Recognition of partially occluded and rotated images with a network of spiking neurons.
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.
SourceAvailable from: Zhenzhong Wang[Show abstract] [Hide abstract]
ABSTRACT: This study introduces a new Generalized Leaky Integrate-and-Fire (GLIF) neuron model with variable leaking resistor and bias current in order to reproduce accurately the membrane voltage dynamics of a biological neuron. The accuracy of this model is ensured by adjusting its parameters to the statistical properties of the Hodgkin-Huxley model outputs; while the speed is enhanced by introducing a Generalized Exponential Moving Average method that converts the parameterized kernel functions into pre-calculated lookup tables based on an analytic solution of the dynamic equations of the GLIF model.International Journal of Neural Systems 08/2014; 24(5):1440004. DOI:10.1142/S0129065714400048 · 6.06 Impact Factor
[Show abstract] [Hide abstract]
ABSTRACT: In this paper, we present a novel algorithm for recognition of vein features based on optimized generalized Hough transform (GHT). The new algorithm involves several steps. First, it extracts singular points from the binary image of finger veins, and segments the finger veins by these points. Then it selects valid segments and sequences them by way of chain codes. Next it uses the optimized GHT to differentiate sectional curves of finger veins from the whole finger vein image. Using this approach reduces the influence of fragmentation, enhances adaptability for displacement, rotation, and zooming, and accordingly improves the quality of finger vein recognition. We have tested the proposed method with actual finger vein images and produced very satisfactory reassembly results.Optik - International Journal for Light and Electron Optics 03/2014; 125(6):1780–1783. DOI:10.1016/j.ijleo.2013.09.038 · 0.77 Impact Factor
Conference Paper: Encoding of Facial Images into Illumination-Invariant Spike Trains[Show abstract] [Hide abstract]
ABSTRACT: Some previous work of several researchers have mathematically proven the advantage of Spiking Neural Network (SNN) in term of computational power and one of the neuron model that shows promising result is Spike response Model (SRM). Facial recognition is one of the tasks that can benefit from the advantages of SNN. Therefore in this work we try to unravel the elementary of facial recognition using SNN -the encoding of analog-valued images of the subject face into spike trains as inputs to the neural network using Leaky Integrate and Fire (LIF) model. Implementation of an adaptive LIF model is investigated and a spike adjustment method is proposed to improve the robustness of the generated spikes from a normalized image against different level of illuminations.International Conference on Computer and Communication Engineering (ICCCE 2012), Kuala Lumpur; 01/2012