A Real Time Gender Recognition System Using Facial Images and CNN
DOI:
https://doi.org/10.26438/ijcse/v7i9.122126Keywords:
CNN, Face Images, Gender RecognitionAbstract
With technological advancements many small to large, simple to complex activities are automated. Growth of Artificial Intelligent techniques has eased the way we would look to solve the real world problems. One such area which has recently gained lot of attention is the facial analytics. It involves extracting features such as face expressions, gender, age etc. Gender information plays a vital role in areas such as human computer interaction, crime detection, gender preferences, facial biometrics for digital payments etc. This paper proposes an improved Convolutional Neural Network (CNN) framework for real time gender classification from facial images. A pretrained model Visual Geometry Group “VGGNet16” is used. It loads image datasets consisting of male and female images and trains consistently for 16 hours. Haar Cascade classifier is used to classify images based on facial traits. The proposed architecture exhibits a much reduced design complexity as compared to other CNN solutions applied in pattern recognition. A recognition accuracy of 90% was achieved with this method.
References
[1] D. Gupta, “Architecture of Convolutional Neural Networks (CNNs) demystified”, Analytics Vidhya, June 29, 2017.
[2] P. Smith, C. Chen, “Transfer Learning with Deep CNNs for Gender Recognition and Age Estimation”, In the Proceedings of the 2018 IEEE International Conference on Big Data, Seatle USA,pp. 2564-2571,2018
[3] S. Choudhary, M.Agarwal, M. Jailia, “Design Framework for Facial Gender Recognition Using MCNN”, International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Vol.8 Issue-3, pp. 209-213,2019
[4] O. Arriaga ,M.Valdenegro-Toro, P.G. Ploger, “Real-time Con tional Neural Networks for emotion and gender classification”, In the Proceedings of European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, pp. 221-226, 2019
[5] L. F. d. Araujo Zeni and C. Rosito Jung, "Real-Time Gender Detection in the Wild Using Deep Neural Networks," In the Proceedings of 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, pp. 118-125, 2018.
[6] N. M. Khalifa , M.H. N. Taha , A.E. Hassanien, H. N. E. T. Mohamed “Deep Iris: Deep Learning for Gender Classification Through Iris Patterns”, ACTA INFORM MED. Vol.27, Issue2, pp. 96-102,2019. doi: 10.5455/aim.2019.27.96-102
[7] A. V. Savchenko “Efficient facial representations for age, gender and identity recognition in organizing photo albums using multi-output ConvNet “,PeerJ Comput. Sci, June, pp.1-26, 2019. DOI 10.7717/peerj-cs.197
[8] R.Ranjan, A. Bansal, J. Zheng, H. Xu, J.Gleason, B. Lu, A. anduri, J. Chen, C. D. Castillo, R. Chellappa “ A Fast and Accurate System for Face Detection, Identification, and Verification”, Journal of Latex Class Files, Vol. 14, no. 8, pp.1-16, 2015.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
