Target Segmentation in Complex Environment Using Fractal Features

By analysis of the discrete fractal Brownian random field model, an intelligent segmentation algorithm is proposed to process targets in complex environment. Firstly, to smooth the rough background texture, four-direction gradients are extracted out for filter which would obviously reduce singular v...

Full description

Saved in:
Bibliographic Details
Main Authors: Ding Su, Qiheng Zhang, Shenghua Xie
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
BP NN
Content addressable storage
Equations
Fractal
Fractals
Mathematical model
Multi-features
Neural networks
Optical control
Optical filters
Pattern recognition
Robustness
Segmentation
Smooth
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 83
container_issue
container_start_page 79
container_title
container_volume 1
creator Ding Su
Qiheng Zhang
Shenghua Xie
description By analysis of the discrete fractal Brownian random field model, an intelligent segmentation algorithm is proposed to process targets in complex environment. Firstly, to smooth the rough background texture, four-direction gradients are extracted out for filter which would obviously reduce singular values with variable gray intensity distribution. Secondly, a new fractal parameter, named fractal modulation degree, is computed out to highlight immanent diversities of target and background. Then, passing through three-layer BP NN, multi-features are trained to obtain rational weight values and perform pattern recognition. Eventually, the contour of target is segmented out. Abundant experiments support the scheme's satisfying validity and reliability
doi_str_mv 10.1109/COGINF.2006.365680
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4216395</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4216395</ieee_id><sourcerecordid>4216395</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-a3ccaae3ebb8c6dc84c830f117c758ad5bc14047fd15794cdb0b0c747bfffebb3</originalsourceid><addsrcrecordid>eNotjs1KxDAYRQMiKGNfQDd5gdak-e1yKFMVBl04sx6S9EuJtOmQRtG3t4PezV1czuUgdE9JRSlpHtu3p5fXrqoJkRWTQmpyhYpGacprzglXorlBxbJ8kDWsYUqKW7Q9mDRAxu8wTBCzyWGOOETcztN5hG-8i18hzfGy4eMS4oC7ZFw2I-7A5M8Eyx269mZcoPjvDTp2u0P7XO5XnXa7LwNVIpeGOWcMMLBWO9k7zZ1mxFOqnBLa9MI6epH0PRWq4a63xBKnuLLe-xViG_Tw9xsA4HROYTLp58RrKlkj2C-x-Eq0</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Target Segmentation in Complex Environment Using Fractal Features</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ding Su ; Qiheng Zhang ; Shenghua Xie</creator><creatorcontrib>Ding Su ; Qiheng Zhang ; Shenghua Xie</creatorcontrib><description>By analysis of the discrete fractal Brownian random field model, an intelligent segmentation algorithm is proposed to process targets in complex environment. Firstly, to smooth the rough background texture, four-direction gradients are extracted out for filter which would obviously reduce singular values with variable gray intensity distribution. Secondly, a new fractal parameter, named fractal modulation degree, is computed out to highlight immanent diversities of target and background. Then, passing through three-layer BP NN, multi-features are trained to obtain rational weight values and perform pattern recognition. Eventually, the contour of target is segmented out. Abundant experiments support the scheme's satisfying validity and reliability</description><identifier>ISBN: 9781424404759</identifier><identifier>ISBN: 1424404754</identifier><identifier>DOI: 10.1109/COGINF.2006.365680</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; BP NN ; Content addressable storage ; Equations ; Fractal ; Fractals ; Mathematical model ; Multi-features ; Neural networks ; Optical control ; Optical filters ; Pattern recognition ; Robustness ; Segmentation ; Smooth</subject><ispartof>2006 5th IEEE International Conference on Cognitive Informatics, 2006, Vol.1, p.79-83</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4216395$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,27904,54899</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4216395$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ding Su</creatorcontrib><creatorcontrib>Qiheng Zhang</creatorcontrib><creatorcontrib>Shenghua Xie</creatorcontrib><title>Target Segmentation in Complex Environment Using Fractal Features</title><title>2006 5th IEEE International Conference on Cognitive Informatics</title><addtitle>COGINF</addtitle><description>By analysis of the discrete fractal Brownian random field model, an intelligent segmentation algorithm is proposed to process targets in complex environment. Firstly, to smooth the rough background texture, four-direction gradients are extracted out for filter which would obviously reduce singular values with variable gray intensity distribution. Secondly, a new fractal parameter, named fractal modulation degree, is computed out to highlight immanent diversities of target and background. Then, passing through three-layer BP NN, multi-features are trained to obtain rational weight values and perform pattern recognition. Eventually, the contour of target is segmented out. Abundant experiments support the scheme's satisfying validity and reliability</description><subject>Algorithm design and analysis</subject><subject>BP NN</subject><subject>Content addressable storage</subject><subject>Equations</subject><subject>Fractal</subject><subject>Fractals</subject><subject>Mathematical model</subject><subject>Multi-features</subject><subject>Neural networks</subject><subject>Optical control</subject><subject>Optical filters</subject><subject>Pattern recognition</subject><subject>Robustness</subject><subject>Segmentation</subject><subject>Smooth</subject><isbn>9781424404759</isbn><isbn>1424404754</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjs1KxDAYRQMiKGNfQDd5gdak-e1yKFMVBl04sx6S9EuJtOmQRtG3t4PezV1czuUgdE9JRSlpHtu3p5fXrqoJkRWTQmpyhYpGacprzglXorlBxbJ8kDWsYUqKW7Q9mDRAxu8wTBCzyWGOOETcztN5hG-8i18hzfGy4eMS4oC7ZFw2I-7A5M8Eyx269mZcoPjvDTp2u0P7XO5XnXa7LwNVIpeGOWcMMLBWO9k7zZ1mxFOqnBLa9MI6epH0PRWq4a63xBKnuLLe-xViG_Tw9xsA4HROYTLp58RrKlkj2C-x-Eq0</recordid><startdate>200607</startdate><enddate>200607</enddate><creator>Ding Su</creator><creator>Qiheng Zhang</creator><creator>Shenghua Xie</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200607</creationdate><title>Target Segmentation in Complex Environment Using Fractal Features</title><author>Ding Su ; Qiheng Zhang ; Shenghua Xie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-a3ccaae3ebb8c6dc84c830f117c758ad5bc14047fd15794cdb0b0c747bfffebb3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Algorithm design and analysis</topic><topic>BP NN</topic><topic>Content addressable storage</topic><topic>Equations</topic><topic>Fractal</topic><topic>Fractals</topic><topic>Mathematical model</topic><topic>Multi-features</topic><topic>Neural networks</topic><topic>Optical control</topic><topic>Optical filters</topic><topic>Pattern recognition</topic><topic>Robustness</topic><topic>Segmentation</topic><topic>Smooth</topic><toplevel>online_resources</toplevel><creatorcontrib>Ding Su</creatorcontrib><creatorcontrib>Qiheng Zhang</creatorcontrib><creatorcontrib>Shenghua Xie</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore (Online service)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ding Su</au><au>Qiheng Zhang</au><au>Shenghua Xie</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Target Segmentation in Complex Environment Using Fractal Features</atitle><btitle>2006 5th IEEE International Conference on Cognitive Informatics</btitle><stitle>COGINF</stitle><date>2006-07</date><risdate>2006</risdate><volume>1</volume><spage>79</spage><epage>83</epage><pages>79-83</pages><isbn>9781424404759</isbn><isbn>1424404754</isbn><abstract>By analysis of the discrete fractal Brownian random field model, an intelligent segmentation algorithm is proposed to process targets in complex environment. Firstly, to smooth the rough background texture, four-direction gradients are extracted out for filter which would obviously reduce singular values with variable gray intensity distribution. Secondly, a new fractal parameter, named fractal modulation degree, is computed out to highlight immanent diversities of target and background. Then, passing through three-layer BP NN, multi-features are trained to obtain rational weight values and perform pattern recognition. Eventually, the contour of target is segmented out. Abundant experiments support the scheme's satisfying validity and reliability</abstract><pub>IEEE</pub><doi>10.1109/COGINF.2006.365680</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781424404759
ispartof 2006 5th IEEE International Conference on Cognitive Informatics, 2006, Vol.1, p.79-83
issn
language eng
recordid cdi_ieee_primary_4216395
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Algorithm design and analysis
BP NN
Content addressable storage
Equations
Fractal
Fractals
Mathematical model
Multi-features
Neural networks
Optical control
Optical filters
Pattern recognition
Robustness
Segmentation
Smooth
title Target Segmentation in Complex Environment Using Fractal Features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T22%3A38%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Target%20Segmentation%20in%20Complex%20Environment%20Using%20Fractal%20Features&rft.btitle=2006%205th%20IEEE%20International%20Conference%20on%20Cognitive%20Informatics&rft.au=Ding%20Su&rft.date=2006-07&rft.volume=1&rft.spage=79&rft.epage=83&rft.pages=79-83&rft.isbn=9781424404759&rft.isbn_list=1424404754&rft_id=info:doi/10.1109/COGINF.2006.365680&rft_dat=%3Cieee_6IE%3E4216395%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-a3ccaae3ebb8c6dc84c830f117c758ad5bc14047fd15794cdb0b0c747bfffebb3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4216395&rfr_iscdi=true