GENDER RECOGNITION THROUGH FACE IMAGES USING CONVOLUTIONAL NEURAL NETWORKS

Main Article Content

Rahul Gautam
Priya Laxmi

Abstract

Gender recognition from facial images is widely used in the field of computer vision for surveillance which is easy for a human but challenging for machines. In computer vision, some factors such as differences in illumination, angle, occlusion, and expressions cause the problem of low accuracy. So, a Convolutional Neural Network (CNN) based transfer learning method is being applied in this work since CNN performs automatic feature extraction and learns complex high-level features in image classification applications. The proposed method efficiently classifies gender classes (male and female) on ‘Adience’: a benchmark face image dataset publicly available on the Kaggle website. This work interrogates seven different pre-trained CNNs used as base networks in the proposed transfer learning method. For the transfer of the pre-acquired knowledge, five different sets of layers (named experiments-1 to 5) have been tested with every model, and their performance is evaluated. Among these, experiment-4 has performed best with all models. However, DenseNet-121 has achieved the highest mean accuracy of 92.83% with a set of layers in experiment-4. We evaluate the performance of the proposed model using five-fold cross-validation, and the final mean accuracy is compared with previous methods in the literature

Article Details

Section

Articles

Author Biography

Rahul Gautam

Sant Longowal Institute of Engineering & Technology,

Longowal, Punjab ,India

References

[1] A. Dantcheva, P. Elia, and A. Ross, “What else does your biometric data reveal? A survey on soft biometrics,” IEEE Trans. Inf. Forensics Secur., vol. 11, no. 3, pp. 441–467, 2016, doi: 10.1109/TIFS.2015.2480381.

[2] A. Bhattacharyya, R. Saini, P. P. Roy, D. P. Dogra, and S. Kar, “Recognizing gender from human facial regions using genetic algorithm,” Soft Comput., vol. 23, no. 17, pp. 8085–8100, Sep. 2019, doi: 10.1007/s00500-018-3446-9.

[3] R. Wason, “Deep learning: Evolution and expansion,” Cogn. Syst. Res., vol. 52, pp. 701–708, 2018, doi: 10.1016/j.cogsys.2018.08.023.

[4] D. Cires and U. Meier, “Multi-column Deep Neural Networks for Image Classification,” pp. 3642–3649, 2012.

[5] S. Ji, W. Xu, M. Yang, and K. Yu, “3D Convolutional neural networks for human action recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 1, pp. 221–231, 2013, doi: 10.1109/TPAMI.2012.59.

[6] S. S. Farfade, M. Saberian, and L. J. Li, “Multi-view face detection using Deep convolutional neural networks,” ICMR 2015 - Proc. 2015 ACM Int. Conf. Multimed. Retr., pp. 643–650, 2015, doi: 10.1145/2671188.2749408.

[7] G. Levi and T. Hassncer, “Age and gender classification using convolutional neural networks,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun. 2015, vol. 928, no. 3, pp. 34–42, doi: 10.1109/CVPRW.2015.7301352.

[8] M. Shaha and M. Pawar, “Transfer Learning for Image Classification,” Proc. 2nd Int. Conf. Electron. Commun. Aerosp. Technol. ICECA 2018, no. Iceca, pp. 656–660, 2018, doi: 10.1109/ICECA.2018.8474802.

[9] T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, 2002, doi: 10.1109/TPAMI.2002.1017623.

[10] H.-C. Lian and B.-L. Lu, “Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machines,” in International Journal of Neural Systems, vol. 17, no. 6, 2006, pp. 202–209.

[11] L. A. Alexandre, “Gender recognition: A multiscale decision fusion approach,” Pattern Recognit. Lett., vol. 31, no. 11, pp. 1422–1427, 2010, doi: 10.1016/j.patrec.2010.02.010.

[12] J. E. Tapia and C. A. Perez, “Gender classification based on fusion of different spatial scale features selected by mutual information from histogram of LBP, intensity, and shape,” IEEE Trans. Inf. Forensics Secur., vol. 8, no. 3, pp. 488–499, 2013, doi: 10.1109/TIFS.2013.2242063.

[13] C. Shan, “Learning local binary patterns for gender classification on real-world face images,” Pattern Recognit. Lett., vol. 33, no. 4, pp. 431–437, 2012, doi: 10.1016/j.patrec.2011.05.016.

[14] H. C. Shih, “Robust gender classification using a precise patch histogram,” Pattern Recognit., vol. 46, no. 2, pp. 519–528, 2013, doi: 10.1016/j.patcog.2012.08.003.

[15] B. Patel, R. P. Maheshwari, and B. Raman, “Compass local binary patterns for gender recognition of facial photographs and sketches,” Neurocomputing, vol. 218, pp. 203–215, 2016, doi: 10.1016/j.neucom.2016.08.055.

[16] B. Moghaddam and Ming-Hsuan Yang, “Learning gender with support faces,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 5, pp. 707–711, May 2002, doi: 10.1109/34.1000244.

[17] S. Baluja and H. A. Rowley, “Boosting Sex Identification Performance,” Int. J. Comput. Vis., vol. 71, no. 1, pp. 111–119, Jan. 2007, doi: 10.1007/s11263-006-8910-9.

[18] A. Jain, J. Huang, and Shiaofen Fang, “Gender Identification Using Frontal Facial Images,” in 2005 IEEE International Conference on Multimedia and Expo, 2005, vol. 2005, pp. 1082–1085, doi: 10.1109/ICME.2005.1521613.

[19] M. A. Berbar, “Three robust features extraction approaches for facial gender classification,” Vis. Comput., vol. 30, no. 1, pp. 19–31, Jan. 2014, doi: 10.1007/s00371-013-0774-8.

[20] T. Jabid, M. H. Kabir, and O. Chae, “Gender classification using local directional pattern (LDP),” Proc. - Int. Conf. Pattern Recognit., pp. 2162–2165, 2010, doi: 10.1109/ICPR.2010.373.

[21] L. Lu and P. Shi, “A novel fusion-based method for expression-invariant gender classification,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., pp. 1065–1068, 2009, doi: 10.1109/ICASSP.2009.4959771.

[22] L. Bui, D. Tran, X. Huang, and G. Chetty, “Face gender recognition based on 2D Principal Component Analysis and Support Vector Machine,” Proc. - 2010 4th Int. Conf. Netw. Syst. Secur. NSS 2010, pp. 579–582, 2010, doi: 10.1109/NSS.2010.19.

[23] B. Li, X. C. Lian, and B. L. Lu, “Gender classification by combining clothing, hair and facial component classifiers,” Neurocomputing, vol. 76, no. 1, pp. 18–27, 2012, doi: 10.1016/j.neucom.2011.01.028.

[24] J. Mansanet, A. Albiol, and R. Paredes, “Local Deep Neural Networks for gender recognition,” Pattern Recognit. Lett., vol. 70, pp. 80–86, 2016, doi: 10.1016/j.patrec.2015.11.015.

[25] A. Dhomne, R. Kumar, and V. Bhan, “Gender Recognition Through Face Using Deep Learning,” Procedia Comput. Sci., vol. 132, pp. 2–10, 2018, doi: 10.1016/j.procs.2018.05.053.

[26] C. J. Lin, Y. C. Li, and H. Y. Lin, “Using convolutional neural networks based on a Taguchi method for face gender recognition,” Electron., vol. 9, no. 8, pp. 1–15, 2020, doi: 10.3390/electronics9081227.

[27] T. V. Janahiraman and P. Subramaniam, “Gender Classification Based on Asian Faces using Deep Learning,” in 2019 IEEE 9th International Conference on System Engineering and Technology (ICSET), Oct. 2019, vol. 57, no. 5, pp. 84–89, doi: 10.1109/ICSEngT.2019.8906399.

[28] E. Eidinger, R. Enbar, and T. Hassner, “Age and Gender Estimation of Unfiltered Faces,” IEEE Trans. Inf. Forensics Secur., vol. 9, no. 12, pp. 2170–2179, Dec. 2014, doi: 10.1109/TIFS.2014.2359646.

[29] P. Rodríguez, G. Cucurull, J. M. Gonfaus, F. X. Roca, and J. Gonzàlez, “Age and gender recognition in the wild with deep attention,” Pattern Recognit., vol. 72, pp. 563–571, Dec. 2017, doi: 10.1016/j.patcog.2017.06.028.

[30] K. Zhang et al., “Age Group and Gender Estimation in the Wild with Deep RoR Architecture,” IEEE Access, vol. 5, no. X, pp. 22492–22503, 2017, doi: 10.1109/ACCESS.2017.2761849.

[31] M. Duan, K. Li, C. Yang, and K. Li, “A hybrid deep learning CNN–ELM for age and gender classification,” Neurocomputing, vol. 275, pp. 448–461, 2018, doi: 10.1016/j.neucom.2017.08.062.

[32] M. Afifi and A. Abdelhamed, “AFIF4: Deep gender classification based on AdaBoost-based fusion of isolated facial features and foggy faces,” J. Vis. Commun. Image Represent., vol. 62, pp. 77–86, 2019, doi: 10.1016/j.jvcir.2019.05.001.

[33] K. Khan, M. Attique, I. Syed, and A. Gul, “Automatic Gender Classification through Face Segmentation,” Symmetry (Basel)., vol. 11, no. 6, p. 770, Jun. 2019, doi: 10.3390/sym11060770.

[34] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.

[35] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.

[36] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 2818–2826, 2016, doi: 10.1109/CVPR.2016.308.

[37] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.

[38] J. Van De Wolfshaar, M. F. Karaaba, and M. A. Wiering, “Deep convolutional neural networks and support vector machines for gender recognition,” Proc. - 2015 IEEE Symp. Ser. Comput. Intell. SSCI 2015, no. October, pp. 188–195, 2015, doi: 10.1109/SSCI.2015.37.

[39] G. Özbulak, Y. Aytar, and H. K. Ekenel, “How transferable are CNN-based features for age and gender classification?,” Lect. Notes Informatics (LNI), Proc. - Ser. Gesellschaft fur Inform., vol. P-260, no. 113, pp. 4–9, 2016, doi: 10.1109/BIOSIG.2016.7736925.