Criminal Face Detection: Building an Automated System for Criminal Face Detection using Facial Details

Abstract

Criminal Face Detection project aims to build an automated Criminal Face Detection systemby levering the human ability to recall minute facial details. Identification of criminals at the scene of acrime can be achieved in many ways like fingerprinting, DNA matching or eye witness accounts. Out ofthese methods eye witness accounts are preferred because it stands scrutiny in court and it is a costeffective method. It is possible that witnesses to a crime have seen the criminal though in most cases itmay not be possible to completely see the face of the perpetrator. The Criminal Face Detection Systemwill be built of an existing criminal database. Input would be provided in the form of sketch or an imageand matched against the existing database and results would be provided. Criminal record generallycontains personal information about particular person along with photograph. To identify any Criminalwe need some identification regarding person, which are given by eyewitness. The human face is acomplicated multidimensional visual model and hence it is very difficult to develop a computationalmodel for recognizing it. The paper presents a methodology for recognizing the human face based onthe features derived from the image. The proposed methodology is implemented in two stages. The firststage detects the human face in an image using viola Jones algorithm. In the next stage the detectedface in the image is recognized using a fusion of principle.