基于粒子群优化的条件概率神经网络
Particle Swarm Optimization Based Algorithm for Conditional Probability Neural Network Learning

DOI: 10.12677/AIRR.2016.51002, PP. 13-22

Keywords: 年龄估计，标签分布学习，条件概率神经网络，粒子群优化
Age Estimation, Label Distribution Learning, Conditional Probability Neural Network, Particle Swarm Optimization

Full-Text   Cite this paper   Add to My Lib

Abstract:

条件概率神经网络在进行模式分类时具有独特的优势，然而如何对其进行有效的训练，从而找到最优参数却是一个困难的问题。在考虑条件概率神经网络的结构特点之后，本文提出了一种基于粒子群优化的条件概率神经网络的训练方法。我们将这种基于粒子群优化的条件概率神经网络用于人脸年龄估计，实验结果表明这种网络能够显著地提高识别的准确率。
Conditional probability neural network (CPNN) has special advantage in pattern classification problems. However, how to find the optimal parameters of the CPNN to achieve better perfor-mance is an extraordinary challenge. Considering the structure feature of CPNN, we proposed a new training method based on particle swarm optimization (PSO). This method utilizes PSO to optimize the structure of CPNN and label distributions by introducing Hellinger distance between different label distributions. We applied the improved CPNN on facial age estimation. The experimental results showed that this network could increase recognition accuracy significantly.

References

[1]	Kwon, Y.H. and da Vitoria Lobo, N. (1994) Age Classification from Facial Images. IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition, Seattle, 21-23 Jun 1994, 762-767.
[2]	Hayashi, J., Yasumoto, M., Ito, H. and Koshimizu, H. (2002) Age and Gender Estimation Based on Wrinkle Texture and Color of Facial Images. 16th International Conference on Pattern Recognition, 1, 405-408.
[3]	Lanitis, A., Draganova, C. and Christodoulou, C. (2004) Comparing Different Classifiers for Automatic Age Estimation. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 34, 621-628. http://dx.doi.org/10.1109/TSMCB.2003.817091
[4]	Nakano, M., Yasukata, F. and Fukumi, M. (2004) Age Classification from Face Images Focusing on Edge Information. Knowledge-Based Intelligent Information and Engineering Systems. Springer Berlin Heidelberg.
[5]	Zhou, S.K., Georgescu, B., Zhou, X.S. and Comaniciu, D. (2005) Image Based Regression Using Boosting Method. 10th IEEE International Conference on Computer Vision, 1, 541-548.
[6]	Geng, X., et al. (2006) Learning from Facial Aging Patterns for Automatic Age Estimation. Proceedings of the 14th annual ACM International Conference on Multimedia, ACM. http://dx.doi.org/10.1145/1180639.1180711
[7]	Yin, C. and Geng, X. (2012) Facial Age Estimation by Conditional Probability Neural Network. Pattern Recognition. Springer Berlin Heidelberg, 243-250. http://dx.doi.org/10.1007/978-3-642-33506-8_31
[8]	Hellinger, E. (1909) Neue Begründung der Theorie quadra-tischer Formen von unendlichvielen Ver？nderlichen. Journal für die reine und angewandte Mathematik, 136, 210-271.
[9]	Sarajedini, A., Hecht-Nielsen, R. and Chau, P.M. (1999) Conditional Probability Density Function Estimation with Sigmoidal Neural Networks. IEEE Transactions on Neural Networks, 10, 231-238. http://dx.doi.org/10.1109/72.750544
[10]	Riedmiller, M. and Braun, H. (1993) A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. IEEE International Conference on Neural Networks, 1, 586-591. http://dx.doi.org/10.1109/icnn.1993.298623
[11]	Eberhart, R.C. and Kennedy, J. (1995) A New Optimizer Using Particle Swarm Theory. Proceedings of the 6th International Symposium on Micro Machine and Human Science, Nagoya, 4-6 October 1995, 39-43. http://dx.doi.org/10.1109/MHS.1995.494215
[12]	Lanitis, A., Taylor, C.J. and Cootes, T.F. (2002) Toward Automatic Simulation of Aging Effects on Face Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 442-455. http://dx.doi.org/10.1109/34.993553
[13]	Chang, K.-Y., Chen, C.-S. and Hung, Y.-P. (2011) Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, 20-25 June 2011, 585- 592.
[14]	Geng, X., Zhou, Z.H. and Smith-Miles, K. (2007) Automatic Age Estimation Based on Facial Aging Patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 2234-2240. http://dx.doi.org/10.1109/TPAMI.2007.70733
[15]	Lanitis, A., Taylor, C.J. and Cootes, T.F. (2002) Toward Automatic Simulation of Aging Effects on Face Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 442-455. http://dx.doi.org/10.1109/34.993553
[16]	Lanitis, A., Draganova, C. and Christodoulou, C. (2004) Comparing Different Classifiers for Automatic Age Estimation. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 34, 621-628. http://dx.doi.org/10.1109/TSMCB.2003.817091
[17]	Jang, J.-S.R. (1993) ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics, 23, 665-685. http://dx.doi.org/10.1109/21.256541
[18]	Jiang, M., Ding, Y., Goertzel, B., et al. (2014) Improving Machine Vision via Incorporating Expectation-Maximization into Deep Spatio-Temporal Learning. International Joint Conference on Neural Networks (IJCNN), Beijing, 6-11 July 2014, 1804-1811.
[19]	Jiang, M., Zhou, C. and Chen, S. (2010) Embodied Concept Formation and Reasoning via Neural-Symbolic Integration. Neurocomputing, 74, 113-120. http://dx.doi.org/10.1016/j.neucom.2009.11.052
[20]	Wu, Y., Jiang, M., Huang, Z., et al. (2015) An NP-Complete Fragment of Fibring Logic. Annals of Mathematics and Artificial Intelligence, 75, 391-417. http://dx.doi.org/10.1007/s10472-015-9468-4
[21]	Jiang, M., Yu, Y., Chao, F., et al. (2013) A Connectionist Model for 2-Dimensional Modal Logic. IEEE Symposium on Computational Intelligence for Human-Like Intelligence (CIHLI), Singapore, 16-19 April 2013, 54-59.
[22]	Jiang, M., Yu, Y., Liu, X., et al. (2012) Fuzzy Neural Network Based Dynamic Path Planning. International Conference on Machine Learning and Cybernetics (ICMLC), Xi’an, 15-17 July 2012, 326-330.
[23]	Chao, F., Lee, M.H., Jiang, M., et al. (2014) An Infant Development-Inspired Ap-proach to Robot Hand-Eye Coordination. International Journal of Advanced Robotic Systems, 11. http://dx.doi.org/10.5772/57555
[24]	Chao, F., Chen, F., Shen, Y., et al. (2014) Robotic Free Writing of Chinese Characters via Human-Robot Interactions. International Journal of Humanoid Robotics, 11, 1450007. http://dx.doi.org/10.1142/S0219843614500078
[25]	Jiang, M., Huang, W., Huang, Z. and Yen, G.G. (2015) Integration of Global and Local Metrics for Domain Adaptation Learning via Dimensionality Reduction. IEEE Transactions on Cybernetics, PP, 1-14.

Full-Text