Extreme learning machine based image classification
Extreme Learning Machine (ELM) as a type of generalized single-hidden layer feed-forward networks (SLFNs) has demonstrated its good generalization performance with extreme fast learning speed in many benchmark and real applications. This project further studies the performance of ELM in image classi...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/50041 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-50041 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-500412023-07-07T16:13:51Z Extreme learning machine based image classification Xu, Jiantao. Huang Guangbin School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Extreme Learning Machine (ELM) as a type of generalized single-hidden layer feed-forward networks (SLFNs) has demonstrated its good generalization performance with extreme fast learning speed in many benchmark and real applications. This project further studies the performance of ELM in image classification using two different feature extraction methods. The first method extracts texture features, intensity features from Histogram and features from two types of color space: HSV & RGB. The second method extracts shape features based on Radon transform. The classification performance of ELM is compared with the performance of Support Vector Machines (SVMs). Simulation results show that ELM has better testing accuracy with much less training time on majority cases than SVM for both feature extraction methods. Besides, the parameter tuning process for ELM is much easier than SVM as well. Bachelor of Engineering 2012-05-29T03:54:35Z 2012-05-29T03:54:35Z 2012 2012 Final Year Project (FYP) http://hdl.handle.net/10356/50041 en Nanyang Technological University 60 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Xu, Jiantao. Extreme learning machine based image classification |
description |
Extreme Learning Machine (ELM) as a type of generalized single-hidden layer feed-forward networks (SLFNs) has demonstrated its good generalization performance with extreme fast learning speed in many benchmark and real applications. This project further studies the performance of ELM in image classification using two different feature extraction methods. The first method extracts texture features, intensity features from Histogram and features from two types of color space: HSV & RGB. The second method extracts shape features based on Radon transform. The classification performance of ELM is compared with the performance of Support Vector Machines (SVMs). Simulation results show that ELM has better testing accuracy with much less training time on majority cases than SVM for both feature extraction methods. Besides, the parameter tuning process for ELM is much easier than SVM as well. |
author2 |
Huang Guangbin |
author_facet |
Huang Guangbin Xu, Jiantao. |
format |
Final Year Project |
author |
Xu, Jiantao. |
author_sort |
Xu, Jiantao. |
title |
Extreme learning machine based image classification |
title_short |
Extreme learning machine based image classification |
title_full |
Extreme learning machine based image classification |
title_fullStr |
Extreme learning machine based image classification |
title_full_unstemmed |
Extreme learning machine based image classification |
title_sort |
extreme learning machine based image classification |
publishDate |
2012 |
url |
http://hdl.handle.net/10356/50041 |
_version_ |
1772826600403894272 |