Two-dimensional multifractal detrended fluctuation analysis for plant identification

BACKGROUND: In this paper, a novel method is proposed to identify plant species by using the two- dimensional multifractal detrended fluctuation analysis (2D MF-DFA). Our method involves calculating a set of multifractal parameters that characterize the texture features of each plant leaf image. An...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Plant methods 2015-02, Vol.11 (1), p.12-12
Hauptverfasser: Wang, Fang, Liao, Deng-wen, Li, Jin-wei, Liao, Gui-ping
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 12
container_issue 1
container_start_page 12
container_title Plant methods
container_volume 11
creator Wang, Fang
Liao, Deng-wen
Li, Jin-wei
Liao, Gui-ping
description BACKGROUND: In this paper, a novel method is proposed to identify plant species by using the two- dimensional multifractal detrended fluctuation analysis (2D MF-DFA). Our method involves calculating a set of multifractal parameters that characterize the texture features of each plant leaf image. An index, I₀, that characterizes the relation of the intra-species variances and inter-species variances is introduced. This index is used to select three multifractal parameters for the identification process. The procedure is applied to the Swedish leaf data set containing leaves from fifteen different tree species. RESULTS: The chosen three parameters form a three-dimensional space in which the samples from the same species can be clustered together and be separated from other species. Support vector machines and kernel methods are employed to assess the identification accuracy. The resulting averaged discriminant accuracy reaches 98.4% for every two species by the 10 − fold cross validation, while the accuracy reaches 93.96% for all fifteen species. CONCLUSIONS: Our method, based on the 2D MF-DFA, provides a feasible and efficient procedure to identify plant species.
doi_str_mv 10.1186/s13007-015-0049-7
format Article
fullrecord <record><control><sourceid>gale_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_4358846</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A541553194</galeid><sourcerecordid>A541553194</sourcerecordid><originalsourceid>FETCH-LOGICAL-b585t-9c6bdf9978b9192152b28f6a1c51ece4cc9206c29eb03ff23a89bdb2aca1472c3</originalsourceid><addsrcrecordid>eNp1kktv1DAUhS0EomXgB7CBSGxgkWI7dmJvkKryqlQJiU7Xlu3Yg1ESD7YD9N9zh5SqkYq88ON-5-jeIyP0nOATQkT7NpMG467GhNcYM1l3D9Ax6VhbM0HIwzvnI_Qk5-_AENq0j9ER5V3HKG6P0Xb7K9Z9GN2UQ5z0UI3zUIJP2ha49K4kN_Wur_ww2zLrAlClgbvOIVc-pmo_6KlUoXcTyIL9SzxFj7wesnt2s2_Q1ccP27PP9cWXT-dnpxe14YKXWtrW9F7KThhJJCWcGip8q4nlxFnHrJXQo6XSGdx4TxstpOkN1VYT1lHbbNC7xXc_m9H1FnpIelD7FEadrlXUQa0rU_imdvGnYg0XgrVg8H4xMCH-x2BdsXFUS-oKUleH1FUHNq9v-kjxx-xyUWPI1g0QjYtzVqRtGZEMQ_ob9GpBd3pwKkw-gq894OqUM8J5AyBQJ_dQsHo3Bhsn5wO8rwRvVgJgivtddnrOWZ1ffl2zZGFtijkn52_nJVgd_tW9E764m_St4t9HAuDlAngdld6lkNXVJQUHjGF6IUTzB9Zl0zc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1664194012</pqid></control><display><type>article</type><title>Two-dimensional multifractal detrended fluctuation analysis for plant identification</title><source>DOAJ Directory of Open Access Journals</source><source>SpringerNature Journals</source><source>PubMed Central Open Access</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Springer Nature OA/Free Journals</source><creator>Wang, Fang ; Liao, Deng-wen ; Li, Jin-wei ; Liao, Gui-ping</creator><creatorcontrib>Wang, Fang ; Liao, Deng-wen ; Li, Jin-wei ; Liao, Gui-ping</creatorcontrib><description>BACKGROUND: In this paper, a novel method is proposed to identify plant species by using the two- dimensional multifractal detrended fluctuation analysis (2D MF-DFA). Our method involves calculating a set of multifractal parameters that characterize the texture features of each plant leaf image. An index, I₀, that characterizes the relation of the intra-species variances and inter-species variances is introduced. This index is used to select three multifractal parameters for the identification process. The procedure is applied to the Swedish leaf data set containing leaves from fifteen different tree species. RESULTS: The chosen three parameters form a three-dimensional space in which the samples from the same species can be clustered together and be separated from other species. Support vector machines and kernel methods are employed to assess the identification accuracy. The resulting averaged discriminant accuracy reaches 98.4% for every two species by the 10 − fold cross validation, while the accuracy reaches 93.96% for all fifteen species. CONCLUSIONS: Our method, based on the 2D MF-DFA, provides a feasible and efficient procedure to identify plant species.</description><identifier>ISSN: 1746-4811</identifier><identifier>EISSN: 1746-4811</identifier><identifier>DOI: 10.1186/s13007-015-0049-7</identifier><identifier>PMID: 25774206</identifier><language>eng</language><publisher>England: Springer-Verlag</publisher><subject>data collection ; leaves ; Methodology ; plant identification ; support vector machines ; texture ; trees</subject><ispartof>Plant methods, 2015-02, Vol.11 (1), p.12-12</ispartof><rights>COPYRIGHT 2015 BioMed Central Ltd.</rights><rights>Wang et al.; licensee BioMed Central. 2015</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-b585t-9c6bdf9978b9192152b28f6a1c51ece4cc9206c29eb03ff23a89bdb2aca1472c3</citedby><cites>FETCH-LOGICAL-b585t-9c6bdf9978b9192152b28f6a1c51ece4cc9206c29eb03ff23a89bdb2aca1472c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC4358846/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC4358846/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,729,782,786,866,887,27931,27932,53798,53800</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/25774206$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Fang</creatorcontrib><creatorcontrib>Liao, Deng-wen</creatorcontrib><creatorcontrib>Li, Jin-wei</creatorcontrib><creatorcontrib>Liao, Gui-ping</creatorcontrib><title>Two-dimensional multifractal detrended fluctuation analysis for plant identification</title><title>Plant methods</title><addtitle>Plant Methods</addtitle><description>BACKGROUND: In this paper, a novel method is proposed to identify plant species by using the two- dimensional multifractal detrended fluctuation analysis (2D MF-DFA). Our method involves calculating a set of multifractal parameters that characterize the texture features of each plant leaf image. An index, I₀, that characterizes the relation of the intra-species variances and inter-species variances is introduced. This index is used to select three multifractal parameters for the identification process. The procedure is applied to the Swedish leaf data set containing leaves from fifteen different tree species. RESULTS: The chosen three parameters form a three-dimensional space in which the samples from the same species can be clustered together and be separated from other species. Support vector machines and kernel methods are employed to assess the identification accuracy. The resulting averaged discriminant accuracy reaches 98.4% for every two species by the 10 − fold cross validation, while the accuracy reaches 93.96% for all fifteen species. CONCLUSIONS: Our method, based on the 2D MF-DFA, provides a feasible and efficient procedure to identify plant species.</description><subject>data collection</subject><subject>leaves</subject><subject>Methodology</subject><subject>plant identification</subject><subject>support vector machines</subject><subject>texture</subject><subject>trees</subject><issn>1746-4811</issn><issn>1746-4811</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNp1kktv1DAUhS0EomXgB7CBSGxgkWI7dmJvkKryqlQJiU7Xlu3Yg1ESD7YD9N9zh5SqkYq88ON-5-jeIyP0nOATQkT7NpMG467GhNcYM1l3D9Ax6VhbM0HIwzvnI_Qk5-_AENq0j9ER5V3HKG6P0Xb7K9Z9GN2UQ5z0UI3zUIJP2ha49K4kN_Wur_ww2zLrAlClgbvOIVc-pmo_6KlUoXcTyIL9SzxFj7wesnt2s2_Q1ccP27PP9cWXT-dnpxe14YKXWtrW9F7KThhJJCWcGip8q4nlxFnHrJXQo6XSGdx4TxstpOkN1VYT1lHbbNC7xXc_m9H1FnpIelD7FEadrlXUQa0rU_imdvGnYg0XgrVg8H4xMCH-x2BdsXFUS-oKUleH1FUHNq9v-kjxx-xyUWPI1g0QjYtzVqRtGZEMQ_ob9GpBd3pwKkw-gq894OqUM8J5AyBQJ_dQsHo3Bhsn5wO8rwRvVgJgivtddnrOWZ1ffl2zZGFtijkn52_nJVgd_tW9E764m_St4t9HAuDlAngdld6lkNXVJQUHjGF6IUTzB9Zl0zc</recordid><startdate>20150226</startdate><enddate>20150226</enddate><creator>Wang, Fang</creator><creator>Liao, Deng-wen</creator><creator>Li, Jin-wei</creator><creator>Liao, Gui-ping</creator><general>Springer-Verlag</general><general>BioMed Central Ltd</general><general>BioMed Central</general><scope>FBQ</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20150226</creationdate><title>Two-dimensional multifractal detrended fluctuation analysis for plant identification</title><author>Wang, Fang ; Liao, Deng-wen ; Li, Jin-wei ; Liao, Gui-ping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-b585t-9c6bdf9978b9192152b28f6a1c51ece4cc9206c29eb03ff23a89bdb2aca1472c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>data collection</topic><topic>leaves</topic><topic>Methodology</topic><topic>plant identification</topic><topic>support vector machines</topic><topic>texture</topic><topic>trees</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Fang</creatorcontrib><creatorcontrib>Liao, Deng-wen</creatorcontrib><creatorcontrib>Li, Jin-wei</creatorcontrib><creatorcontrib>Liao, Gui-ping</creatorcontrib><collection>AGRIS</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Plant methods</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Fang</au><au>Liao, Deng-wen</au><au>Li, Jin-wei</au><au>Liao, Gui-ping</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Two-dimensional multifractal detrended fluctuation analysis for plant identification</atitle><jtitle>Plant methods</jtitle><addtitle>Plant Methods</addtitle><date>2015-02-26</date><risdate>2015</risdate><volume>11</volume><issue>1</issue><spage>12</spage><epage>12</epage><pages>12-12</pages><issn>1746-4811</issn><eissn>1746-4811</eissn><abstract>BACKGROUND: In this paper, a novel method is proposed to identify plant species by using the two- dimensional multifractal detrended fluctuation analysis (2D MF-DFA). Our method involves calculating a set of multifractal parameters that characterize the texture features of each plant leaf image. An index, I₀, that characterizes the relation of the intra-species variances and inter-species variances is introduced. This index is used to select three multifractal parameters for the identification process. The procedure is applied to the Swedish leaf data set containing leaves from fifteen different tree species. RESULTS: The chosen three parameters form a three-dimensional space in which the samples from the same species can be clustered together and be separated from other species. Support vector machines and kernel methods are employed to assess the identification accuracy. The resulting averaged discriminant accuracy reaches 98.4% for every two species by the 10 − fold cross validation, while the accuracy reaches 93.96% for all fifteen species. CONCLUSIONS: Our method, based on the 2D MF-DFA, provides a feasible and efficient procedure to identify plant species.</abstract><cop>England</cop><pub>Springer-Verlag</pub><pmid>25774206</pmid><doi>10.1186/s13007-015-0049-7</doi><tpages>1</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1746-4811
ispartof Plant methods, 2015-02, Vol.11 (1), p.12-12
issn 1746-4811
1746-4811
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_4358846
source DOAJ Directory of Open Access Journals; SpringerNature Journals; PubMed Central Open Access; EZB-FREE-00999 freely available EZB journals; PubMed Central; Springer Nature OA/Free Journals
subjects data collection
leaves
Methodology
plant identification
support vector machines
texture
trees
title Two-dimensional multifractal detrended fluctuation analysis for plant identification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T13%3A16%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Two-dimensional%20multifractal%20detrended%20fluctuation%20analysis%20for%20plant%20identification&rft.jtitle=Plant%20methods&rft.au=Wang,%20Fang&rft.date=2015-02-26&rft.volume=11&rft.issue=1&rft.spage=12&rft.epage=12&rft.pages=12-12&rft.issn=1746-4811&rft.eissn=1746-4811&rft_id=info:doi/10.1186/s13007-015-0049-7&rft_dat=%3Cgale_pubme%3EA541553194%3C/gale_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1664194012&rft_id=info:pmid/25774206&rft_galeid=A541553194&rfr_iscdi=true