Statistics of Natural Stochastic Textures and Their Application in Image Denoising
Natural stochastic textures (NSTs), characterized by their fine details, are prone to corruption by artifacts, introduced during the image acquisition process by the combined effect of blur and noise. While many successful algorithms exist for image restoration and enhancement, the restoration of na...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on image processing 2016-05, Vol.25 (5), p.2130-2145 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 2145 |
---|---|
container_issue | 5 |
container_start_page | 2130 |
container_title | IEEE transactions on image processing |
container_volume | 25 |
creator | Zachevsky, Ido Zeevi, Yehoshua Y. Josh |
description | Natural stochastic textures (NSTs), characterized by their fine details, are prone to corruption by artifacts, introduced during the image acquisition process by the combined effect of blur and noise. While many successful algorithms exist for image restoration and enhancement, the restoration of natural textures and textured images based on suitable statistical models has yet to be further improved. We examine the statistical properties of NST using three image databases. We show that the Gaussian distribution is suitable for many NST, while other natural textures can be properly represented by a model that separates the image into two layers; one of these layers contains the structural elements of smooth areas and edges, while the other contains the statistically Gaussian textural details. Based on these statistical properties, an algorithm for the denoising of natural images containing NST is proposed, using patch-based fractional Brownian motion model and regularization by means of anisotropic diffusion. It is illustrated that this algorithm successfully recovers both missing textural details and structural attributes that characterize natural images. The algorithm is compared with classical as well as the state-of-the-art denoising algorithms. |
doi_str_mv | 10.1109/TIP.2016.2539689 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_1787034879</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7428912</ieee_id><sourcerecordid>4046288201</sourcerecordid><originalsourceid>FETCH-LOGICAL-c380t-18dd2e6ac5f7c0ffd81b8ec9296e2c00f689ec334ff9f2f227f5c22e51979ef93</originalsourceid><addsrcrecordid>eNqFkU1r3DAQhkVpaD7aeyEQBLnk4s2MLFnSMST9WFiS0t2ejSKPEgWvvbVsaP59tOw2h1xykhg97wyjh7GvCDNEsJer-a-ZAKxmQpW2MvYDO0IrsQCQ4mO-g9KFRmkP2XFKTwAoFVaf2KHQIJUU5RH7vRzdGNMYfeJ94LdunAbX8uXY-0e3LfMV_cs1Stx1DV89Uhz41WbTRp9zfcdjx-dr90D8hro-ptg9fGYHwbWJvuzPE_bn-7fV9c9icfdjfn21KHxpYCzQNI2gynkVtIcQGoP3hrwVtiLhAULeh3xZyhBsEEEIHZQXghRabSnY8oRd7Ppuhv7vRGms1zF5alvXUT-lGo1QSmtA8z6qdf42KS1m9PwN-tRPQ5cXyZTRUEqjt7NhR_mhT2mgUG-GuHbDc41Qb9XUWU29VVPv1eTI2b7xdL-m5jXw30UGTndAJKLXZy2FsSjKF196kV0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1787034879</pqid></control><display><type>article</type><title>Statistics of Natural Stochastic Textures and Their Application in Image Denoising</title><source>IEEE Electronic Library (IEL)</source><creator>Zachevsky, Ido ; Zeevi, Yehoshua Y. Josh</creator><creatorcontrib>Zachevsky, Ido ; Zeevi, Yehoshua Y. Josh</creatorcontrib><description>Natural stochastic textures (NSTs), characterized by their fine details, are prone to corruption by artifacts, introduced during the image acquisition process by the combined effect of blur and noise. While many successful algorithms exist for image restoration and enhancement, the restoration of natural textures and textured images based on suitable statistical models has yet to be further improved. We examine the statistical properties of NST using three image databases. We show that the Gaussian distribution is suitable for many NST, while other natural textures can be properly represented by a model that separates the image into two layers; one of these layers contains the structural elements of smooth areas and edges, while the other contains the statistically Gaussian textural details. Based on these statistical properties, an algorithm for the denoising of natural images containing NST is proposed, using patch-based fractional Brownian motion model and regularization by means of anisotropic diffusion. It is illustrated that this algorithm successfully recovers both missing textural details and structural attributes that characterize natural images. The algorithm is compared with classical as well as the state-of-the-art denoising algorithms.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2016.2539689</identifier><identifier>PMID: 27045423</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Algorithms ; Anisotropic magnetoresistance ; Anisotropy ; Correlation ; denoising ; Eigenvalues and eigenfunctions ; fractional Brownian motion ; Histograms ; Image edge detection ; image modelling ; Noise reduction ; Normal distribution ; Restoration ; self-similarity ; Stochastic processes ; Stochastic texture restoration ; Stochasticity ; Surface layer ; Texture</subject><ispartof>IEEE transactions on image processing, 2016-05, Vol.25 (5), p.2130-2145</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2016</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c380t-18dd2e6ac5f7c0ffd81b8ec9296e2c00f689ec334ff9f2f227f5c22e51979ef93</citedby><cites>FETCH-LOGICAL-c380t-18dd2e6ac5f7c0ffd81b8ec9296e2c00f689ec334ff9f2f227f5c22e51979ef93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7428912$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7428912$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/27045423$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zachevsky, Ido</creatorcontrib><creatorcontrib>Zeevi, Yehoshua Y. Josh</creatorcontrib><title>Statistics of Natural Stochastic Textures and Their Application in Image Denoising</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>Natural stochastic textures (NSTs), characterized by their fine details, are prone to corruption by artifacts, introduced during the image acquisition process by the combined effect of blur and noise. While many successful algorithms exist for image restoration and enhancement, the restoration of natural textures and textured images based on suitable statistical models has yet to be further improved. We examine the statistical properties of NST using three image databases. We show that the Gaussian distribution is suitable for many NST, while other natural textures can be properly represented by a model that separates the image into two layers; one of these layers contains the structural elements of smooth areas and edges, while the other contains the statistically Gaussian textural details. Based on these statistical properties, an algorithm for the denoising of natural images containing NST is proposed, using patch-based fractional Brownian motion model and regularization by means of anisotropic diffusion. It is illustrated that this algorithm successfully recovers both missing textural details and structural attributes that characterize natural images. The algorithm is compared with classical as well as the state-of-the-art denoising algorithms.</description><subject>Algorithms</subject><subject>Anisotropic magnetoresistance</subject><subject>Anisotropy</subject><subject>Correlation</subject><subject>denoising</subject><subject>Eigenvalues and eigenfunctions</subject><subject>fractional Brownian motion</subject><subject>Histograms</subject><subject>Image edge detection</subject><subject>image modelling</subject><subject>Noise reduction</subject><subject>Normal distribution</subject><subject>Restoration</subject><subject>self-similarity</subject><subject>Stochastic processes</subject><subject>Stochastic texture restoration</subject><subject>Stochasticity</subject><subject>Surface layer</subject><subject>Texture</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqFkU1r3DAQhkVpaD7aeyEQBLnk4s2MLFnSMST9WFiS0t2ejSKPEgWvvbVsaP59tOw2h1xykhg97wyjh7GvCDNEsJer-a-ZAKxmQpW2MvYDO0IrsQCQ4mO-g9KFRmkP2XFKTwAoFVaf2KHQIJUU5RH7vRzdGNMYfeJ94LdunAbX8uXY-0e3LfMV_cs1Stx1DV89Uhz41WbTRp9zfcdjx-dr90D8hro-ptg9fGYHwbWJvuzPE_bn-7fV9c9icfdjfn21KHxpYCzQNI2gynkVtIcQGoP3hrwVtiLhAULeh3xZyhBsEEEIHZQXghRabSnY8oRd7Ppuhv7vRGms1zF5alvXUT-lGo1QSmtA8z6qdf42KS1m9PwN-tRPQ5cXyZTRUEqjt7NhR_mhT2mgUG-GuHbDc41Qb9XUWU29VVPv1eTI2b7xdL-m5jXw30UGTndAJKLXZy2FsSjKF196kV0</recordid><startdate>20160501</startdate><enddate>20160501</enddate><creator>Zachevsky, Ido</creator><creator>Zeevi, Yehoshua Y. Josh</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20160501</creationdate><title>Statistics of Natural Stochastic Textures and Their Application in Image Denoising</title><author>Zachevsky, Ido ; Zeevi, Yehoshua Y. Josh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c380t-18dd2e6ac5f7c0ffd81b8ec9296e2c00f689ec334ff9f2f227f5c22e51979ef93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Anisotropic magnetoresistance</topic><topic>Anisotropy</topic><topic>Correlation</topic><topic>denoising</topic><topic>Eigenvalues and eigenfunctions</topic><topic>fractional Brownian motion</topic><topic>Histograms</topic><topic>Image edge detection</topic><topic>image modelling</topic><topic>Noise reduction</topic><topic>Normal distribution</topic><topic>Restoration</topic><topic>self-similarity</topic><topic>Stochastic processes</topic><topic>Stochastic texture restoration</topic><topic>Stochasticity</topic><topic>Surface layer</topic><topic>Texture</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zachevsky, Ido</creatorcontrib><creatorcontrib>Zeevi, Yehoshua Y. Josh</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zachevsky, Ido</au><au>Zeevi, Yehoshua Y. Josh</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Statistics of Natural Stochastic Textures and Their Application in Image Denoising</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2016-05-01</date><risdate>2016</risdate><volume>25</volume><issue>5</issue><spage>2130</spage><epage>2145</epage><pages>2130-2145</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>Natural stochastic textures (NSTs), characterized by their fine details, are prone to corruption by artifacts, introduced during the image acquisition process by the combined effect of blur and noise. While many successful algorithms exist for image restoration and enhancement, the restoration of natural textures and textured images based on suitable statistical models has yet to be further improved. We examine the statistical properties of NST using three image databases. We show that the Gaussian distribution is suitable for many NST, while other natural textures can be properly represented by a model that separates the image into two layers; one of these layers contains the structural elements of smooth areas and edges, while the other contains the statistically Gaussian textural details. Based on these statistical properties, an algorithm for the denoising of natural images containing NST is proposed, using patch-based fractional Brownian motion model and regularization by means of anisotropic diffusion. It is illustrated that this algorithm successfully recovers both missing textural details and structural attributes that characterize natural images. The algorithm is compared with classical as well as the state-of-the-art denoising algorithms.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>27045423</pmid><doi>10.1109/TIP.2016.2539689</doi><tpages>16</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1057-7149 |
ispartof | IEEE transactions on image processing, 2016-05, Vol.25 (5), p.2130-2145 |
issn | 1057-7149 1941-0042 |
language | eng |
recordid | cdi_proquest_journals_1787034879 |
source | IEEE Electronic Library (IEL) |
subjects | Algorithms Anisotropic magnetoresistance Anisotropy Correlation denoising Eigenvalues and eigenfunctions fractional Brownian motion Histograms Image edge detection image modelling Noise reduction Normal distribution Restoration self-similarity Stochastic processes Stochastic texture restoration Stochasticity Surface layer Texture |
title | Statistics of Natural Stochastic Textures and Their Application in Image Denoising |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T17%3A55%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Statistics%20of%20Natural%20Stochastic%20Textures%20and%20Their%20Application%20in%20Image%20Denoising&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Zachevsky,%20Ido&rft.date=2016-05-01&rft.volume=25&rft.issue=5&rft.spage=2130&rft.epage=2145&rft.pages=2130-2145&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2016.2539689&rft_dat=%3Cproquest_RIE%3E4046288201%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1787034879&rft_id=info:pmid/27045423&rft_ieee_id=7428912&rfr_iscdi=true |