Title
View-Independent Face Recognition with RBF Gating in Mixture of Experts Method by Teacher-Directed Learning
Abstract
The present study focuses on using a new model to perform view-independent human face recognition. A model based on mixture of experts is proposed, which uses teacher-directed learning method to force the experts to learn a predetermined partitioning of the input face space, using a Radial basis function neural network for Gating network. This way, each expert obtains expertise over faces of a same pose. Experimental results on the PIE dataset demonstrated the improved performance of our proposed model in comparison with ME in its conventional learning style in terms of higher recognition rate.
Year
DOI
Venue
2008
10.1007/978-90-481-3656-8_75
TECHNOLOGICAL DEVELOPMENTS IN EDUCATION AND AUTOMATION
Keywords
Field
DocType
face recognition
Facial recognition system,Radial basis function network,Radial basis function,Gating,Face space,Pattern recognition,Radial basis function neural,Computer science,Hum,Mixture of experts,Artificial intelligence
Conference
Citations 
PageRank 
References 
0
0.34
9
Authors
4
Name
Order
Citations
PageRank
Salman Khaleghian111.71
Nina Taheri Makhsoos251.20
Reza Ebrahimpour331424.55
Alireza Hajiany451.20