Age and Gender Predictions using Artificial Intelligence Algorithm
Anirudh Ghildiyal, Sachin Sharma, Ishita Verma, Urvi Marhatta
Abstract
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 expression, lighting, occlusion, and resolution.