| Home  | About ScienceAsia  | Publication charge  | Advertise with us  | Subscription for printed version  | Contact us  
Editorial Board
Journal Policy
Instructions for Authors
Online submission
Author Login
Reviewer Login
Volume 43 Number 1
Volume 42 Number 6
Volume 42S Number 1
Volume 42 Number 5
Volume 42 Number 4
Volume 42 Number 3
Earlier issues
Volume  Number  Volume 34 Number 2

previous article next article

Research articles

ScienceAsia 42(2016): 136-145 |doi: 10.2306/scienceasia1513-1874.2016.42.136

Computer-aided craniofacial superimposition using a quasi-Newton iterative closest point approach

Joi San Tana,*, Ibrahim Venkata, Paul T. Jayaprakashb

ABSTRACT:     Craniofacial superimposition is a forensic imaging technique used to identify an unknown skull by matching it with the available face photographs of missing individuals. Life-size enlargement of the face image and orientating the skull to correspond to the posture seen in the face photograph are the two main problems that exist in conventional as well as in the computer-aided craniofacial superimposition. Here we address these two potential issues by proposing a novel computer-aided approach which uses the quasi-Newton optimization method and iterative closest point algorithm. The results showed that the quasi-Newton method proposed is able to eliminate 76% and 66% of false matches, respectively, for the male and the female skull superimpositions during the initial stage of filtration. Our experimental results demonstrate that the proposed approach is efficient in assigning face photographs as inclusions (positives) and exclusions (negatives) while superimposing with related and unrelated skulls.

Download PDF

a School of Computer Sciences, Universiti Sains Malaysia, 11800 USM, Penang, Malaysia
b School of Health Sciences, Health Campus, Universiti Sains Malaysia, 16150 Kubang Kerian, Kelantan, Malaysia

* Corresponding author, E-mail: hiki_3joi@yahoo.com

Received 17 Nov 2014, Accepted 0 0000