Users online: 4269    [ij] [ij] [ij] 
Email id

Research Journal of Engineering and Technology
Year : 2015, Volume : 6, Issue : 2
First page : ( 258) Last page : ( 262)
Print ISSN : 0976-2973. Online ISSN : 2321-581X.
Article DOI : 10.5958/2321-581X.2015.00039.2

Suspect identification by matching composite sketch with mug-shot

Wakode Shubhangi A.*, Gupta Sunil R.**

Department of Electronics Engineering, J. D. College of Engineering & Management (JDCOEM), Nagpur, Maharashtra, India

*Corresponding Author Email: shubhangi18wakode@gmail.com

** sungt_in@yahoo.com

Online published on 29 October, 2015.


The problem of automatically matching composite sketches to mug-shot is addressed in this paper. To determine the identity of a criminal, composite sketch to photograph is commonly used technique due to budgetary reason. The accuracy in detection is more using forensic sketches than composite sketches using facial composite software. Composite sketches have the same modality as that of the mug-shot has that changed the forensic world. In this paper emphasis is made on matching composite sketches to mug-shots that gives better performance over the more common representation method exists already. The component based framework presented in this paper consists of the following major steps. 1) Face normalization using a geometric transformation and color space conversion. 2) Facial component localization using Viola-John algorithm, followed by ASM. 3) Per component feature extraction using nearest neighbor symmetry and matrix normalize cross-correlation followed by computing length between facial constituent. The proposed system has been evaluated on mugshot photographs-composite sketches pairs with hundreds of individuals. The results are encouraging.



Composite sketches, mug-shot, face normalization, ASM, Viola-John algorithm.


║ Site map ║ Privacy Policy ║ Copyright ║ Terms & Conditions ║ Page Rank Tool
554,069,786 visitor(s) since 30th May, 2005.
All rights reserved. Site designed and maintained by DIVA ENTERPRISES PVT. LTD..
Note: Please use Internet Explorer (6.0 or above). Some functionalities may not work in other browsers.