THE JOURNAL OF INDUSTRIAL TECHNOLOGY

Volume 18, No. 02, Month MAY, Year 2022, Pages 164 - 179

A service system for estimation of gender and assessing the person s age from facial images by deep learning-based method

Choopan Rattanapoka, Panupong Jannet, Teeratorn Moonpanyo

Abstract Download PDF

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.

Keywords

Web API, Image processing, Deep learning, Convolutional neural network

---