遗传算法在人脸识别中的应用
|
摘要
人脸识别是一项极富挑战性的课题。传统方法需要极其繁多的前期工作和识别阶段的诸多限制，因而不论从理论上还是在实际应用中都极为困难。本文把遗传算法应用于人脸识别的分割、定位和角度矫正三个环节，并建立了相应的数学模型。
具体做法是用二进制数串作为染色体，表示某个分割阈值。遗传算法中的选择算子采用“精英选择”策略，即每一代种群都将上一代中最优染色体保留下来；杂交阶段，从父代和子代染色体中选取最优的两条染色体作为杂交后代；变异算子与传统的取反变异不同，需两条染色体参与，通过逻辑运算，使得种群中同一基因位上的基因不会出现全0或全1的情况，从而最大限度地避免了早熟收敛。本文还添加了一种“倒位算子”，即在一条染色体上随机选择两点构成一个子串，首尾倒置形成新子串替代原子串在个体中的位置。
本文对于提出的遗传算法，给出了遗传算子的数学描述，建立了精确的马尔可夫链模型，并在此基础上给出了遗传算法全局收敛性的证明。
通过仿真实验表明，本文提出的遗传算法与标准遗传算法相比，收敛速度和得到的最优值都有了极大的提高，使人脸识别各个环节避免了繁重的工作，提高了识别的质量和速度。
Human face recognition is a challenging issue. The traditional methods of face recognition need most heavy prepare works and many confinements in the real face recognition phase. So in this article, GA is applied in the principal steps of face recognition, including segmenting face, location of face and curing of face angle, simultaneously, the mathematical model is built.
The concrete means is to design chromosome by a binary chain comprised by 8 genes, which represent a segmenting threshold that is corresponding to a gray. Selection operator is designed to be 'elite selection'; in crossover phase, 'preferred selection' is presented; differed from traditional methods, in the course of mutation, at least both a '0' and a T exist simultaneously on the same gene position in the current population and that avoid premature mostly. Inversion operator is presented to generate a new binary chain by randomly selecting two gene positions and inversing the chain between the two positions in a chromosome.
According to the genetic algorithm presented in this article, a
mathematical description is presented and an accurate markov model is built. Based on this, the presented algorithm in this article is proved to be global convergent.
The emulation illustrates that alongside the standard genetic algorithm, the convergence velocity and optimal solution of the presented genetic algorithm is enhanced mostly. Heavy works in steps of face recognition is so reduced that the effect and rate of face recognition is improved mostly.
具体做法是用二进制数串作为染色体，表示某个分割阈值。遗传算法中的选择算子采用“精英选择”策略，即每一代种群都将上一代中最优染色体保留下来；杂交阶段，从父代和子代染色体中选取最优的两条染色体作为杂交后代；变异算子与传统的取反变异不同，需两条染色体参与，通过逻辑运算，使得种群中同一基因位上的基因不会出现全0或全1的情况，从而最大限度地避免了早熟收敛。本文还添加了一种“倒位算子”，即在一条染色体上随机选择两点构成一个子串，首尾倒置形成新子串替代原子串在个体中的位置。
本文对于提出的遗传算法，给出了遗传算子的数学描述，建立了精确的马尔可夫链模型，并在此基础上给出了遗传算法全局收敛性的证明。
通过仿真实验表明，本文提出的遗传算法与标准遗传算法相比，收敛速度和得到的最优值都有了极大的提高，使人脸识别各个环节避免了繁重的工作，提高了识别的质量和速度。
Human face recognition is a challenging issue. The traditional methods of face recognition need most heavy prepare works and many confinements in the real face recognition phase. So in this article, GA is applied in the principal steps of face recognition, including segmenting face, location of face and curing of face angle, simultaneously, the mathematical model is built.
The concrete means is to design chromosome by a binary chain comprised by 8 genes, which represent a segmenting threshold that is corresponding to a gray. Selection operator is designed to be 'elite selection'; in crossover phase, 'preferred selection' is presented; differed from traditional methods, in the course of mutation, at least both a '0' and a T exist simultaneously on the same gene position in the current population and that avoid premature mostly. Inversion operator is presented to generate a new binary chain by randomly selecting two gene positions and inversing the chain between the two positions in a chromosome.
According to the genetic algorithm presented in this article, a
mathematical description is presented and an accurate markov model is built. Based on this, the presented algorithm in this article is proved to be global convergent.
The emulation illustrates that alongside the standard genetic algorithm, the convergence velocity and optimal solution of the presented genetic algorithm is enhanced mostly. Heavy works in steps of face recognition is so reduced that the effect and rate of face recognition is improved mostly.
引文
1 Bledsoe W W. The model method in facial recognition[M]. Panoramic Research Inc, Palo Alto, CA, 1966.
2 Kannde T. Picture processing system by computer complex and recognition of human faces[R]. Dept of Information Science, Kyoto University, 1973.
3 Samal A, Iyengar P A. Automatic recognition and analysis of human faces and facial expressions: A survey[J]. Pattern Recognition, 1992,25(1): 65～77.
4 Brunelli R, Poggio T. Face recognition: features versus templates[J]. IEEE Transactions on PAMI, 1993,15(10): 1042～1052.
5 Birchfield S. An elliptical head tracker[A]. 31st Asilomar conference on Signals, Systems and Computers[C]. 1997. 1710～1714.
6 Tang C Y, Chen Z, Huang Y P. Automatic detection and tracking of human heads using an active stereo vision system[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2000,14(2): 137～166.
7 Yuille A L. Deformable templates for face recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1): 59～70
8 Turk M, Pentland A P. eigenfaces for recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1): 71～86.
9 Peng H, Zhang D. Dual Eigenspace method for human face recognition[J]. Electronics Letters, 1997,33(4): 283～284.
10 Swetes D L, Weng J. using discriminant eigenfeatures for image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intellegence, 1996,18(8): 831～836.
11 Belhumeur P N, Hespanba J P, Kriegman D J. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997,19(7): 711～720.
12 Luis T, Josep V. Automatic face recognition for video indexing
applications[J]. Pattern Recognition,2002,35(3): 615～625.
13 Albert P, Jordi Vitriu, Felipe Lumbreras er al. Topological principal component analysis for face encoding and recognition[J], Pattern Recognition Letters, 2001,22(6-7): 769～776.
14 Moghaddam B, Wahid W, Pentland A. Beyond eigenfaces: Probabilistic matching for face recognition[A]. Proceedings of the International Conference on Automatic Face and Gesture Recognition[C]. Nara, Japan. 1998.30～35.
15 Hong Z. Algebraic feature extraction from image for recogniton[J]. Pattern Recognition, 1991,24(3): 211～219
16 Nefian A, Hayes M. Hidden Markov models for face recognition[A]. IEEE International Conference on Acoustics, Speech and Signals Processings[C]. Seattle, Washington, 1998,5:2721～2724
17 Valentin D, Abdi H, O'Toole A J, et al. Connectionist models of face processing: A survey[J]. Pattern Recognition, 1994,27(9): 1209～1230
18 Flming M, Cottrell G. Categorization of faces using unsupervised feature extraction[A]. Proceedings of the International Conference on Neural Networks[C]. California Univ Aan Diego, CA, USA, 1990.65～70
19 Intrator N, Reisfeld D, Yeshurun Y. Face recognition by supervised/unsupervised hybrid network[J]. Pattern Recognition Letters,1996,17(1): 67～76
20 Lawrence S, Giles C L, Tsoi A C, et al. Face recognition: A convolutional neural approach[J]. IEEE Transactions on Neural Networks, 1997,8(1): 98～113
21 Lin S H, Hung S Y, Lin L J. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks, 1997,8(1): 114～132
22 Lades M, Vorbrueggen J C, Buhmann J, et al. Distortion in dynamic link architecture[J]. IEEE Transactions on Computers, 1993,42(3): 300～311
23 Wiskott L. Phantom faces for face analysis[J]. Pattern Recognition, 1997,30(6): 837～846
24 Wiskott L, Fellous J M, Kruer N, et al. Face recognition by elastic
bunch graph matching[J]. IEEE Transitions on Pattern Analysis and Machine Intelligence, 1997,9(7): 775～779
25 W Bledsoe. Mun-machine facial recognition. Panoramic Research Inc, Palo Alto, CA, 1966,Rep PRI: 22.
26 Berto R, Poggio T. Face recognition: Feature versus templatea. IEEE Trans. on PAMI, 1993,15(10): 1042～1052
27 Lanitis A, Taylor C J, Cootes T F. Automatic interpretation and coding of face images using flexible models. IEEE Trans. on PAMI, 1997,19(7)
28 张良杰，毛志宏，李衍达．遗传算法中突变算子的数学分析及改进策略．电子科学学刊．1996，18(6)：590～595．
29 丁承民，张传生，刘贵忠．利用正交试验法优化配置遗传算法控制参数．西安交通大学电子与信息工程学院信息工程研究所研究报告．1996．
30 张金奎，林萌宇，杨传忠，甘兴国，谢科．基于遗传算法的潮流多根求解方法．重庆大学学报(自然科学版)．2000，23(1)：56～59．
31 吴新余，孙力娟．改进交叉方式的遗传算法在求解通信网络优化问题中的应用．通信学报，1997，18(10)：15～21
32 Computer & operation research, 1995, vol 22, no 1.
33 王进，余松煜．基于遗传算法的改进GLA算法．上海交通大学学报，2000，34(7)：970～972
34 Yair E, Zeger K, Gershn A. Competitve learning and soft compeition for. vector quantizer design. IEEE Trans Signal Processing, 1992,40(2): 294～309
35 徐立中，杨锦堂．遗传操作的一般性算子及图像恢复处理．电路与系统学报，1999，4(3)：80～85
2 Kannde T. Picture processing system by computer complex and recognition of human faces[R]. Dept of Information Science, Kyoto University, 1973.
3 Samal A, Iyengar P A. Automatic recognition and analysis of human faces and facial expressions: A survey[J]. Pattern Recognition, 1992,25(1): 65～77.
4 Brunelli R, Poggio T. Face recognition: features versus templates[J]. IEEE Transactions on PAMI, 1993,15(10): 1042～1052.
5 Birchfield S. An elliptical head tracker[A]. 31st Asilomar conference on Signals, Systems and Computers[C]. 1997. 1710～1714.
6 Tang C Y, Chen Z, Huang Y P. Automatic detection and tracking of human heads using an active stereo vision system[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2000,14(2): 137～166.
7 Yuille A L. Deformable templates for face recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1): 59～70
8 Turk M, Pentland A P. eigenfaces for recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1): 71～86.
9 Peng H, Zhang D. Dual Eigenspace method for human face recognition[J]. Electronics Letters, 1997,33(4): 283～284.
10 Swetes D L, Weng J. using discriminant eigenfeatures for image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intellegence, 1996,18(8): 831～836.
11 Belhumeur P N, Hespanba J P, Kriegman D J. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997,19(7): 711～720.
12 Luis T, Josep V. Automatic face recognition for video indexing
applications[J]. Pattern Recognition,2002,35(3): 615～625.
13 Albert P, Jordi Vitriu, Felipe Lumbreras er al. Topological principal component analysis for face encoding and recognition[J], Pattern Recognition Letters, 2001,22(6-7): 769～776.
14 Moghaddam B, Wahid W, Pentland A. Beyond eigenfaces: Probabilistic matching for face recognition[A]. Proceedings of the International Conference on Automatic Face and Gesture Recognition[C]. Nara, Japan. 1998.30～35.
15 Hong Z. Algebraic feature extraction from image for recogniton[J]. Pattern Recognition, 1991,24(3): 211～219
16 Nefian A, Hayes M. Hidden Markov models for face recognition[A]. IEEE International Conference on Acoustics, Speech and Signals Processings[C]. Seattle, Washington, 1998,5:2721～2724
17 Valentin D, Abdi H, O'Toole A J, et al. Connectionist models of face processing: A survey[J]. Pattern Recognition, 1994,27(9): 1209～1230
18 Flming M, Cottrell G. Categorization of faces using unsupervised feature extraction[A]. Proceedings of the International Conference on Neural Networks[C]. California Univ Aan Diego, CA, USA, 1990.65～70
19 Intrator N, Reisfeld D, Yeshurun Y. Face recognition by supervised/unsupervised hybrid network[J]. Pattern Recognition Letters,1996,17(1): 67～76
20 Lawrence S, Giles C L, Tsoi A C, et al. Face recognition: A convolutional neural approach[J]. IEEE Transactions on Neural Networks, 1997,8(1): 98～113
21 Lin S H, Hung S Y, Lin L J. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks, 1997,8(1): 114～132
22 Lades M, Vorbrueggen J C, Buhmann J, et al. Distortion in dynamic link architecture[J]. IEEE Transactions on Computers, 1993,42(3): 300～311
23 Wiskott L. Phantom faces for face analysis[J]. Pattern Recognition, 1997,30(6): 837～846
24 Wiskott L, Fellous J M, Kruer N, et al. Face recognition by elastic
bunch graph matching[J]. IEEE Transitions on Pattern Analysis and Machine Intelligence, 1997,9(7): 775～779
25 W Bledsoe. Mun-machine facial recognition. Panoramic Research Inc, Palo Alto, CA, 1966,Rep PRI: 22.
26 Berto R, Poggio T. Face recognition: Feature versus templatea. IEEE Trans. on PAMI, 1993,15(10): 1042～1052
27 Lanitis A, Taylor C J, Cootes T F. Automatic interpretation and coding of face images using flexible models. IEEE Trans. on PAMI, 1997,19(7)
28 张良杰，毛志宏，李衍达．遗传算法中突变算子的数学分析及改进策略．电子科学学刊．1996，18(6)：590～595．
29 丁承民，张传生，刘贵忠．利用正交试验法优化配置遗传算法控制参数．西安交通大学电子与信息工程学院信息工程研究所研究报告．1996．
30 张金奎，林萌宇，杨传忠，甘兴国，谢科．基于遗传算法的潮流多根求解方法．重庆大学学报(自然科学版)．2000，23(1)：56～59．
31 吴新余，孙力娟．改进交叉方式的遗传算法在求解通信网络优化问题中的应用．通信学报，1997，18(10)：15～21
32 Computer & operation research, 1995, vol 22, no 1.
33 王进，余松煜．基于遗传算法的改进GLA算法．上海交通大学学报，2000，34(7)：970～972
34 Yair E, Zeger K, Gershn A. Competitve learning and soft compeition for. vector quantizer design. IEEE Trans Signal Processing, 1992,40(2): 294～309
35 徐立中，杨锦堂．遗传操作的一般性算子及图像恢复处理．电路与系统学报，1999，4(3)：80～85