A Service System for Estimation of Gender and Assessing the Person's Age from Facial Images by Deep Learning-based Method
DOI: 10.14416/j.ind.tech.2022.08.003
Keywords:
Web API, Image processing, Deep learning, Convolutional neural networkAbstract
This article proposes the design and development of deep learning models for predicting age and gender from a facial image, the web API for using the developed model, and a web application and a mobile application that use our model via the web API. The architecture of the developed model is based on the integration of VGG16 and ResNet. We implemented three models: (1) an age prediction model, (2) a gender prediction model, and (3) an age and gender prediction model. All three models were trained with 154,667 images from the IMDB dataset. The models were evaluated with 38,138 images from the WIKI datasets. From the experiments, we found that the age prediction model had a mean absolute error of 5.949 with 0.167s processing time while the gender prediction model has 96.58% accuracy with 0.169s processing time. Finally, the age and gender prediction model has a gender prediction accuracy of 95.82% and a mean absolute error in age prediction of 6.347 with a prediction time of 0.171s.
References
Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature, 2015, 521, 436-444.
J. Liu and X. Wang, Tomato diseases and pests detection based on improved Yolo V3 convolutional neural network, Frontiers in Plant Science, 2020, 11, 898.
Y. Ji, S. Kim, Y.J. Kim, and K.B. Lee, Human-like sign-language learning method using deep learning, ETRI Journal, 2018, 40(4), 435 - 445.
S.E. Bekhouche, A. Ouafi, A. Benlamoudi, A. Taleb-Ahmed, and A. Hadid, Facial age estimation and gender classification using multi level local phase quantization, The 3rd International Conference on Control, Engineering Information Technology (CEIT- 2015), Proceeding, 2015, 1-4.
S. H. Lee, S. Hosseini, H. J. Kwon, J. Moon, H. I. Koo, and N. I. Cho, Age and gender estimation using deep residual learning network, International Workshop on Advanced Image Technology (IWAIT-2018), Proceeding, 2018, 1 - 3.
https://github.com/yu4u/age-gender-estimation. (Accessed on 15 February 2022)
M. Tan and Q.V. Le, EfficientNet: Rethinking model scaling for convolutional neural networks, arXiv, 2019, 1905.11946.
K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv, 2014, 1409.1556.
https://github.com/rcmalli/keras-vggface. (Accessed on 10 February 2022)
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, arXiv, 2015, 1512.03385.
S. Loffe and C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift, arXiv, 2015, 1502.03167.
R. Rothe, R. Timofte, and L.V. Gool, Deep expectation of real and apparent age from a single image without facial landmarks, International Journal of Computer Vision, 2018, 126, 144-157.
M. Jones, J. Bradley, and N. Sakimura, JSON Web Token (JWT), Internet Engineering Task Force, RFC 7519, 2015.
D.E. King, Dlib-ml: A machine learning toolkit, Journal of Machine Learning Research, 2009, 10, 1755-1758.
E. Bisong, Google colaboratory, In: Building machine learning and deep learning models on google cloud platform: A comprehensive guide for beginners, Apress Berkeley, CA, USA, 2019, 59-64.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
ผลงานวิจัยและบทความวิชาการที่ปรากฏในวารสารนี้ เป็นความคิดเห็นอิสระของผู้เขียน ผู้เขียนจะต้องเป็นผู้รับผิดชอบต่อผลทางกฎหมายใด ๆ ที่อาจจะเกิดขึ้นจากบทความนั้น กองบรรณาธิการและคณะจัดทำวารสารฯไม่จำเป็นต้องเห็นด้วยเสมอไป