Published Paper Details:

The process of categorising facial photos or videos into specified age groups is known as age group classification. Due of its many applications, including in recruitment, security, health, and social robots with intelligence, it is a crucial task. Recently, Convolutional Neural Network (CNN) has demonstrated exceptional performance in interpreting photos and videos of human faces. This study suggested an All-Age Face (AAF) dataset-trained and evaluated age group classification task using CNN. In this study, a 128-d embedding that quantifies the face of the age group was computed using the FaceNet deep learning model, which makes use of CNN. Adolescence and Mature Adulthood were the two age ranges represented in the experiment. For the training photos, the proposed age group classification model had an accuracy of 84.90%, and for the test images, it had an accuracy of 85.12%. The experimental findings demonstrated that CNN can, even with an imbalanced data distribution, achieve competitive classification accuracy across two age groups in the AAF dataset.