The International Arab Journal of Information Technology (IAJIT)


A Novel Age Classification Method Using Morph- Based Models

Automatic facial age classification and estimation is an interesting and challenging problem, and has many real world applications. The performances of the classification methods may differ depending on the selected training samples. Also using large amount of training samples makes the classification systems more complex and time consuming. In this paper, a novel and a simple age classification method using morph-based age models is presented. The age models representing the common characteristics of age groups are produced using image morphing method. Then age related facial features are extracted with Local Binary Patterns. In the classification phase, ensemble of distance metrics is used to determine the closeness of the test sample to age groups. Then, the results of these metrics are combined with Borda Count voting method to improve the classification performance. Experimental results using the Face and Gesture Recognition Research Network (FGNET) and Park Aging Mind Laboratory (PAL) aging databases show that the proposed method achieves better age classification accuracy when compared to some of the previous methods.

[1] Aeminov V., Panteleev I., and Selivanov N., Criminalistics, Progress Publishers, 1989.

[2] Albert M., Ricanek K., and Patterson E., “A Review of the Literature on the Aging Adult Skull and Face: Implications for Forensic Science Research and Applications,” Forensic Science International, vol. 172, no. 1, pp. 1-9, 2007.

[3] Chen Y., Han M., Song K., and Ho Y., “Image- Based Age-Group Classification Design Using Facial Features,” in Proceedings of International Conference on System Science and Engineering, Taipei, pp. 548-552, 2010.

[4] Dehshibi M. and Bastanfard A., “A New Algorithm for Age Recognition from Facial Images,” Signal Processing, vol. 90, no. 8, pp. 2431-2444, 2010.

[5] Erikson E., Identity, Youth and Crisis, Norton Company, 1968.

[6] Hayashi J., Yasumoto M., Ito H., Niwa Y., and Koshimizu H., “Age and Gender Estimation from Facial Image Processing,” in Proceedings of the 41st SICE Annual Conference, Osaka, pp. 13-18, 2002.

[7] Higashi A., Yasui T., Fukumizu Y., and Yamauchi H., “Local Gabor Directional Pattern Histogram Sequence for Age and Gender Classification,” in Proceedings of IEEE Statistical Signal Processing Workshop, Nice, pp. 505-508, 2011.

[8] Horng W., Lee C., and Chen C., “Classification of Age Groups Based on Facial Features,” Tamkang Journal of Science and Engineering, vol. 4, no. 3, pp. 183-192, 2001.

[9] Kalansuriya T. and Dharmaratne A., “Facial Image Classification Based on Age and Gender,” in Proceedings of International Conference on Advances in ICT for Emerging Regions, Colombo, pp. 44-50, 2013.

[10] Karungaru S., Fukumi M., and Akamatsu N., “Morphing Human Faces: Automatic Control Points Selection and Color Transition,” in Proceedings of World Academy of Science, A Novel Age Classification Method Using Morph-Based Models 685 Engineering and Technology, vol. 1, pp. 224- 227, 2004.

[11] Kohli S., Prakash S., and Gupta P., “Hierarchical Age Estimation with Dissimilarity-Based Classification,” Neurocomputing, vol. 120, pp. 164-176, 2013.

[12] Kwon Y. and Lobo N., “Age Classification from Facial Images,” Computer Vision and Image Understanding, vol. 74, no. 1, pp. 1-21, 1999.

[13] Li W., Su H., Pan F., Gao Q. and Guo S., “Facial Age Classification Based on Weighted Decision Fusion,” in Proceedings of the 33rd Chinese Control Conference, pp. 4870-4874, 2014.

[14] Liu K., Yan S., and Kuo C., “Age Estimation via Grouping and Decision Fusion,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 11, pp. 2408-2423, 2015.

[15] Liu L., Liu J., and Cheng J., “Age-Group Classification of Facial Images,” in Proceedings of 11th International Conference on Machine Learning and Applications, Boca Raton, pp. 693- 696, 2012.

[16] Minear M. and Park D., “A Lifespan Database of Adult Stimuli,” Behavior Research Methods, Instruments and Computers, vol. 36, no. 4, pp. 630-633, 2004.

[17] Murtaza M., Sharif M., Raza M., and Shah J., “Analysis of Face Recognition Under Varying Facial Expressions: A Survey,” The International Arab Journal of Information Technology, vol. 10, no. 4, pp. 378-388, 2013.

[18] Nguyen D., Cho S., Shin K., Bang J., and Park K., “Comparative Study of Human Age Estimation with or without Preclassification of Gender and Facial Expression,” The Scientific World Journal, 2014.

[19] Ojala T., Pietikainen M., and Maenpaa T., “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 971-987, 2002.

[20] Parramon J., How to Draw Heads and Portraits, Watson-Guptill Publications, 1989.

[21] Ren H. and Li Z., “Age Estimation Based on Complexity-Aware Features,” in Proceedings of 12th Asian Conference on Computer Vision, Singapore, pp. 115-128, 2015.

[22] Sai P., Wang J., and Teoh E., “Facial Age Range Estimation with Extreme Learning Machines,” Neurocomputing, vol. 149, pp. 364-372, 2015.

[23] Tonchev K., Paliy I., Boumbarov O., and Sokolov S., “Human Age-Group Classification of Facial Images with Subspace Projection and Support Vector Machines,” in Proceedings IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Prague, pp. 439- 443, 2011.

[24] Txia J. and Huang C., “Age Estimation using AAM and Local Facial Features,” in Proceedings of IEEE 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Kyoto, pp. 885-888, 2009. Asuman Günay Yılmaz received her BSc., MSc. and Ph.D. Degrees from Department of Computer Engineering, Karadeniz Technical University, Trabzon, Turkey in 2000, 2003 and 2015 respectively. Currently, she is a Lecturer in Trabzon Vocational School, Karadeniz Technical University, Trabzon, Turkey. Her research interests include biometric security and machine learning. Vasif Nabiyev received BSc. and MSc. degrees in the Faculty of Computer Engineering and Automation from St. Petersburg Electro Technical University in 1985, and a Ph.D. degree in the Department of Computer Science from Moscow Technical University in 1990. Currently he is a Professor in Department of Computer Engineering, Karadeniz Technical University, Trabzon, Turkey. His research interests are artificial intelligence, biometry, security, image processing, operational research, combinatorial algorithms. He is author of textbooks titled “Artificial Intelligence: Problems, Methods and Algorithms”, “Algorithms: From Theory to Applications”.