A Technique and Architectural Design for Criminal Detection based on Lombroso Theory Using Deep Learning

Abstract

Crimes and criminal activities are increasing day by day and there are no proper criteria to search, detect, identify, and predict these criminals. Despite various surveillance cameras in different areas still, crimes are at a peak. The police investigation department cannot efficiently detect the criminals in time. However, in many countries for the sake of public and private security, the initiation of security technologies has been employed for criminal identification or recognition with the help of footprint identification, fingerprint identification, facial recognition, or based on other suspicious activity detections through surveillance cameras. However, there are limited automated systems that can identify the criminals precisely and get the accurate or precise similarity between the recorded footage images with the criminals that already are available in the police criminal records. To make the police investigation department more effective, this research work presents the design of an automated criminal detection system for the prediction of criminals. The proposed system can predict criminals or possibilities of being criminal based on Lombrosso's Theory of Criminology about born criminals or the persons who look like criminals. A deep learning-based facial recognition approach was used that can detect or predict any person whether he is criminal, or not and that can also give the possibility of being criminal. For training, the ResNet50 model was used, which is based on CNN and SVM Classifiers for feature extracting from the dataset. Two different labeled based datasets were used, having different criminals and noncriminals images in the database. The proposed system could efficiently help the investigating officers in narrowing down the suspects' pool.