Use of learning methods for gender and age classification based on front shot face images

Document Type : Research Paper


Department of Computer Science, College of Science, University of Baghdad, Baghdad, Iraq


Facial system estimation is a mature and in-depth research technique in age and gender. Estimation accuracy is an important indicator for evaluating algorithms. By using deep learning-based learning (DL) and machine learning, this work provides a robust approach to estimating the type and age of different external environment changes based on two different algorithms, comparing the results, and analyzing the performance of the two algorithms. The algorithm was evaluated using a data set that is considered the basis in this area of the face estimation system, namely (IMDB-WIKI) an image. The basis of the work depends on the external appearance and the front section. The results obtained: DL(Effacint-B3) AGE Accuracy=0.99 Gender Accuracy=0.97 ML(SVM) AGE Accuracy=0.87 Gender Accuracy=0.97.


[1] R. Abinaya, L.P. Maguluri, S. Narayana and M. Syamala, A novel biometric approach for facial image recognition using deep learning techniques, Int. J. Adv. Trends Comput. Sci. Eng. 9 (2020), no. 5, 8874–8879.
[2] J.M. Al-Tuwaijari and S.A. Shaker, Face detection system based Viola-Jones algorithm, 6th Int. Engin. Conf. ”Sustainable Technology and Development” (IEC), 2020, pp. 211–215.
[3] H.O. Aworinde, A.O. Afolabi, A.S. Falohun and O.T. Adedeji, Performance evaluation of feature extraction techniques in multi-layer based fingerprint ethnicity recognition system, Asian J. Res. Comput. Sci. 3 (2019), no. 1, 1–9.
[4] P. Giammatteo, F.V. Fiordigigli, L. Pomante, T. Di Mascio and F. Caruso, Age gender classifier for edge computing, 8th Mediterr. Conf. Embed. Comput. MECO 2019 - Proc., 2019, pp. 6–10.
[5] S. Gollapudi, Deep learning for computer vision, In Learn computer vision using OpenCV, Apress, Berkeley, CA, 2019.
[6] S.A. Grainger, J.D. Henry, L.H. Phillips, E.J. Vanman and R. Allen, Age deficits in facial affect recognition: The influence of dynamic cues, J. Gerontol. - Ser. B Psychol. Sci. Soc. Sci. 72 (2017), no. 4, 622–632.
[7] G. Guo and N. Zhang, A survey on deep learning based face recognition, Comput. Vis. Image Underst. 189 (2019), p. 102805.
[8] M. Hassaballah and S. Aly, Face recognition: Challenges, achievements and future directions, IET Comput. Vis. 9 (2015), no. 4, 614–626.
[9] B. Hassan, E. Izquierdo and T. Piatrik, Soft biometrics: A survey benchmark analysis, open challenges and recommendations, Multimedia Tools and Applications, (2021).
[10] C.Y. Hsu, L.E. Lin and C.H. Lin, Age and gender recognition with random occluded data augmentation on facial images, Multimed. Tools Appl. 80 (2021), no. 8, 11631–11653.
[11] K. Ito, H. Kawai, T. Okano, and T. Aoki, Age and gender prediction from face images using convolutional neural network, Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. APSIPA ASC 2018 - Proc. IEEE, 2018, pp. 7–11.
[12] A. Jain and V. Kanhangad, Gender classification in smartphones using gait information, Expert Syst. Appl. 93 (2017), 257–266.
[13] A.K. Jain, A. Ross and S. Prabhakar, An introduction to biometric recognition, IEEE Trans. Circuits Syst. Video Technol. 14 (2004), no. 1, 4–20.
[14] F. Karamizadeh, Face recognition by implying illumination techniques – A review paper, J. Sci. Engin. 6 (2015), no. 1, 1–7.
[15] J.A. Lee and K.C. Kwak, Personal identification using an ensemble approach of 1D-LSTM and 2D-CNN with electrocardiogram signals, Appl. Sci. 12 (2022), no. 5.
[16] G. Levi and T. Hassner, Age and gender classification using convolutional neural networks, Proc. IEEE Conf. Computer Vision pPattern Recogn. Workshops, 2015, pp. 34–42.
[17] C.H. Nga, K.-T. Nguyen, N.C. Tran and J.-C. Wang, Transfer learning for gender and age prediction, IEEE Int. Conf. Consum. Electron. (ICCE-Taiwan), IEEE, Taiwan, 2020, pp. 1–2.
[18] I. Siddiqi, C. Djeddi, A. Raza and L. Souici-Meslati, Automatic analysis of handwriting for gender classification, Pattern Anal. Appl. 18 (2015), no. 4, 887–899.
[19] P. Terh¨orst, D. F¨ahrmann, N. Damer and F. Kirchbuchner, On soft-biometric information stored in biometric face embeddings, IEEE Trans. Biomet. Behav. Identity Sci. 3 (2021), no. 4, 519–534.
[20] Y. Xu, Z. Li, J. Yang and D. Zhang, A survey of dictionary learning algorithms for face recognition, IEEE Access, 5 (2017), 8502–8514.
[21] A. Zhuchkov, Analyzing the effectiveness of image augmentations for face recognition from limited data, Int. Conf. Nonlinearity Inf. Robotics (NIR), IEEE, 2021, pp.1–6.
Volume 14, Issue 3
March 2023
Pages 327-342
  • Receive Date: 07 July 2022
  • Revise Date: 16 August 2022
  • Accept Date: 20 September 2022