Eyewitness Research In Criminal Investigation

Abstract— To determine the uniqueness of criminal, growth in biometric technology have provide law enforcement agency other tools but, several crimes take place where none of the information is present, but instead an eyewitness description of the crime is presented. In these circumstances, a forensic artist is commonly used to work with the eyewitness in order to draw a sketch that depicts the facial look of the criminal according to the spoken description. Forensic sketches differ from view sketches in that they are drawn by a police sketch artist using the description of the issue provided by an eyewitness. Because face sketches represent the original faces in a very short recognizable form, they play an vital role in criminal investigations,

INTRODUCTION

Today, advance in biometric technology have provided criminal investigators extra tools to help conclude the identity of criminal. In addition to the supplementary evidence, if a unseen fingerprint is found at the scene of crime or a examination camera capture an image of the face of a suspect, then these clue be used in determining the suspect via biometric identification techniques. on the other hand, lots of crimes arise where none of the above discuss information is present. the lack of technology to efficiently capture the biometric data like finger prints within a short period after the scene of crime is a regular problem in isolated area. in spite of these result, many a times, an eyewitness report of the crime is available who have seen the criminal. The law enforcement department organize a forensic artist to work with the eyewitness in order to draw a sketch that represent the facial look of the criminal. These sketches are known as forensic

Klare, Kathryn Bonnen, and Anil K. Jain[12], Unlike sketches hand drawn by artists, composite sketches are synthesize using one of the number of facial composite software systems available to law enforcement agency. To calculate the similarity between a composite sketch and digital photograph a component based representation (CBR) approach. manually detect facial landmarks in composite sketches and digital photos using an active shape model (ASM). Features are extract for each facial component using multiscale local binary patterns (MLBPs), and per component similarity are calculate. Finally, the matching score obtained from individual facial components are merged together, Matching performance is more enhanced by filtering the large gallery of digital images using gender information. These are useful for law enforcement investigation of the variations in the quality of composite sketches synthesize by two users of different cultural environment suggests that users of facial composite software should be train to reduce the cross race bias in order to create high quality composite sketches for prospective suspects of various race. The second approach to sketch recognition attempt to learn or design feature representations that reducthe infraclass difference caused by modality gap while preserving interclass