Encoding of facial images into illumination-invariant spike trains

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.