Multi-face Recognition for the Detection of Prisoners in Jail using a Modified Cascade Classifier and CNN

Abstract

Identifying the identity of a prisoner in a detention cell, through facial recognition automatically is a big, exciting problem and there are many different approaches to solve this problem because it must detect multiple faces (multi-face). Especially in uncontrolled real-life scenarios, faces will be seen from various sides and not always facing forward, which makes classification problems more difficult to solve. In this research, one method is combined deep neural networks that is Convolutional Neural Networks (CNN) and Haar Cascade Classifier as real-time facial recognition, which has proven to be very efficient in face classification. Methods are implemented with assistance library Open-CV for multi-face detection and 5MP CCTV camera devices. In preparing the architectural model Convolutional Neural Networks Do configuration parameter initialization to speed up the network training process. Test results on 51 test data using constructs Convolutional Neural Networks VGG16 models up to a depth of 16 layers of convolution layers with input from the extraction of the Haar Cascade Classifier resulting in facial recognition system performance reaching an accuracy rate of about 87%.