Criminal investigation and management system using CCTV footage - "Eagle Eye"

Abstract

Automated criminal identification is not a very popular topic in Sri Lanka. To identify criminals, the methods which authorities are using are unnecessarily time-consuming. To make this process immovable, identifying a wanted person using an automated system would be a better alternative rather than the current practices. Current practices and techniques such as gathering records from eyewitnesses are not highly reliable. Even though scanning through CCTV camera footage manually is again laborious. Using modern technologies such as biometrics would be the best way to achieve this task in terms of accuracy. We will also use abnormal behavioral detection accompanied by Threatening weapons. As biometric techniques, using face recognition and figure recognition will provide the most promising result. Along with the modified image enhancement method that we are suggesting, the system will be able to capture and process the task in a much better way. Although biometric systems have already been used in society, there is no such system which can be used to identify and verify criminals. we used algorithms such as CNN, DNN, LBPH and Deep learning. As a final result, the system will automatically identify the entire crime incident to improve the quality of the footage, detect the abnormal behaviors accompanied by threatening weapons, identity & recognize the registered criminals using faces and their figures automatically with a minimum amount of time and higher accuracy level.