Supervised vessel segmentation with minimal features

Current state-of-the art supervised vessel segmentation methods require large number of feature vectors to construct a good model. In this paper, we propose a framework to optimally search for optimal features as inputs to Artificial Neural Network (ANN) trained by Scaled Conjugate Gradient (SCG). S...

Full description

Bibliographic Details
Main Authors: Che Azemin, Mohd Zulfaezal, Mohd Tamrin, Mohd Izzuddin
Format: Proceeding Paper
Language:English
Published: 2014
Subjects:
Online Access:http://irep.iium.edu.my/42183/
http://irep.iium.edu.my/42183/4/su.pdf
_version_ 1848782232721817600
author Che Azemin, Mohd Zulfaezal
Mohd Tamrin, Mohd Izzuddin
author_facet Che Azemin, Mohd Zulfaezal
Mohd Tamrin, Mohd Izzuddin
author_sort Che Azemin, Mohd Zulfaezal
building IIUM Repository
collection Online Access
description Current state-of-the art supervised vessel segmentation methods require large number of feature vectors to construct a good model. In this paper, we propose a framework to optimally search for optimal features as inputs to Artificial Neural Network (ANN) trained by Scaled Conjugate Gradient (SCG). SCG is known to speed-up the learning stage in a supervised learning especially when error reduction is critical. The proposed framework is able to reduce features from 16 to 4 dimensions and the overall performance is only decreased by 1% in average
first_indexed 2025-11-14T16:02:11Z
format Proceeding Paper
id iium-42183
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T16:02:11Z
publishDate 2014
recordtype eprints
repository_type Digital Repository
spelling iium-421832015-10-16T07:00:53Z http://irep.iium.edu.my/42183/ Supervised vessel segmentation with minimal features Che Azemin, Mohd Zulfaezal Mohd Tamrin, Mohd Izzuddin RE Ophthalmology TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices TK7885 Computer engineering Current state-of-the art supervised vessel segmentation methods require large number of feature vectors to construct a good model. In this paper, we propose a framework to optimally search for optimal features as inputs to Artificial Neural Network (ANN) trained by Scaled Conjugate Gradient (SCG). SCG is known to speed-up the learning stage in a supervised learning especially when error reduction is critical. The proposed framework is able to reduce features from 16 to 4 dimensions and the overall performance is only decreased by 1% in average 2014 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/42183/4/su.pdf Che Azemin, Mohd Zulfaezal and Mohd Tamrin, Mohd Izzuddin (2014) Supervised vessel segmentation with minimal features. In: IEEE 19th Functional Electrical Stimulation Society Annual Conference (IFESS), 17-19 Sep 2014, Kuala Lumpur. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7036744
spellingShingle RE Ophthalmology
TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
TK7885 Computer engineering
Che Azemin, Mohd Zulfaezal
Mohd Tamrin, Mohd Izzuddin
Supervised vessel segmentation with minimal features
title Supervised vessel segmentation with minimal features
title_full Supervised vessel segmentation with minimal features
title_fullStr Supervised vessel segmentation with minimal features
title_full_unstemmed Supervised vessel segmentation with minimal features
title_short Supervised vessel segmentation with minimal features
title_sort supervised vessel segmentation with minimal features
topic RE Ophthalmology
TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
TK7885 Computer engineering
url http://irep.iium.edu.my/42183/
http://irep.iium.edu.my/42183/
http://irep.iium.edu.my/42183/4/su.pdf