Comparison of ARTMAP neural networks for classification for face recognition from video

Authors:
M. Barry;E. Granger
Affiliations:
Laboratoire d'imagerie, de vision et d'intelligence artificielle, École de technologie supérieure, Montreal, Canada;École de technologie supérieure, Montreal, Canada, Quebec, Canada
Venue:
ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition
Year:
2007

Citing 7
Cited 0

ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network

Neural Networks
ARTMAP-IC and medical diagnosis: instance counting and inconsistent cases

Neural Networks
Probabilistic recognition of human faces from video

Computer Vision and Image Understanding - Special issue on Face recognition
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Video-Based Framework for Face Recognition in Video

CRV '05 Proceedings of the 2nd Canadian conference on Computer and Robot Vision
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps

IEEE Transactions on Neural Networks
ART-EMAP: A neural network architecture for object recognition by evidence accumulation

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In video-based of face recognition applications, the What-and-Where Fusion Neural Network (WWFNN) has been shown to reduce the generalization error by accumulating a classifier's predictions over time, according to each individual in the environment. In this paper, three ARTMAP variants - fuzzy ARTMAP, ART-EMAP (Stage 1) and ARTMAP-IC - are compared for the classification of faces detected in the WWFNN. ART-EMAP (stage 1) and ARTMAPIC expand on the well-known fuzzy ARTMAP by using distributed activation of category neurons, and by biasing distributed predictions according to the number of time these neurons are activated by training set patterns. The average performance of the WWFNNs with each ARTMAP network is compared to the WWFNN with a reference k-NN classifier in terms of generalization error, convergence time and compression, using a data set of real-world video sequences. Simulations results indicate that when ARTMAP-IC is used inside the WWFNN, it can achieve a generalization error that is significantly higher (about 20% on average) than if fuzzy ARTMAP or ART-EMAP is used. Indeed, ARTMAP-IC is less discriminant than the two other ARTMAP networks in cases with complex decision bounderies, when the training data is limited and unbalanced, as found in complex video data. However, ARTMAP-IC can outperform the others when classes are designed with a larger number of training patterns.