Face Recognition is one of the process of identifying people using their face, it has various applications like authentication systems, surveillance systems and law enforcement. Convolutional Neural Networks are proved to be best for facial recognition. Detecting faces using core-ml api and processing the extracted face through a coreML model, which is trained to recognise specific persons. The creation of dataset is done by converting face videos of the persons to be recognised into Hundreds of images of person, which is further used for training and validation of the model to provide accurate real-time results. Face Recognition is the process of identifying a person using their face. There has been great progress in face recognition due to increase in computation power. As humans have an exceptional ability to recognise faces irrespective of the lighting conditions and varying expressions. The aim of face recognition systems is to surpass the human level of accuracy and speed.
A Convolutional Neural Network (CNN, or ConvNet) are a special kind of multi-layer neural networks, designed to recognise the visual patterns directly from pixel images with minimal pre processing. The models used are trained on ImageNet project which is a large visual database designed for use in visual object recognition software research.
Recommended citation: Rohith Pudari, Sunil Bhutada, Sai Pavan. (2019). “Realtime face recognition using CNN.” International Journal of Sciences and Technology 2019.. 1(1).