Familiar face recognition: a comparative study of a connectionist model and human performance

Luckman, Adrian J. and Allinson, Nigel M. and Ellis, Andrew W. and Flude, Brenda M. (1995) Familiar face recognition: a comparative study of a connectionist model and human performance. Neurocomputing, 7 (1). pp. 3-27. ISSN 0925-2312

Full content URL: http://www.sciencedirect.com/science/article/pii/0...

Full text not available from this repository.

Item Type:Article
Item Status:Live Archive

Abstract

A connectionist simulation of familiar face recognition by humans, which incorporates aspects of the Bruce and Young cognitive model, is discussed in detail. The computer model employs three self-organising neural maps, whose input vectors are the eye region, the mouth region and a reduced resolution full-face image of the input grey-scale face images, together with a decision-making supervised multi-layer perceptron as the output network. A comparative set of experiments has been performed using this simulation and human subjects for the task of familiar face recognition. When the gender of the facial images is supplied to the simulation, the recall misclassifications of the simulation and the human subjects are statistically similar. A connectionist simulation of familiar face recognition by humans, which incorporates aspects of the Bruce and Young cognitive model, is discussed in detail. The computer model employs three self-organising neural maps, whose input vectors are the eye region, the mouth region and a reduced resolution full-face image of the input grey-scale face images, together with a decision-making supervised multi-layer perceptron as the output network. A comparative set of experiments has been performed using this simulation and human subjects for the task of familiar face recognition. When the gender of the facial images is supplied to the simulation, the recall misclassifications of the simulation and the human subjects are statistically similar.

Keywords:Cognitive systems, Computer simulation, Decision making, Image processing, Neural networks, Self organizing storage, Vision, Cognitive psychology, Connectionist model, Familiar face recognition, Human performance, Kohonen networks, Multi layer perceptron, Pattern recognition, article, classification, cognition, computer model, face, pattern recognition, priority journal
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
C Biological Sciences > C850 Cognitive Psychology
Divisions:College of Science > School of Computer Science
ID Code:8605
Deposited On:26 Apr 2013 11:00

Repository Staff Only: item control page