Forensic Sketch-Photo Matching using LFDA
Ujwala T. Tayade, Seema Biday, Lata L. Ragha · 2013
Abstract — The advancement of biometric technology has provided criminal investigators additional tools to determine the identity of criminals. In addition to DNA and circumstantial evidence, if a latent fingerprint is found at an investigative scene or a surveillance camera captures an image of a suspect’s face, then these cues may be used to determine the culprit’s identity using automated biometric identification. However, many crimes occur where none of this information is present, but instead an eye-witness of the crime is available. In these circumstances a forensic artist is often used to work with the witness or the victim in order to draw a sketch that depicts the facial appearance of the culprit according to the verbal description. These sketches are known as forensic sketches. This problem of matching a forensic sketch to a gallery of mugshot images is addressed here using a robust framework called local feature-based discriminant analysis (LFDA). Since, forensic sketches or digital face images can be of poor quality, a pre-processing technique is used to enhance the quality of images and improve the identification performance.In this paper experiments are carried out using 52 forensic sketches for matching against a gallery of 264 photo images. The experimental results demonstrate the matching performance of the proposed algorithm with the use of preprocessing approach yields better identification accuracy compared to other methods. 1. The person may have already been convicted once or 2. The person has not been convicted even once or this is the first time, he may be committing crime. In general, sketches are classified into two categories: viewed sketches and forensic sketches • Viewed Sketches: These are the sketches drawn by an artist, directly looking at the subject or the photograph of the subject as shown in fig. 1. Forensic Sketches: These are the sketches drawn by specially trained artists based on the description of subject by an eye witness as shown in fig. 2. Two key difficulties highlighted in matching forensic sketches are: (1) Matching across image modalities, and (2) performing face recognition despite possibly inaccurate depictions of the face.