Age and Gender Prediction using Transfer Learning

Authors: Shraddha Thorat, Aditya Bhavar, Atharva Shirole, Sakshi Mindhe

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Automatic age and gender prediction from face images has lately attracted much attention due to its wide range of applications in numerous facial analyses. We show in this study that utilizing the Caffe Model Architecture of Deep Learning Frame Work; we were able to greatly enhance age and gender recognition by learning representations using deep convolutional neural networks (CNN). We propose a much simpler convolutional net architecture that can be employed even if no learning data is available. In a recent study presenting a potential benchmark for age and gender estimation, we show that our strategy greatly outperforms existing state-of-the-art methods.Gender is still a central aspect of personality, and in social life it is still an important factor. Gender and age projections for artificial intelligence can be used in many areas, such as the development of smart human-machine interfaces, fitness, cosmetics, e-commerce, etc. The prediction of age and gender is an ongoing and active research question for individuals from their facial images. A number of approaches to solving this issue have been suggested by the researchers, but the criteria and actual performance are still insufficient. This paper proposes a mathematical approach to recognition patterns in order to solve this problem. The Convolution Neural Network (ConvNet / CNN) deep learning algorithm is used as a feature extractor in the proposed solution. CNN takes input images and assigns value to and can distinguish between various aspects / objects (learnable weights and biases) of the image. ConvNet needs much less pre-processing than other classification algorithms. While the filters are hand-made in primitive methods, ConvNet can learn these filters / features with adequate training. In this research, face images of individuals have been trained with convolution neural networks, and age and sex with a high rate of success have been predicted. More than 20,000 images are containing age, gender and ethnicity annotations. The images cover a wide range of poses, facial expresiii Transfer learning for gender and age prediction sion, lighting, occlusion, and resolution

Keywords: Gender Recognition, Age Classification, Haar Cascade, Caffe Deep Learning Framework

Paper Id: 230210

Published On: 2023-06-03

Published In: Volume 11, Issue 3, May-June 2023

Cite This: Age and Gender Prediction using Transfer Learning - Shraddha Thorat, Aditya Bhavar, Atharva Shirole, Sakshi Mindhe - IJIRMPS Volume 11, Issue 3, May-June 2023.

Share this