Enhanced extreme learning machines for image classification
Image Classification is one of the key computer vision tasks. Among numerous machine learning methods, we choose the Extreme Learning Machine (ELM) for our image classification applications. This thesis contributes to four aspects of ELM netwroks. From the view of efficient input data, we have desig...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Theses and Dissertations |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/106446 http://hdl.handle.net/10220/47966 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-106446 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1064462020-11-01T05:03:33Z Enhanced extreme learning machines for image classification Cui, Dongshun Huang Guangbin Interdisciplinary Graduate School (IGS) Energy Research Institute @NTU DRNTU::Engineering::Electrical and electronic engineering Image Classification is one of the key computer vision tasks. Among numerous machine learning methods, we choose the Extreme Learning Machine (ELM) for our image classification applications. This thesis contributes to four aspects of ELM netwroks. From the view of efficient input data, we have designed handcrafted feature extraction method for smile images classification. From the perspective of the distribution of random weights between the input layer and hidden layer, we have proposed and proved the effectiveness of the sparse binary ELM. Inspired by the deep architecture of deep learning, we have extended the single layer to multiple layers of ELM to achieve better performance on large image classification datasets. Finally, from the point of target coding, we have introduced and evaluated different target coding methods for image classification. Doctor of Philosophy 2019-04-02T08:48:53Z 2019-12-06T22:11:58Z 2019-04-02T08:48:53Z 2019-12-06T22:11:58Z 2019 Thesis Cui, D. (2019). Enhanced extreme learning machines for image classification. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/106446 http://hdl.handle.net/10220/47966 10.32657/10220/47966 en 161 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 |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Cui, Dongshun Enhanced extreme learning machines for image classification |
description |
Image Classification is one of the key computer vision tasks. Among numerous machine learning methods, we choose the Extreme Learning Machine (ELM) for our image classification applications. This thesis contributes to four aspects of ELM netwroks. From the view of efficient input data, we have designed handcrafted feature extraction method for smile images classification. From the perspective of the distribution of random weights between the input layer and hidden layer, we have proposed and proved the effectiveness of the sparse binary ELM. Inspired by the deep architecture of deep learning, we have extended the single layer to multiple layers of ELM to achieve better performance on large image classification datasets. Finally, from the point of target coding, we have introduced and evaluated different target coding methods for image classification. |
author2 |
Huang Guangbin |
author_facet |
Huang Guangbin Cui, Dongshun |
format |
Theses and Dissertations |
author |
Cui, Dongshun |
author_sort |
Cui, Dongshun |
title |
Enhanced extreme learning machines for image classification |
title_short |
Enhanced extreme learning machines for image classification |
title_full |
Enhanced extreme learning machines for image classification |
title_fullStr |
Enhanced extreme learning machines for image classification |
title_full_unstemmed |
Enhanced extreme learning machines for image classification |
title_sort |
enhanced extreme learning machines for image classification |
publishDate |
2019 |
url |
https://hdl.handle.net/10356/106446 http://hdl.handle.net/10220/47966 |
_version_ |
1683494615504650240 |