Optimized features selection for gender classi cation using optimization algorithms

Optimized features selection for gender classi cation using optimization algorithms

Optimized feature selection is an important task in gender classi cation. The optimized features not only reduce the dimensions, but also reduce the error rate. In this paper, we have proposed a technique for the extraction of facial features using both appearance-based and geometric-based feature extraction methods. The extracted features are then optimized using particle swarm optimization (PSO) and the bee algorithm. The geometric-based features are optimized by PSO with ensemble classi er optimization by the genetic algorithm. Using this approach, we have obtained promising results in terms of the classi cation error rate and computation time minimization. Moreover, our optimized feature-based method is robust to illumination, noise, and occlusion changes.

___

  • [1] A. Burton, V. Bruce, N. Dentch, What's the dierence between men and women? Evidence from facial measurements", Perception, Vol. 22, pp. 153-176, 1993.
  • [2] J. Fellous, Gender discrimination and predication on the basis of facial metric information", Vision Research, Vol. 37, pp. 1961-1973, 1997.
  • [3] B. Li, X.C. Lian, B.L. Lu, Gender classi cation by combining clothing, hair and facial component classi ers", Neuro Computing, Vol. 76, pp. 18-27, 2011.
  • [4] B. Golomb, D. Lawrence, T. Sejnowski, SexNet: a neural network identi es sex from human faces", Advances in Neural Information Processing Systems, Vol. 3, pp. 572-577, 1991.
  • [5] M. Nazir, M. Ishtaiq, A. Batool, A. Jaar, M. Mirza, Feature selection for ecient gender classi cation", Proceedings of the 11th WSEAS International Conference, pp. 70-75, 2010.
  • [6] B. Somayeh Mousavi, A. Hirad, Automatic gender classi cation using neuro fuzzy system", Indian Journal of Science and Technology, Vol. 4, pp. 1198-1201, 2011.
  • [7] P. Rai, P. Khanna, Gender classi cation using Radon and wavelet transform", Proceedings of the IEEE International Conference on Industrial and Information System, pp. 448-451, 2010.
  • [8] S. Ravi, S. Wilson, Face detection with facial features and gender classi cation based on support vector machine", Proceedings of IEEE International Conference on Computational Intelligence and Computing Research, pp. 125- 130, 2010.
  • [9] A. Shobeirinejad, Y. Gao, Gender classi cation using interlaced derivative pattern", Proceedings of IEEE international Conference on Pattern Recognition, pp. 1509-1512, 2010.
  • [10] Z. Xu, L. Lu, P. Shi, A hybrid approach to gender classi cation from face images", Proceedings of IEEE International Conference on Pattern Recognition, pp. 1-4, 2008.
  • [11] P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features", Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 511-518, 2001.
  • [12] Y. Su, S. Shan, X. Chen, W. Gao, Hierarchical ensemble of global and local classi ers for face recognition", Proceedings of International Conference on Computer Vision, pp. 1-8, 2007.
  • [13] E. Brown, D. Perrett, What gives a face its gender?", Perception, Vol. 22, pp. 829-840, 1993.
  • [14] T. Cootes, C. Taylor, D. Cooper, J. Graham, Active shape models-their training and application", Computer Vision and Image Understanding, Vol. 61, pp. 38-59, 1995.
  • [15] X. Lian, B. Lu, Gender classi cation by combining facial and hair information", Proceedings of Advances in Neuro-Information Processing, pp. 647-654, 2009.
  • [16] J. Kennedy, R. Eberhart, Particle swarm optimization", Proceedings of IEEE International conference on neural networks, pp. 1942-1948, 1995.
  • [17] J. Kennedy, R.C. Eberhart, A discrete binary version of the particle swarm algorithm", Proceedings of the IEEE International Conference on System, Man and Cybernetics, pp. 4104-4108, 1997.
  • [18] D.T. Pham, A. Ghanbarzadeh, E. Koc, S. Otri, S. Rahim, M. Zaidi, The bees algorithm - a novel tool for complex optimization problems", Proceedings of Virtual International Conference on Intelligent Production Machines and Systems, pp. 254-461, 2006.
  • [19] T.Z. Zhao, Y.H. Li, J.J. Lu, Y.F. Zhang, Classi er ensemble based on bi-coded chromosome genetic algorithm for automatic image annotation", Proceedings of the 7th Conference on Machine Learning and Cybernetics, pp. 12-15, 2008.
  • [20] B. Gabrysa, D. Ruta, Genetic algorithms in classi er fusion", Applied Soft Computing, Application of Soft Computing in Information & Communication Technology, Vol. 6, pp. 337-347, 2006.
  • [21] L.I. Kuncheva, Combining Pattern Classi ers: Methods and Algorithms, New York, Wiley, 2004.
  • [22] Z. Sun, G. Bebis, X. Yuan, S.J. Louis, Genetic feature subset selection for gender classi cation: a comparison study", Proceedings of the IEEE Workshop on Applications of Computer Vision, pp. 165-170, 2002.
  • [23] B. Gabrysa, D. Ruta, Genetic algorithms in classi er fusion", Applied Soft Computing, Application of Soft Computing in Information & Communication Technology, Vol. 6, pp. 337-347, 2006.
  • [24] P. Phillips, H. Wechsler, J. Huang, P. Rauss, The FERET database and evaluation procedure for face-recognition algorithms", Image and Vision Computing, Vol. 16, pp. 295-306, 1998.
  • [25] S. Ali Khan, M. Nazir, U. Asghar, Ecient gender classi cation using interlaced derivative pattern (IDP) and principal component analysis", Proceedings of the 9th International Conference on Frontiers of Information Technology, pp. 270-274, 2011.
  • [26] C. Shan, Learning local binary pattern for gender classi cation on real-world face images", Pattern Recognition Letter, Vol. 33, pp. 421-437, 2011.