CRIMINAL DETECTION USING FACE RECOGNITION

Abstract: We all know that human Face is a unique and crucial part of the human body structure that identifies a person. Face detection which is the task of localizing faces in an input image is a fundamental part of any face processing system. The aim of this paper is to present a review on methods and algorithms used for face detection. The algorithm Haar cascade was described. We represent a methodology for face detection robustly in real time environment. Here we use Haar cascade like classifier to track faces on OpenCV platform which is open source and developed by Intel. The main concept of this paper is to experiment with using deep learning neural networks to detect and quickly respond to crimes in progress with effective Criminal Recognition to reduce the crime rate. Manually doing and tracking is very difficult job for the police. We can use the proposed system to trace the identity of a criminal person. With the advancement in technology, we can place CCTV at many public places to capture the criminal’s image. This system will be able to detect face and recognize face automatically as well. Using the previously captured faces and criminal’s images that are available in the police station, the criminal face recognition system can be implemented. We have used deep learning libraries and some image processing tools to achieve this task.

Keywords: Face recognition; OpenCV; Haar Cascade; CCTV; Deep learning