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 t...

Full description

Bibliographic Details
Main Authors:	Hafiz , Fadhlan, Shafie, Amir Akramin
Format:	Conference or Workshop Item
Language:	English
Published:	2012
Subjects:	TK7885 Computer engineering
Online Access:	http://irep.iium.edu.my/27222/ http://irep.iium.edu.my/27222/ http://irep.iium.edu.my/27222/1/06271167.pdf

id	iium-27222
recordtype	eprints
spelling	iium-272222013-01-23T07:33:52Z http://irep.iium.edu.my/27222/ Encoding of facial images into illumination-invariant spike trains Hafiz , Fadhlan Shafie, Amir Akramin TK7885 Computer engineering 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. 2012-07-03 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/27222/1/06271167.pdf Hafiz , Fadhlan and Shafie, Amir Akramin (2012) Encoding of facial images into illumination-invariant spike trains. In: International Conference on Computer and Communication Engineering (ICCCE 2012), 3-5 July 2012, Seri Pacific Hotel Kuala Lumpur. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6271167
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	TK7885 Computer engineering
spellingShingle	TK7885 Computer engineering Hafiz , Fadhlan Shafie, Amir Akramin Encoding of facial images into illumination-invariant spike trains
description	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.
format	Conference or Workshop Item
author	Hafiz , Fadhlan Shafie, Amir Akramin
author_facet	Hafiz , Fadhlan Shafie, Amir Akramin
author_sort	Hafiz , Fadhlan
title	Encoding of facial images into illumination-invariant spike trains
title_short	Encoding of facial images into illumination-invariant spike trains
title_full	Encoding of facial images into illumination-invariant spike trains
title_fullStr	Encoding of facial images into illumination-invariant spike trains
title_full_unstemmed	Encoding of facial images into illumination-invariant spike trains
title_sort	encoding of facial images into illumination-invariant spike trains
publishDate	2012
url	http://irep.iium.edu.my/27222/ http://irep.iium.edu.my/27222/ http://irep.iium.edu.my/27222/1/06271167.pdf
first_indexed	2023-09-18T20:40:29Z
last_indexed	2023-09-18T20:40:29Z
_version_	1777409332243070976

Encoding of facial images into illumination-invariant spike trains

Similar Items