Home // COGNITIVE 2017, The Ninth International Conference on Advanced Cognitive Technologies and Applications // View article

Incremental Face Recognition by Tagged Neural Cliques

Authors:
Ehsan Sedgh Gooya
Dominique Pastor

Keywords: Face recognition; incremental learning; neural tagged cliques; SIFT (Scale-Invariant Feature Transform) features.

Abstract:
We present a system aimed at performing an incremental learning based on a neural network of tagged cliques for face recognition. A crucial component of the system is the network of neural tagged cliques. In its original version, cliques are a set of binary connections linking a set of fired neurons. Tagged cliques make it then possible to identify these cliques. The incremental learning is achieved through two phases: the first one is supervised by an oracle and the second one is automatic. Experimental results on the ORL (Olivetti Research Laboratory) face database pinpoint that incremental learning significantly reduces the number of features to store and yields substantial recognition rate improvement, in comparison with no incremental learning.

Pages: 54 to 58

Copyright: Copyright (c) IARIA, 2017

Publication date: February 19, 2017

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-531-9

Location: Athens, Greece

Dates: from February 19, 2017 to February 23, 2017