Separation of specular and diffuse components using tensor voting in color images

Most methods for the detection and removal of specular reflections suffer from nonuniform highlight regions and/or nonconverged artifacts induced by discontinuities in the surface colors, especially when dealing with highly textured, multicolored images. In this paper, a novel noniterative and prede...

Full description

Saved in:
Bibliographic Details
Published in:Applied optics (2004) 2014-11, Vol.53 (33), p.7924-7936
Main Authors: Nguyen, Tam, Vo, Quang Nhat, Yang, Hyung-Jeong, Kim, Soo-Hyung, Lee, Guee-Sang
Format: Article
Language:English
Subjects:
Color
Color imagery
Diffusion
Mathematical analysis
Pixels
Tensors
Voting
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c460t-b3f9e8b9e4dd05c57123ba2ba2820d0d5ac8e71b2fc1a5aa65037b68753efefd3
cites
container_end_page 7936
container_issue 33
container_start_page 7924
container_title Applied optics (2004)
container_volume 53
creator Nguyen, Tam
Vo, Quang Nhat
Yang, Hyung-Jeong
Kim, Soo-Hyung
Lee, Guee-Sang
description Most methods for the detection and removal of specular reflections suffer from nonuniform highlight regions and/or nonconverged artifacts induced by discontinuities in the surface colors, especially when dealing with highly textured, multicolored images. In this paper, a novel noniterative and predefined constraint-free method based on tensor voting is proposed to detect and remove the highlight components of a single color image. The distribution of diffuse and specular pixels in the original image is determined using tensors' saliency analysis, instead of comparing color information among neighbor pixels. The achieved diffuse reflectance distribution is used to remove specularity components. The proposed method is evaluated quantitatively and qualitatively over a dataset of highly textured, multicolor images. The experimental results show that our result outperforms other state-of-the-art techniques.
doi_str_mv 10.1364/AO.53.007924
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_miscellaneous_1808120802</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1808120802</sourcerecordid><originalsourceid>FETCH-LOGICAL-c460t-b3f9e8b9e4dd05c57123ba2ba2820d0d5ac8e71b2fc1a5aa65037b68753efefd3</originalsourceid><addsrcrecordid>eNo1kE1LxDAQhoMo7rp68yw5euk6SZqPHpfFL1hYRAVvJW0mS6VNatMK_nsrKgy888DDMLyEXDJYM6Hym81-LcUaQBc8PyJLzqTMBFPymCzntcgYN28LcpbSO4CQeaFPyYJLBdqoYkmenrG3gx2bGGj0NPVYT60dqA2Ousb7KSGtY9fHgGFMdEpNONARQ4oD_YzjDzVhNtqZm84eMJ2TE2_bhBd_uSKvd7cv24dst79_3G52WZ0rGLNK-AJNVWDuHMhaasZFZfk8hoMDJ21tULOK-5pZaa2SIHSljJYCPXonVuT6924_xI8J01h2TaqxbW3AOKWSGTCMgwE-q1d_6lR16Mp-mF8dvsr_GsQ3Vwdfyg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1808120802</pqid></control><display><type>article</type><title>Separation of specular and diffuse components using tensor voting in color images</title><source>Optica Publishing Group (OPG)</source><creator>Nguyen, Tam ; Vo, Quang Nhat ; Yang, Hyung-Jeong ; Kim, Soo-Hyung ; Lee, Guee-Sang</creator><creatorcontrib>Nguyen, Tam ; Vo, Quang Nhat ; Yang, Hyung-Jeong ; Kim, Soo-Hyung ; Lee, Guee-Sang</creatorcontrib><description>Most methods for the detection and removal of specular reflections suffer from nonuniform highlight regions and/or nonconverged artifacts induced by discontinuities in the surface colors, especially when dealing with highly textured, multicolored images. In this paper, a novel noniterative and predefined constraint-free method based on tensor voting is proposed to detect and remove the highlight components of a single color image. The distribution of diffuse and specular pixels in the original image is determined using tensors' saliency analysis, instead of comparing color information among neighbor pixels. The achieved diffuse reflectance distribution is used to remove specularity components. The proposed method is evaluated quantitatively and qualitatively over a dataset of highly textured, multicolor images. The experimental results show that our result outperforms other state-of-the-art techniques.</description><identifier>ISSN: 1559-128X</identifier><identifier>EISSN: 2155-3165</identifier><identifier>DOI: 10.1364/AO.53.007924</identifier><identifier>PMID: 25607869</identifier><language>eng</language><publisher>United States</publisher><subject>Color ; Color imagery ; Diffusion ; Mathematical analysis ; Pixels ; Tensors ; Voting</subject><ispartof>Applied optics (2004), 2014-11, Vol.53 (33), p.7924-7936</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c460t-b3f9e8b9e4dd05c57123ba2ba2820d0d5ac8e71b2fc1a5aa65037b68753efefd3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/25607869$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Nguyen, Tam</creatorcontrib><creatorcontrib>Vo, Quang Nhat</creatorcontrib><creatorcontrib>Yang, Hyung-Jeong</creatorcontrib><creatorcontrib>Kim, Soo-Hyung</creatorcontrib><creatorcontrib>Lee, Guee-Sang</creatorcontrib><title>Separation of specular and diffuse components using tensor voting in color images</title><title>Applied optics (2004)</title><addtitle>Appl Opt</addtitle><description>Most methods for the detection and removal of specular reflections suffer from nonuniform highlight regions and/or nonconverged artifacts induced by discontinuities in the surface colors, especially when dealing with highly textured, multicolored images. In this paper, a novel noniterative and predefined constraint-free method based on tensor voting is proposed to detect and remove the highlight components of a single color image. The distribution of diffuse and specular pixels in the original image is determined using tensors' saliency analysis, instead of comparing color information among neighbor pixels. The achieved diffuse reflectance distribution is used to remove specularity components. The proposed method is evaluated quantitatively and qualitatively over a dataset of highly textured, multicolor images. The experimental results show that our result outperforms other state-of-the-art techniques.</description><subject>Color</subject><subject>Color imagery</subject><subject>Diffusion</subject><subject>Mathematical analysis</subject><subject>Pixels</subject><subject>Tensors</subject><subject>Voting</subject><issn>1559-128X</issn><issn>2155-3165</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNo1kE1LxDAQhoMo7rp68yw5euk6SZqPHpfFL1hYRAVvJW0mS6VNatMK_nsrKgy888DDMLyEXDJYM6Hym81-LcUaQBc8PyJLzqTMBFPymCzntcgYN28LcpbSO4CQeaFPyYJLBdqoYkmenrG3gx2bGGj0NPVYT60dqA2Ousb7KSGtY9fHgGFMdEpNONARQ4oD_YzjDzVhNtqZm84eMJ2TE2_bhBd_uSKvd7cv24dst79_3G52WZ0rGLNK-AJNVWDuHMhaasZFZfk8hoMDJ21tULOK-5pZaa2SIHSljJYCPXonVuT6924_xI8J01h2TaqxbW3AOKWSGTCMgwE-q1d_6lR16Mp-mF8dvsr_GsQ3Vwdfyg</recordid><startdate>20141120</startdate><enddate>20141120</enddate><creator>Nguyen, Tam</creator><creator>Vo, Quang Nhat</creator><creator>Yang, Hyung-Jeong</creator><creator>Kim, Soo-Hyung</creator><creator>Lee, Guee-Sang</creator><scope>NPM</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20141120</creationdate><title>Separation of specular and diffuse components using tensor voting in color images</title><author>Nguyen, Tam ; Vo, Quang Nhat ; Yang, Hyung-Jeong ; Kim, Soo-Hyung ; Lee, Guee-Sang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c460t-b3f9e8b9e4dd05c57123ba2ba2820d0d5ac8e71b2fc1a5aa65037b68753efefd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Color</topic><topic>Color imagery</topic><topic>Diffusion</topic><topic>Mathematical analysis</topic><topic>Pixels</topic><topic>Tensors</topic><topic>Voting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nguyen, Tam</creatorcontrib><creatorcontrib>Vo, Quang Nhat</creatorcontrib><creatorcontrib>Yang, Hyung-Jeong</creatorcontrib><creatorcontrib>Kim, Soo-Hyung</creatorcontrib><creatorcontrib>Lee, Guee-Sang</creatorcontrib><collection>PubMed</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Applied optics (2004)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nguyen, Tam</au><au>Vo, Quang Nhat</au><au>Yang, Hyung-Jeong</au><au>Kim, Soo-Hyung</au><au>Lee, Guee-Sang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Separation of specular and diffuse components using tensor voting in color images</atitle><jtitle>Applied optics (2004)</jtitle><addtitle>Appl Opt</addtitle><date>2014-11-20</date><risdate>2014</risdate><volume>53</volume><issue>33</issue><spage>7924</spage><epage>7936</epage><pages>7924-7936</pages><issn>1559-128X</issn><eissn>2155-3165</eissn><abstract>Most methods for the detection and removal of specular reflections suffer from nonuniform highlight regions and/or nonconverged artifacts induced by discontinuities in the surface colors, especially when dealing with highly textured, multicolored images. In this paper, a novel noniterative and predefined constraint-free method based on tensor voting is proposed to detect and remove the highlight components of a single color image. The distribution of diffuse and specular pixels in the original image is determined using tensors' saliency analysis, instead of comparing color information among neighbor pixels. The achieved diffuse reflectance distribution is used to remove specularity components. The proposed method is evaluated quantitatively and qualitatively over a dataset of highly textured, multicolor images. The experimental results show that our result outperforms other state-of-the-art techniques.</abstract><cop>United States</cop><pmid>25607869</pmid><doi>10.1364/AO.53.007924</doi><tpages>13</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1559-128X
ispartof Applied optics (2004), 2014-11, Vol.53 (33), p.7924-7936
issn 1559-128X
2155-3165
language eng
recordid cdi_proquest_miscellaneous_1808120802
source Optica Publishing Group (OPG)
subjects Color
Color imagery
Diffusion
Mathematical analysis
Pixels
Tensors
Voting
title Separation of specular and diffuse components using tensor voting in color images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T22%3A30%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Separation%20of%20specular%20and%20diffuse%20components%20using%20tensor%20voting%20in%20color%20images&rft.jtitle=Applied%20optics%20(2004)&rft.au=Nguyen,%20Tam&rft.date=2014-11-20&rft.volume=53&rft.issue=33&rft.spage=7924&rft.epage=7936&rft.pages=7924-7936&rft.issn=1559-128X&rft.eissn=2155-3165&rft_id=info:doi/10.1364/AO.53.007924&rft_dat=%3Cproquest_pubme%3E1808120802%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c460t-b3f9e8b9e4dd05c57123ba2ba2820d0d5ac8e71b2fc1a5aa65037b68753efefd3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1808120802&rft_id=info:pmid/25607869&rfr_iscdi=true