Criminal Identification System Based on Facial Recognition Using Generalized Gaussian Mixture Model

There is an abnormal increase in the crime rate and also the number of criminals is increasing, this leads towards a great concern about the security issues. Crime preventions and criminal identification are the primary issues before the police personnel, since property and lives protection are the basic concerns of the police but to combat the crime, the availability of police personnel is limited. To help the cops, comprehensive data regarding the criminals will be advantageous. Data mining concepts proved to yield better results in this direction. In this paper, binary clustering and classification techniques have been used to analyze the criminal data. The crime data considered in this paper is from Andhra Pradesh police department this paper aims to potentially identify a criminal based on the facial evidence obtained through the CCT cameras or the identification based on witness/clue at the crime spot using a Generalized Gaussian Mixture model. INTRODUCTION Undoubtedly, there are significant changes in the living styles of humans, which may be due to the effect of technological growth and modernization or environmental conditions that force the humans to indulge in criminal activities. Law keepers are working rigorously to maintain law and order, but at the same time, the crime activities are increasing enormously leaving the cops difficult to analyze the crime and arrest the criminals [1][2]. Lot of research is projected in this direction by construction different models by the researchers for effective analysis [3][4][5][6]. However, the main disadvantage is that due to the overload of data regarding the crime activities, together with the increase in the number of criminals makes it difficult in analyzing the data. Therefore a better model with the knowledge about the crime & the criminal always will always be advantageous. Data mining techniques will be very much useful for these purposes [ 5][7][8] for analyzing enormous data. The usage of data mining helps in exploring the voluminous data and help the law keepers to retrieve the information more effectively and efficiently. With the usage of the data mining concepts, such as clustering and classification analyzing the large data gets simplified and this helps in the identification of the criminals. In order to identify a criminal, either direct evidence from the witness or indirect witness gathered by the forensic experts from the spot will be of great use. In this paper, we use the information available at the crime spot.