Fast RT-LoG operator for scene text detection
This paper proposes a new real-time Laplacian of Gaussian (RT-LoG) operator for scene text detection. This method takes advantage of the Gaussian kernel distribution in the spatial/scale-space domains and kernel decomposition with the box filtering method. Two levels of optimization are given. The f...
Gespeichert in:
| Veröffentlicht in: | Journal of real-time image processing 2021-02, Vol.18 (1), p.19-36 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 36 |
|---|---|
| container_issue | 1 |
| container_start_page | 19 |
| container_title | Journal of real-time image processing |
| container_volume | 18 |
| creator | Nguyen Dinh, Cong Delalandre, Mathieu Conte, Donatello Pham, The Anh |
| description | This paper proposes a new real-time Laplacian of Gaussian (RT-LoG) operator for scene text detection. This method takes advantage of the Gaussian kernel distribution in the spatial/scale-space domains and kernel decomposition with the box filtering method. Two levels of optimization are given. The first level of optimization within the spatial domain is obtained by box mutualization. The second level of optimization within the spatial/scale-space domains is performed using a mixed method for box selection. The proposed RT-LoG operator is evaluated on the ICDAR2017 RRC-MLT dataset in terms of robustness and time processing. The results are compared with the state-of-the-art real-time operators for scene text detection. The proposed operator appears as the top performance with the best trade-off between robustness and time processing. The proposed operator can support approximately 30 frames per second (FPS) up to the Quad-HD resolution on a regular CPU architecture with a low-level latency. In addition, the proposed operator can support the full pipeline for scene text detection. Our system is competitive with the top accurate systems of the literature while processing with a difference of two orders of magnitude in term of processing resources. |
| doi_str_mv | 10.1007/s11554-020-00942-7 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_02867207v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2918675852</sourcerecordid><originalsourceid>FETCH-LOGICAL-c397t-8a00adfd2734049471035ccb5d4e910782b6bc7d2cd8546890f315d0816d5c643</originalsourceid><addsrcrecordid>eNp9kE9LAzEQxYMoWKtfwNOCJw_RSTb_9liKtsKCIPUc0iSrLXVTk1T025u6Um8ehhmG33vMPIQuCdwQAHmbCOGcYaCAARpGsTxCI6IEwYqS5vgwA5yis5TWAEKKmo8QvjcpV08L3IZZFbY-mhxi1ZVK1ve-yv4zV85nb_Mq9OfopDOb5C9--xg9398tpnPcPs4eppMW27qRGSsDYFznqKwZsIZJAjW3dskd8w0BqehSLK101DrFmVANdDXhDhQRjlvB6jG6HnxfzUZv4-rNxC8dzErPJ63e74AqISnID1LYq4HdxvC-8ynrddjFvpynaVPellxxWig6UDaGlKLvDrYE9D5CPURYnEH_RKhlEdWDKBW4f_Hxz_of1TeoBXAT</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2918675852</pqid></control><display><type>article</type><title>Fast RT-LoG operator for scene text detection</title><source>SpringerNature Journals</source><source>ProQuest Central UK/Ireland</source><source>ProQuest Central</source><creator>Nguyen Dinh, Cong ; Delalandre, Mathieu ; Conte, Donatello ; Pham, The Anh</creator><creatorcontrib>Nguyen Dinh, Cong ; Delalandre, Mathieu ; Conte, Donatello ; Pham, The Anh</creatorcontrib><description>This paper proposes a new real-time Laplacian of Gaussian (RT-LoG) operator for scene text detection. This method takes advantage of the Gaussian kernel distribution in the spatial/scale-space domains and kernel decomposition with the box filtering method. Two levels of optimization are given. The first level of optimization within the spatial domain is obtained by box mutualization. The second level of optimization within the spatial/scale-space domains is performed using a mixed method for box selection. The proposed RT-LoG operator is evaluated on the ICDAR2017 RRC-MLT dataset in terms of robustness and time processing. The results are compared with the state-of-the-art real-time operators for scene text detection. The proposed operator appears as the top performance with the best trade-off between robustness and time processing. The proposed operator can support approximately 30 frames per second (FPS) up to the Quad-HD resolution on a regular CPU architecture with a low-level latency. In addition, the proposed operator can support the full pipeline for scene text detection. Our system is competitive with the top accurate systems of the literature while processing with a difference of two orders of magnitude in term of processing resources.</description><identifier>ISSN: 1861-8200</identifier><identifier>EISSN: 1861-8219</identifier><identifier>DOI: 10.1007/s11554-020-00942-7</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Adaptation ; Approximation ; Cognitive science ; Computer Graphics ; Computer Science ; Computer Vision and Pattern Recognition ; Deadlines ; Energy consumption ; Frames per second ; Image Processing ; Image Processing and Computer Vision ; Localization ; Multimedia Information Systems ; Normal distribution ; Optimization ; Original Research Paper ; Pattern Recognition ; Performance evaluation ; Real time ; Robustness ; Signal and Image Processing ; Signal,Image and Speech Processing</subject><ispartof>Journal of real-time image processing, 2021-02, Vol.18 (1), p.19-36</ispartof><rights>Springer-Verlag GmbH Germany, part of Springer Nature 2020</rights><rights>Springer-Verlag GmbH Germany, part of Springer Nature 2020.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c397t-8a00adfd2734049471035ccb5d4e910782b6bc7d2cd8546890f315d0816d5c643</citedby><cites>FETCH-LOGICAL-c397t-8a00adfd2734049471035ccb5d4e910782b6bc7d2cd8546890f315d0816d5c643</cites><orcidid>0000-0003-0798-5511 ; 0000-0003-4642-4768</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11554-020-00942-7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2918675852?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>230,314,780,784,885,21388,27924,27925,33744,41488,42557,43805,51319,64385,64389,72469</link.rule.ids><backlink>$$Uhttps://hal.science/hal-02867207$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Nguyen Dinh, Cong</creatorcontrib><creatorcontrib>Delalandre, Mathieu</creatorcontrib><creatorcontrib>Conte, Donatello</creatorcontrib><creatorcontrib>Pham, The Anh</creatorcontrib><title>Fast RT-LoG operator for scene text detection</title><title>Journal of real-time image processing</title><addtitle>J Real-Time Image Proc</addtitle><description>This paper proposes a new real-time Laplacian of Gaussian (RT-LoG) operator for scene text detection. This method takes advantage of the Gaussian kernel distribution in the spatial/scale-space domains and kernel decomposition with the box filtering method. Two levels of optimization are given. The first level of optimization within the spatial domain is obtained by box mutualization. The second level of optimization within the spatial/scale-space domains is performed using a mixed method for box selection. The proposed RT-LoG operator is evaluated on the ICDAR2017 RRC-MLT dataset in terms of robustness and time processing. The results are compared with the state-of-the-art real-time operators for scene text detection. The proposed operator appears as the top performance with the best trade-off between robustness and time processing. The proposed operator can support approximately 30 frames per second (FPS) up to the Quad-HD resolution on a regular CPU architecture with a low-level latency. In addition, the proposed operator can support the full pipeline for scene text detection. Our system is competitive with the top accurate systems of the literature while processing with a difference of two orders of magnitude in term of processing resources.</description><subject>Adaptation</subject><subject>Approximation</subject><subject>Cognitive science</subject><subject>Computer Graphics</subject><subject>Computer Science</subject><subject>Computer Vision and Pattern Recognition</subject><subject>Deadlines</subject><subject>Energy consumption</subject><subject>Frames per second</subject><subject>Image Processing</subject><subject>Image Processing and Computer Vision</subject><subject>Localization</subject><subject>Multimedia Information Systems</subject><subject>Normal distribution</subject><subject>Optimization</subject><subject>Original Research Paper</subject><subject>Pattern Recognition</subject><subject>Performance evaluation</subject><subject>Real time</subject><subject>Robustness</subject><subject>Signal and Image Processing</subject><subject>Signal,Image and Speech Processing</subject><issn>1861-8200</issn><issn>1861-8219</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9kE9LAzEQxYMoWKtfwNOCJw_RSTb_9liKtsKCIPUc0iSrLXVTk1T025u6Um8ehhmG33vMPIQuCdwQAHmbCOGcYaCAARpGsTxCI6IEwYqS5vgwA5yis5TWAEKKmo8QvjcpV08L3IZZFbY-mhxi1ZVK1ve-yv4zV85nb_Mq9OfopDOb5C9--xg9398tpnPcPs4eppMW27qRGSsDYFznqKwZsIZJAjW3dskd8w0BqehSLK101DrFmVANdDXhDhQRjlvB6jG6HnxfzUZv4-rNxC8dzErPJ63e74AqISnID1LYq4HdxvC-8ynrddjFvpynaVPellxxWig6UDaGlKLvDrYE9D5CPURYnEH_RKhlEdWDKBW4f_Hxz_of1TeoBXAT</recordid><startdate>20210201</startdate><enddate>20210201</enddate><creator>Nguyen Dinh, Cong</creator><creator>Delalandre, Mathieu</creator><creator>Conte, Donatello</creator><creator>Pham, The Anh</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><general>Springer Verlag</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0003-0798-5511</orcidid><orcidid>https://orcid.org/0000-0003-4642-4768</orcidid></search><sort><creationdate>20210201</creationdate><title>Fast RT-LoG operator for scene text detection</title><author>Nguyen Dinh, Cong ; Delalandre, Mathieu ; Conte, Donatello ; Pham, The Anh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c397t-8a00adfd2734049471035ccb5d4e910782b6bc7d2cd8546890f315d0816d5c643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adaptation</topic><topic>Approximation</topic><topic>Cognitive science</topic><topic>Computer Graphics</topic><topic>Computer Science</topic><topic>Computer Vision and Pattern Recognition</topic><topic>Deadlines</topic><topic>Energy consumption</topic><topic>Frames per second</topic><topic>Image Processing</topic><topic>Image Processing and Computer Vision</topic><topic>Localization</topic><topic>Multimedia Information Systems</topic><topic>Normal distribution</topic><topic>Optimization</topic><topic>Original Research Paper</topic><topic>Pattern Recognition</topic><topic>Performance evaluation</topic><topic>Real time</topic><topic>Robustness</topic><topic>Signal and Image Processing</topic><topic>Signal,Image and Speech Processing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nguyen Dinh, Cong</creatorcontrib><creatorcontrib>Delalandre, Mathieu</creatorcontrib><creatorcontrib>Conte, Donatello</creatorcontrib><creatorcontrib>Pham, The Anh</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>Journal of real-time image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nguyen Dinh, Cong</au><au>Delalandre, Mathieu</au><au>Conte, Donatello</au><au>Pham, The Anh</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fast RT-LoG operator for scene text detection</atitle><jtitle>Journal of real-time image processing</jtitle><stitle>J Real-Time Image Proc</stitle><date>2021-02-01</date><risdate>2021</risdate><volume>18</volume><issue>1</issue><spage>19</spage><epage>36</epage><pages>19-36</pages><issn>1861-8200</issn><eissn>1861-8219</eissn><abstract>This paper proposes a new real-time Laplacian of Gaussian (RT-LoG) operator for scene text detection. This method takes advantage of the Gaussian kernel distribution in the spatial/scale-space domains and kernel decomposition with the box filtering method. Two levels of optimization are given. The first level of optimization within the spatial domain is obtained by box mutualization. The second level of optimization within the spatial/scale-space domains is performed using a mixed method for box selection. The proposed RT-LoG operator is evaluated on the ICDAR2017 RRC-MLT dataset in terms of robustness and time processing. The results are compared with the state-of-the-art real-time operators for scene text detection. The proposed operator appears as the top performance with the best trade-off between robustness and time processing. The proposed operator can support approximately 30 frames per second (FPS) up to the Quad-HD resolution on a regular CPU architecture with a low-level latency. In addition, the proposed operator can support the full pipeline for scene text detection. Our system is competitive with the top accurate systems of the literature while processing with a difference of two orders of magnitude in term of processing resources.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s11554-020-00942-7</doi><tpages>18</tpages><orcidid>https://orcid.org/0000-0003-0798-5511</orcidid><orcidid>https://orcid.org/0000-0003-4642-4768</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1861-8200 |
| ispartof | Journal of real-time image processing, 2021-02, Vol.18 (1), p.19-36 |
| issn | 1861-8200 1861-8219 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_02867207v1 |
| source | SpringerNature Journals; ProQuest Central UK/Ireland; ProQuest Central |
| subjects | Adaptation Approximation Cognitive science Computer Graphics Computer Science Computer Vision and Pattern Recognition Deadlines Energy consumption Frames per second Image Processing Image Processing and Computer Vision Localization Multimedia Information Systems Normal distribution Optimization Original Research Paper Pattern Recognition Performance evaluation Real time Robustness Signal and Image Processing Signal,Image and Speech Processing |
| title | Fast RT-LoG operator for scene text detection |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T05%3A26%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fast%20RT-LoG%20operator%20for%20scene%20text%20detection&rft.jtitle=Journal%20of%20real-time%20image%20processing&rft.au=Nguyen%20Dinh,%20Cong&rft.date=2021-02-01&rft.volume=18&rft.issue=1&rft.spage=19&rft.epage=36&rft.pages=19-36&rft.issn=1861-8200&rft.eissn=1861-8219&rft_id=info:doi/10.1007/s11554-020-00942-7&rft_dat=%3Cproquest_hal_p%3E2918675852%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2918675852&rft_id=info:pmid/&rfr_iscdi=true |