-8.
[35] HEGEN XIONG, KAI XIONG, QIUHUA TANG. A Novel Variable-Boundary-Coded Quantum Genetic Algorithm for Function Optimization [C]. IEEE International Conference on Dependable, Autonomic and Secure Computing, 2010: 279-285.
[36] JIE YAO KHARMA, GROGONO N., Bi-Objective Multi-population GeneticAlgorithm for Multimodal Function Optimization [J]. Evolutionary Computation, 2010: 80-102.
[37]徐瑛,任雪梅.基于MATLAB的遗传算法工具箱[C].自动化理论、技术与应用,中国科学技术大学出版社. 2003:445-452.
[38]陈玉萍,须文波.基于遗传算法的图像压缩[J].计算机应用研究,2007,(6):167-169.
[39]朱灿,梁昔明.一种多精英保存策略的遗传算法[J].计算机应用,2008,28(4):939-941.
[40]周洪伟.遗传算法“早熟”现象和改进策略研究[D].解放军信息工程大学硕士学位论文, 2004:15-30.
[41]明亮.遗传算法模式理论及收敛理论[D].西安电子科技大学博士学位论文, 2006,21-24.
[42]朱成娟.遗传算法的改进及其若干应用[D].燕山大学硕士学位论文, 2006:21-22.
[43] SHEN-CHUAN TAI, WEN-JAN CHEN, PO-JEN CHENG. Genetic algorithm for single bitmap absolute moment block truncation coding of color images [J]. Institute of Electrical Engineering, 1998: 2483-2489.
[44] E. J. DELP AND O. R. MITCHELL. Image compression using block truncation coding [J], IEEE Trans. Commune, 1997(27): 1335-1342.
[45] HOU YOUNG-CHANG, TU, SHU-FEN. Chang Ya-Hui. Block Truncation Coding by Using Genetic Algorithm [J].IEEE Malta, 2008:1273-1278.
[46]雷英杰,张善文,李续武等. MATLAB遗传算法工具箱及应用[M].西安电子科技大学出版社, 2009:23-24.
[47] MENNON A, K MEHROTRA, CK MOHAN et al. Characterization of a class of sigmoid functions with applications to neural networks [J]. Neural Networks, 1996, 9: 819-835.
[48]孙明华,崔海涛等.基于精英保留遗传算法的连续结构多约束拓扑优化[J].航空动力学报, 2006,21(4):732-737.
[49] KAI-KUANG MA, RAJALA S.A.. New properties of absolute moment blocktruncation coding [J]. IEEE Signal Processing Society, 2002, 2(2): 34-36.
[50] DUNWEI GONG, GUANGSONG GUO, LILU. Adaptive interactive genetic algorithms with individual interval fitness [J]. Progress in Natural Science, 2008: 359-365.
[51] QINGLI, WEN-HAO HE, HAN-HONG JIANG. A Study on Image Segmentation by an Improved Adaptive Algorithm [C]. International Conference on Machine Learning and Cybernetics, IEEE, 2007:1570-1573.
[52]阎妍.一种新的自适应遗传算法[D].哈尔滨工程大学硕士学位论文, 2007:23-29.
[53] TAI S. C., LIN Y. C., LIN J. F.. Single bit-map block truncation coding of color images using a Hopfield neural network. Inf. Sci.1997, 103(1-4): 211-228.
[54] WU Y., COLL D. C.. Single bit-map block truncation coding of color images [J]. IEEE J. Sel. Areas Commun. 1992, 10(5): 952-959.
[55] HIN-CHEN CHANG, YI-HUI CHEN. Chia-Chen Lin. A data embedding scheme for color images based on genetic algorithm and absolute moment block truncation coding [J]. Soft Computing, Springer Berlin, 2009: 321-331.
[56] XU ZHENG-JUN, TANG SHUO. UAV Path Planning Based on Adaptive Genetic Algorithm [J]. Journal of System Simulation, 2008, 20(19): 5411-5418.
[57]李敏强,寇纪松.遗传算法的基本理论与应用[M].科学出版社, 2002:1-80.
[58]吴秋玲.改进的遗传算法及其在CDMA基站优化选址中的应用[D].河海大学硕士学位论文, 2006:40-50.
[59]陈华,叶东.遗传算法的数字图像相关搜索法[J].光学精密工程, 2007, 15(10):1633-1637.
[60]张怀柱,向长波.改进的遗传算法在实时图像分割中的应用[J].光学精密工程, 2008,16(2):333-337.
[61] FRIDRICH J., GOLJAN M., DU R.. Lossless data embedding-new paradigm in digital watermarking, Special Issue on Emerging Applications of Multimedia Data Hiding [J]. 2002(2): 185-196.
[62] CHANG C. C., WU M. N.. A color image progressive transmission method by common bit map block truncation coding approach [C]. Proceedings of the International Conference on Communication Technology, Beijing, 2003: 1774-1778.
[63] YU Y. H., CHANG C. C., HU Y. C.. Hiding secret data in images via predictive coding [J]. Pattern Recognition, 2005, 38(5): 691-705.
[2] FRIDRICH J., GOLJAN M, DU R.. Reliable detection of LSB Steganography in color and grayscale images[C]. Proc. ACM Workshop on Multimedia and Security, 2001:27-30.
[3]孔祥维.信息安全中的信息隐藏理论和方法研究[D].大连理工大学博士学位论文, 2003:44-57.
[4] LEE, YEUAN-KUEN, LING-HWEI CHEN. High Capacity Image Steganographic Model [J]. IEEE Proceedings Vision, Image and Signal Process, June 2000, 147(3): 288-294.
[5] JINGMING GUO, MINGFENG WU. Improved Block Truncation Coding Based on the Void-and-Cluster Dithering Approach [J]. IEEE transactions on image processing, 2009, 18(1):211-213.
[6]张粱斌,周必水等.自适应遗传算法与分形图像压缩结合的新方法[J].计算机应用研究, 2006(7):248-251.
[7] FRIDRICH J., LONG M.. Steganalysis of LSB Encoding in Color Images[C]. IEEE International Conference on Multimedia and Expo, 2000(3):1279-1282.
[8] MILLER B.L., SHAW, M. J.. Genetic algorithms with dynamic niche sharing for multimodal function optimization [C]. IEEE International Conference on Evolutionary computation, 2002:786-791.
[9]邝溯琼.遗传算法参数自适应控制[D].中南大学硕士学位论文, 2009:1-2.
[10]徐小云,顔国正.遗传算法及其在机器人控制中的应用[J].光学精密工程, 2001,9(4):334-338.
[11]储理才.基于MATLAB的遗传算法程序设计及TSP问题求解[J].集美大学学报, 2000,(6):15-19.
[12] CHIN-CHEN CHANG, CHIH-YANG LIN, YI-HSUAN FAN. Lossless data hiding for color images based on block truncation coding [J]. Soft Computing, Springer Berlin, 2008: 8-11.
[13] YANG ZEQING, LIU LIBING, TAN ZHIHONG. Application of Adaptive Genetic Algorithm in flexible inspection path planning [C]. IEEE control conference, 2008: 75-80.
[14]王小平,曹立明.遗传算法:理论、应用与软件实现[M].西安:西安交通大学出版社, 2002.
[15]金晶,苏勇.一种改进的自适应遗传算法.计算机工程与应用[J]. 2005,18:64-69.
[16]申晓宁,胡维礼.一种多目标优化合作型协同进化算法[J].计算机仿真, 2007,24(2):157-161.
[17]牛向阳,倪前月,高成修.基于遗传算法和模拟退火算法的混合算法[J].昆明理工大学学报, 2008,33(2):25-28.
[18]钟宁,何遵文,匡镜明.基于遗传算法的图像水印优化嵌入技术研究[J].兵工学报, 2008,29(9):1054-1058.
[19]徐启玉,梅亚东.遗传模拟退火和小生境遗传算法在水库优化调度中的比较[J].水电自动化与大坝监测, 2008,32(4):1-4.
[20]何江萍,马彦.方块截短编码中同步消除噪声干扰的新算法[J].计算机工程与设计. 2008, 29(20):5256-5259.
[21]杨华芬.一种改进的自适应遗传算法[J].云南民族大学学报, 2009,18(3):264-267.
[22]赖鑫生,冷明伟.变异区间自适应调整的遗传算法[J].计算机应用, 2009,29(6):1566-1568.
[23]帅训波,马书南,欧阳永林.一种基于矩阵遗传算子的优化组合遗传算法[J].小型微型计算机系统, 2009,5(5):951-954.
[24]雷亮,汪同庆,彭军等.改进的自适应遗传算法应用研究[J].计算机科学, 2009,36(6):203-247.
[25]李良敏,温广瑞.遗传算法中遗传操作的改进策略[J].计算机应用与软件,2009,26(6):27-29.
[26]贺巧龙,李东亮.基于遗传算法的函数优化问题研究[J].软件导刊, 2009,6(29):71-72.
[27]李光布,李景辉.遗传算法的分析及其改进[J].计算机仿真, 2009,26(7):228-231.
[28]李钊,古辉.基于遗传算法进化的数字图像处理[J].中国新技术新产品, 2010,2(9):7-8.
[29] JOHNSON J.M., RABMAT-SAMII. Genetic algorithm optimization for aerospace electromagnetic design and analysis [C]. IEEE, Aerospace Applications Conference, 2002: 87-102.
[30] SKOLPADUNGKET, P. DAHAL. Portfolio optimization using multi-objective genetic algorithms [J]. Evolutionary Computation, 2007, 516-523.
[31] ZHAO RUIMING, QIAN DONGPING. Application of Genetic Algorithm in the Optimization of Water Pollution Control Scheme [J]. Intelligent Information Technology Application, 2008:189-191.
[32] TAISHAN YAN, YONG-QING TAO, DUWU CUI. Research on handwritten numeral recognition method based on improved genetic algorithm and neural network [J]. Wavelet Analysis and Pattern Recognition, 2008: 1271-1276.
[33] KAUR, D. MURUGAPPAN. Performance enhancement in solving Traveling Salesman Problem using hybrid genetic algorithm [J]. Fuzzy Information Processing Society, 2008, 1-6.
[34] ABDERRAHIM, A. TALBI. Hybridization of Genetic and Quantum Algorithm for gene selection and classification of Micro-array data [J]. Parallel & Distributed Processing, 2009: 1-8.
[35] HEGEN XIONG, KAI XIONG, QIUHUA TANG. A Novel Variable-Boundary-Coded Quantum Genetic Algorithm for Function Optimization [C]. IEEE International Conference on Dependable, Autonomic and Secure Computing, 2010: 279-285.
[36] JIE YAO KHARMA, GROGONO N., Bi-Objective Multi-population GeneticAlgorithm for Multimodal Function Optimization [J]. Evolutionary Computation, 2010: 80-102.
[37]徐瑛,任雪梅.基于MATLAB的遗传算法工具箱[C].自动化理论、技术与应用,中国科学技术大学出版社. 2003:445-452.
[38]陈玉萍,须文波.基于遗传算法的图像压缩[J].计算机应用研究,2007,(6):167-169.
[39]朱灿,梁昔明.一种多精英保存策略的遗传算法[J].计算机应用,2008,28(4):939-941.
[40]周洪伟.遗传算法“早熟”现象和改进策略研究[D].解放军信息工程大学硕士学位论文, 2004:15-30.
[41]明亮.遗传算法模式理论及收敛理论[D].西安电子科技大学博士学位论文, 2006,21-24.
[42]朱成娟.遗传算法的改进及其若干应用[D].燕山大学硕士学位论文, 2006:21-22.
[43] SHEN-CHUAN TAI, WEN-JAN CHEN, PO-JEN CHENG. Genetic algorithm for single bitmap absolute moment block truncation coding of color images [J]. Institute of Electrical Engineering, 1998: 2483-2489.
[44] E. J. DELP AND O. R. MITCHELL. Image compression using block truncation coding [J], IEEE Trans. Commune, 1997(27): 1335-1342.
[45] HOU YOUNG-CHANG, TU, SHU-FEN. Chang Ya-Hui. Block Truncation Coding by Using Genetic Algorithm [J].IEEE Malta, 2008:1273-1278.
[46]雷英杰,张善文,李续武等. MATLAB遗传算法工具箱及应用[M].西安电子科技大学出版社, 2009:23-24.
[47] MENNON A, K MEHROTRA, CK MOHAN et al. Characterization of a class of sigmoid functions with applications to neural networks [J]. Neural Networks, 1996, 9: 819-835.
[48]孙明华,崔海涛等.基于精英保留遗传算法的连续结构多约束拓扑优化[J].航空动力学报, 2006,21(4):732-737.
[49] KAI-KUANG MA, RAJALA S.A.. New properties of absolute moment blocktruncation coding [J]. IEEE Signal Processing Society, 2002, 2(2): 34-36.
[50] DUNWEI GONG, GUANGSONG GUO, LILU. Adaptive interactive genetic algorithms with individual interval fitness [J]. Progress in Natural Science, 2008: 359-365.
[51] QINGLI, WEN-HAO HE, HAN-HONG JIANG. A Study on Image Segmentation by an Improved Adaptive Algorithm [C]. International Conference on Machine Learning and Cybernetics, IEEE, 2007:1570-1573.
[52]阎妍.一种新的自适应遗传算法[D].哈尔滨工程大学硕士学位论文, 2007:23-29.
[53] TAI S. C., LIN Y. C., LIN J. F.. Single bit-map block truncation coding of color images using a Hopfield neural network. Inf. Sci.1997, 103(1-4): 211-228.
[54] WU Y., COLL D. C.. Single bit-map block truncation coding of color images [J]. IEEE J. Sel. Areas Commun. 1992, 10(5): 952-959.
[55] HIN-CHEN CHANG, YI-HUI CHEN. Chia-Chen Lin. A data embedding scheme for color images based on genetic algorithm and absolute moment block truncation coding [J]. Soft Computing, Springer Berlin, 2009: 321-331.
[56] XU ZHENG-JUN, TANG SHUO. UAV Path Planning Based on Adaptive Genetic Algorithm [J]. Journal of System Simulation, 2008, 20(19): 5411-5418.
[57]李敏强,寇纪松.遗传算法的基本理论与应用[M].科学出版社, 2002:1-80.
[58]吴秋玲.改进的遗传算法及其在CDMA基站优化选址中的应用[D].河海大学硕士学位论文, 2006:40-50.
[59]陈华,叶东.遗传算法的数字图像相关搜索法[J].光学精密工程, 2007, 15(10):1633-1637.
[60]张怀柱,向长波.改进的遗传算法在实时图像分割中的应用[J].光学精密工程, 2008,16(2):333-337.
[61] FRIDRICH J., GOLJAN M., DU R.. Lossless data embedding-new paradigm in digital watermarking, Special Issue on Emerging Applications of Multimedia Data Hiding [J]. 2002(2): 185-196.
[62] CHANG C. C., WU M. N.. A color image progressive transmission method by common bit map block truncation coding approach [C]. Proceedings of the International Conference on Communication Technology, Beijing, 2003: 1774-1778.
[63] YU Y. H., CHANG C. C., HU Y. C.. Hiding secret data in images via predictive coding [J]. Pattern Recognition, 2005, 38(5): 691-705.