PSO-GA Based Optimized Feature Selection Using Facial and Clothing Information for Gender Classification

 

M. Nazir *¹, A. Majid-Mirza¹'², S. Ali-Khan ³

 

¹ Department of Computer Science, National University of Computer & Emerging sciences, Islamabad, Pakistan. *Muhammad.nazir@nu.edu.pk

² College of Computer & Information Sciences, King Saud University, Riyadh, Kingdom of Saudi Arabia. ammirza@ksu.edu.sa

³ Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, Pakistan. Sajidalibn@gmail.com

 

Abstract

Gender classification is a fundamental face analysis task. In previous studies, the focus of most researchers has been on face images acquired under controlled conditions. Real-world face images contain different illumination effects and variations in facial expressions and poses, all together make gender classification a more challenging task. In this paper, we propose an efficient gender classification technique for real-world face images (Labeled faces in the Wild). In this work, we extracted facial local features using local binary pattern (LBP) and then, we fuse these features with clothing features, which enhance the classification accuracy rate remarkably. In the following step, particle swarm optimization (PSO) and genetic algorithms (GA) are combined to select the most important features' set which more clearly represent the gender and thus, the data size dimension is reduced. Optimized features are then passed to support vector machine (SVM) and thus, classification accuracy rate of 98.3% is obtained. Experiments are performed on real-world face image database.

Keywords: gender classification, real-world face images, particle swarm optimization, genetic algorithm, local binary pattern, features fusion.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

[1] L. Ramírez-Valdez and R. Hasimoto-Beltran, "3D facial expression synthesis and its application to face recognition systems," Journal of Applied Research and Technology, vol. 7, no. 3, pp. 323-339, 2009.         [ Links ]

[2] G. Aguilar-Torres et al., "Fingerprint recognition using local features and Hu moments," Journal of Applied Research and Technology, vol. 10, no. 5, pp. 745-754, 2012.         [ Links ]

[3] B. Golomb and D. Lawrence, "Sexnet: A neural network identifies sex from human faces," Proceeding of the Advance in neural information processing systems, 2009, pp. 323-339.         [ Links ]

[4] R. Brunelli and T. Poggio, "HyberBF networks for gender classification," Proceeding of the DARPA image understanding workshop, 1992, pp. 311-314.         [ Links ]

[5] Z. Sun et al., "Neural network based gender classification using genetic algorithm for Eigen-feature selection," Proceeding of the EEE International conference on neural networks, 2002, pp. 2433-2438.         [ Links ]

[6] A. Jain et al., "Gender classification using frontal facial images," Proceeding of the IEEE international conference on pattern Recognition, 2008, pp. 1-4.         [ Links ]

[7] N. Sun et al., "Gender classification based on boosting local binary pattern," Proceedings of the Third international conference on Advances in Neural Networks, 2006, pp. 194-201.         [ Links ]

[8] S. Baluja and H. Rowley, "Boosting sex identification performance," International Journal of computer vision, vol. 71, no. 1, pp. 572-577, 1990.         [ Links ]

[9] M. Nazir et al., "Feature selection for efficient gender classification," Proceeding of the 11th WSEAS International conference, 2010, pp. 70-75.         [ Links ]

[10] S.A Khan et al., "Efficient gender classification methodology using DWT and PCA," Proceeding of the 14th IEEE international Multi-topic conference, 2011, pp. 155-158.         [ Links ]

[11] G. Shakhnarovich et al., "A unified learning framework for real time face detection and classification," Proceeding of the IEEE International Conference on Automatic Face & Gesture Recognition, 2002, pp. 14-21.         [ Links ]

[12] W. Gao and H. Ai, "Face gender classification on consumer images in a multiethnic environment," Proceedings of the International Conference on Biometrics, 2009, pp. 169-178.         [ Links ]

[13] N. Kumar et al., "A search engine for large collections of images with faces," Proceeding of the European Conf. on Computer Vision, 2009, pp. 340-353.         [ Links ]

[14] L. Wolf et al., "Similarity scores based on background samples," Proceeding of the Asian Conf. on Computer Vision, 2010, pp. 88-97.         [ Links ]

[15] T. Cootes et al., "Active shape models-their training and application," Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, 1995.         [ Links ]

[16] H. Lian and B. Lu, "Multi-view gender classification using multi-resolution local binary patterns and support vector machines," Proceedings of the Third international conference on Advances in Neural Networks, 2006, pp. 202-209.         [ Links ]

[17] J. Holand, "Adaptation in Nature and Artificial Systems", In MIT Press, 1992.         [ Links ]

[18] J. Kennedy and R. Eberhart, "Particle Swarm Optimization," Proceeding of the IEEE International conference on neural networks, 1995, pp. 1942-1948.         [ Links ]

[19] T. Cover and P. Hart, "Nearest neighbor pattern classification," Proc. IEEE Trans. Information Theory, vol. 11, pp. 21-27, 1967.         [ Links ]

[20] V. Vapnik, "The nature of statistical learning theory," Proceeding of the Springer conference, 1995.         [ Links ]

[21] G. Huang, "Labeled faces in the wild: A database for studying face recognition in unconstrained environments", Tech. Rep. 07-49, University of Massachusetts, Amherst, 2007.         [ Links ]

[22] C. Shan, "Learning local binary pattern for gender classification on real-world face images," Pattern Recognition Letter, vol. 33, no. 4, pp. 431-437, 2011.         [ Links ]