Automated Criminal Identification by Face Recognition using Open Computer Vision Classifiers

Abstract

This paper presents a real time face recognition using a automated surveillance camera. The proposed system consists of 4 steps, including (1)training of real time images (2)face detection using Haar-classifier (3) comparison of trained real time images with images from the surveillance camera (4)result based on the comparison. An important application of interest is automated surveillance, where the objective is to recognize people who are on a watch list. The aspiration of this paper is to compare an image with several images which has been already trained. In this paper, we represent a methodology for face detection robustly in real time environment. Haar cascading is one of the algorithm for face detection. Here we use Haar like classifiers to track faces on OpenCV platform. The accuracy of the face recognition is very high. The proposed system can successfully recognize more than one face which is useful for quickly searching suspected persons as the computation time is very low. In India, we have a system for recognizing citizen called Aadhaar. If we use this as a citizenship database we can differentiate between citizen and foreigner and further investigate whether the identified person is criminal or not.