No Cover Image

Conference contribution 232 views 18 downloads

Learning feature extractors for AMD classification in OCT using convolutional neural networks / Dafydd Ravenscroft; Jingjing Deng; Xianghua Xie; Louise Terry; Tom H. Margrain; Rachel V. North; Ashley Wood

Signal Processing Conference (EUSIPCO), 2017 25th European, Pages: 51 - 55

Swansea University Author: Xie, Xianghua

  • amd.pdf

    PDF | Accepted Manuscript

    © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

    Download (1.24MB)

Abstract

In this paper, we propose a two-step textural feature extraction method, which utilizes the feature learning ability of Convolutional Neural Networks (CNN) to extract a set of low level primitive filter kernels, and then generalizes the discriminative power by forming a histogram based descriptor.

Published in: Signal Processing Conference (EUSIPCO), 2017 25th European
ISSN: 2076-1465
Published: Kos, Greece Signal Processing Conference (EUSIPCO), 2017 25th European 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa33957
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2017-05-27T20:04:53Z
last_indexed 2018-07-10T13:17:40Z
id cronfa33957
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2018-07-09T15:18:58Z</datestamp><bib-version>v2</bib-version><id>33957</id><entry>2017-05-27</entry><title>Learning feature extractors for AMD classification in OCT using convolutional neural networks</title><alternativeTitle></alternativeTitle><author>Xianghua Xie</author><firstname>Xianghua</firstname><surname>Xie</surname><active>true</active><ORCID>0000-0002-2701-8660</ORCID><ethesisStudent>false</ethesisStudent><sid>b334d40963c7a2f435f06d2c26c74e11</sid><email>53b7e8cec1e3c035df428f36f80bdea5</email><emailaddr>ulOdsUw0nzyNlMFzZoDyVp320YwKTXZRCaAvm14NMEw=</emailaddr><date>2017-05-27</date><deptcode>SCS</deptcode><abstract>In this paper, we propose a two-step textural feature extraction method, which utilizes the feature learning ability of Convolutional Neural Networks (CNN) to extract a set of low level primitive filter kernels, and then generalizes the discriminative power by forming a histogram based descriptor.</abstract><type>Conference contribution</type><journal>Signal Processing Conference (EUSIPCO), 2017 25th European</journal><volume/><journalNumber/><paginationStart>51</paginationStart><paginationEnd>55</paginationEnd><publisher>Signal Processing Conference (EUSIPCO), 2017 25th European</publisher><placeOfPublication>Kos, Greece</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2076-1465</issnElectronic><keywords></keywords><publishedDay>26</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-10-26</publishedDate><doi>10.23919/EUSIPCO.2017.8081167</doi><url>http://ieeexplore.ieee.org/document/8081167/</url><notes></notes><college>College of Science</college><department>Computer Science</department><CollegeCode>CSCI</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution/><researchGroup>Visual Computing</researchGroup><supervisor/><sponsorsfunders/><grantnumber/><degreelevel/><degreename>None</degreename><lastEdited>2018-07-09T15:18:58Z</lastEdited><Created>2017-05-27T15:57:18Z</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Dafydd</firstname><surname>Ravenscroft</surname><orcid/><order>1</order></author><author><firstname>Jingjing</firstname><surname>Deng</surname><orcid/><order>2</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid/><order>3</order></author><author><firstname>Louise</firstname><surname>Terry</surname><orcid/><order>4</order></author><author><firstname>Tom H.</firstname><surname>Margrain</surname><orcid/><order>5</order></author><author><firstname>Rachel V.</firstname><surname>North</surname><orcid/><order>6</order></author><author><firstname>Ashley</firstname><surname>Wood</surname><orcid/><order>7</order></author></authors><documents><document><filename>0033957-27052017160046.pdf</filename><originalFilename>amd.pdf</originalFilename><uploaded>2017-05-27T16:00:46Z</uploaded><type>Output</type><contentLength>1274336</contentLength><contentType>application/pdf</contentType><version>AM</version><cronfaStatus>true</cronfaStatus><action>Updated Notes</action><actionDate>09/07/2018</actionDate><embargoDate>2017-12-27T00:00:00</embargoDate><documentNotes>&#xA9; 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents></rfc1807>
spelling 2018-07-09T15:18:58Z v2 33957 2017-05-27 Learning feature extractors for AMD classification in OCT using convolutional neural networks Xianghua Xie Xianghua Xie true 0000-0002-2701-8660 false b334d40963c7a2f435f06d2c26c74e11 53b7e8cec1e3c035df428f36f80bdea5 ulOdsUw0nzyNlMFzZoDyVp320YwKTXZRCaAvm14NMEw= 2017-05-27 SCS In this paper, we propose a two-step textural feature extraction method, which utilizes the feature learning ability of Convolutional Neural Networks (CNN) to extract a set of low level primitive filter kernels, and then generalizes the discriminative power by forming a histogram based descriptor. Conference contribution Signal Processing Conference (EUSIPCO), 2017 25th European 51 55 Signal Processing Conference (EUSIPCO), 2017 25th European Kos, Greece 2076-1465 26 10 2017 2017-10-26 10.23919/EUSIPCO.2017.8081167 http://ieeexplore.ieee.org/document/8081167/ College of Science Computer Science CSCI SCS Visual Computing None 2018-07-09T15:18:58Z 2017-05-27T15:57:18Z College of Science Computer Science Dafydd Ravenscroft 1 Jingjing Deng 2 Xianghua Xie 3 Louise Terry 4 Tom H. Margrain 5 Rachel V. North 6 Ashley Wood 7 0033957-27052017160046.pdf amd.pdf 2017-05-27T16:00:46Z Output 1274336 application/pdf AM true Updated Notes 09/07/2018 2017-12-27T00:00:00 © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works true eng
title Learning feature extractors for AMD classification in OCT using convolutional neural networks
spellingShingle Learning feature extractors for AMD classification in OCT using convolutional neural networks
Xie, Xianghua
title_short Learning feature extractors for AMD classification in OCT using convolutional neural networks
title_full Learning feature extractors for AMD classification in OCT using convolutional neural networks
title_fullStr Learning feature extractors for AMD classification in OCT using convolutional neural networks
title_full_unstemmed Learning feature extractors for AMD classification in OCT using convolutional neural networks
title_sort Learning feature extractors for AMD classification in OCT using convolutional neural networks
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xie, Xianghua
author Xie, Xianghua
author2 Dafydd Ravenscroft
Jingjing Deng
Xianghua Xie
Louise Terry
Tom H. Margrain
Rachel V. North
Ashley Wood
format Conference contribution
container_title Signal Processing Conference (EUSIPCO), 2017 25th European
container_start_page 51
publishDate 2017
institution Swansea University
issn 2076-1465
doi_str_mv 10.23919/EUSIPCO.2017.8081167
publisher Signal Processing Conference (EUSIPCO), 2017 25th European
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
url http://ieeexplore.ieee.org/document/8081167/
document_store_str 1
active_str 1
researchgroup_str Visual Computing
description In this paper, we propose a two-step textural feature extraction method, which utilizes the feature learning ability of Convolutional Neural Networks (CNN) to extract a set of low level primitive filter kernels, and then generalizes the discriminative power by forming a histogram based descriptor.
published_date 2017-10-26T21:42:07Z
_version_ 1642510552117805056
score 10.836733