Invariant pattern recognition using analog recurrent associative memories

Authors:
Iulian B. Ciocoiu
Affiliations:
Faculty of Electronics and Telecommunications, Technical University of Iasi, Bd. Carol I, No. 11, Iasi 700506, Romania
Venue:
Neurocomputing
Year:
2009

Citing 17
Cited 1

Feature extraction from faces using deformable templates

International Journal of Computer Vision
Original Contribution: Associative memory with nonmonotone dynamics

Neural Networks
Dynamic RBF networks

Radial basis function networks 1
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale and Rotation Invariant Recognition Method Using Higher-Order Local Autocorrelation Features of Log-Polar Image

ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume II
Enhancements for Local Feature Based Image Classification

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
On the Euclidean Distance of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
RBF-based neurodynamic nearest neighbor classification in real pattern space

Pattern Recognition
Invariant kernel functions for pattern analysis and machine learning

Machine Learning
Eigenfaces for recognition

Journal of Cognitive Neuroscience
A novelty detection approach to classification

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Analog decoding using a gradient-type neural network

IEEE Transactions on Neural Networks
Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks
Dynamic tunneling technique for efficient training of multilayer perceptrons

IEEE Transactions on Neural Networks
Neural associative memory storing gray-coded gray-scale images

IEEE Transactions on Neural Networks

Grammatical inference with bioinformatics criteria

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

A novel invariant pattern recognition approach is proposed based on a special gradient-type recurrent analog associative memory. The system exhibits stable equilibrium points in predefined positions specified by feature vectors extracted from the training set, while invariance to geometrical transformations is inferred by using the tangent distance. Experimental results for handwritten character recognition and face recognition tasks indicate that the proposed approach may yield superior performances over classical solutions based on the Euclidean distance metric. Possible extensions towards modular and sequential pattern recognition are finally outlined.