Recognition of partially occluded and rotated images with a network of spiking neurons

Authors:
Joo-Heon Shin;David Smith;Waldemar Swiercz;Kevin Staley;J. Terry Rickard;Javier Montero;Lukasz A. Kurgan;Krzysztof J. Cios
Affiliations:
Department of Computer Science, Virginia Common-wealth University, Richmond, VA;University of Colorado Denver, Denver, CO;Massachusetts General Hospital, Boston, MA and Harvard Medical School, Boston, MA;Massachusetts General Hospital, Boston, MA and Harvard Medical School, Boston, MA;Distributed Infinity, Inc., Larkspur, CO;Department of Statistics and Operational Research, Faculty of Mathematics, Complutense University of Madrid, Madrid, Spain;Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada;Department of Computer Science, Virginia Commonwealth University, Richmond, VA and IITiS Polish Academy of Sciences, Gliwice, Poland
Venue:
IEEE Transactions on Neural Networks
Year:
2010

Citing 23
Cited 1

Automatic recognition and analysis of human faces and facial expressions: a survey

Pattern Recognition
Theoretical mechanics of biological neural networks

Theoretical mechanics of biological neural networks
SEEMORE: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition

Neural Computation
Machine Learning

Machine Learning
Neuronal Networks of the Hippocampus

Neuronal Networks of the Hippocampus
Spiking Neuron Models: An Introduction

Spiking Neuron Models: An Introduction
Coding Facial Expressions with Gabor Wavelets

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Face recognition using independent component analysis and support vector machines

Pattern Recognition Letters - Special issue: Audio- and video-based biometric person authentication (AVBPA 2001)
Face recognition: component-based versus global approaches

Computer Vision and Image Understanding - Special issue on Face recognition
Polychronization: Computation with Spikes

Neural Computation
Spike-Driven Synaptic Plasticity: Theory, Simulation, VLSI Implementation

Neural Computation
Multiclass Object Recognition with Sparse, Localized Features

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Data Mining: A Knowledge Discovery Approach

Data Mining: A Knowledge Discovery Approach
Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
A very simple spiking neuron model that allows for modeling of large, complex systems

Neural Computation
Face recognition using adaptively weighted patch PZM array from a single exemplar image per person

Pattern Recognition
Image recognition system based on novel measures of image similarity and cluster validity

Neurocomputing
An improved method for face recognition based on SVM in frequency domain

Machine Graphics & Vision International Journal
Neural networks for classification: a survey

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Solving graph algorithms with networks of spiking neurons

IEEE Transactions on Neural Networks
Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble

IEEE Transactions on Neural Networks
A new synaptic plasticity rule for networks of spiking neurons

IEEE Transactions on Neural Networks
Learning in linear neural networks: a survey

IEEE Transactions on Neural Networks

Synchronization of multiple chaotic FitzHugh-Nagumo neurons with gap junctions under external electrical stimulation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.