Sketch based face recognition: Forensic vs. composite sketches

Abstract

Facial sketches are widely used by law enforcement agencies to assist in the identification and apprehension of suspects involved in criminal activities. Sketches used in forensic investigations are either drawn by forensic artists (forensic sketches) or created with computer software (composite sketches) following the verbal description provided by an eyewitness or the victim. These sketches are posted in public places and in media in hopes that some viewers will provide tips about the identity of the suspect. This method of identifying suspects is slow and tedious and may not lead to apprehension of the suspect. Hence, there is a need for a method that can automatically and quickly match facial sketches to large police mugshot databases. We address the problem of automatic facial sketch to mugshot matching and, for the first time, compare the effectiveness of forensic sketches and composite sketches. The contributions of this paper include: (i) a database containing mugshots and corresponding forensic and composite sketches that will be made available to interested researchers; (ii) a comparison of holistic facial representations versus component based representations for sketch to mugshot matching; and (iii) an analysis of the effect of filtering a mugshot gallery using three sources of demographic information (age, gender and race/ethnicity). Our experimental results show that composite sketches are matched with higher accuracy than forensic sketches to the corresponding mugshots. Both of the face representations studied here yield higher sketch to photo matching accuracy compared to a commercial face matcher.