Publication

Abstract : Determining an individual’s age accurately is important in many contexts, including forensic investigations, medical diagnostics, and security applications. Traditional age estimation techniques rely on manual evaluation, which can be laborious and error prone. Convolutional neural networks (CNN) have been utilized more and more for image-based age estimation since the development of deep learning. The Objective is to create a CNN-based age estimation algorithm that can precisely estimate a person’s age from facial photos. The proposed study used the UTKFace dataset and Facial Image dataset, which included 30,000+ facial images of people from various ethnic backgrounds, aged 0 to 116 and Facial pictures, a public dataset, which is a compilation of digital portraits of people. Five convolutional layers, five pooling layers, and two fully linked layers make up the deep CNN model that has been developed and trained in this project. The study’s findings show how well CNN-based deep learning models may be used to determine an individual’s age from face photos. For the model’s training, the UTKFace dataset and Facial Images dataset supplied a wide-ranging and sizable combined dataset. The model performed better than more established age estimation techniques.