NCJ Number
224276
Journal
Forensic Magazine Volume: 5 Issue: 3 Dated: June/July 2008 Pages: 30,32,34
Date Published
June 2008
Length
3 pages
Annotation
This article provides an overview of two new technological advancements in the production of ‘facial composites’ developed by two research groups in the United Kingdom utilizing a computational search technique known as a genetic algorithm.
Abstract
EvoFIT was produced by Peter Hancock and Charlie Frowd at the University of Stirling, Scotland. From a randomly-generated selection of 18 faces, a witness is asked to choose the 6 faces that most resemble the suspect. These 6 faces become the parents of 18 offspring faces generated by combining the features of the parents. The witness then chooses another sic from the offspring populations to become parents, and so on. The features being selected and mutated are values of around 50 principle components that describe the structure of the face. This process usually produces a likeness acceptable to the witness in about four generations. The University of Stirling is now aiming to improve EvoFIT’s ergonomics or user-friendliness. EigenFIT was produced by Chris Solomon at the University of Kent, England which is similar to EvoFIT. EigenFIT is thought to have been better adapted to human use and cognitive processes. EigenFIT requires the witness to select faces based on their similarity to the target face. Another advantage of the EigenFIT system is its ability to manipulate faces along subjective dimensions. The psychological theory behind both EigenFIT and EvoFIT is very similar, as is the software implementation. Both of these systems have the potential to replace the traditional “photofit” process which has been identified with a problem in that the human brain recognizes faces holistically, not as a collection of isolated features. Today, the race is on to commercialize both the EigenFIT and EvoFIT systems and win the approval of the police and forensics community. Figure, references