Age Estimation in Juveniles using Convolution Neural Network

Age estimation models have been developed by many but no one has been able to build it with much accuracy and precision. This becomes even more challenging while estimating age of juveniles. This project aims to find a solution to this challenging problem. Juvenile age estimation can be used in multiple domains. It can be used majorly to stop criminal activities affecting children and teenagers. Faces of the subjects are captured and then the images are analysed using neural networks. The project is based mainly on concepts of machine learning like computer vision and convolution neural networks. This project has enormous scope as the algorithm applied can be continuously optimised as per requirements. Convolution Neural networks are highly used for tasks involving image analysis and identification. Computer vision deals with how the computer perceives and visualises the input provided to it. The fundamental concepts used in any machine learning based image analysis are Computer vision and Convolution Neural networks. These fundamentals have been developed by researchers across the world but still have some improvements to be done. With accurate dataset and proper optimisation of algorithms it is possible to create an age estimation model more precise and accurate than the existing ones.