A Hybrid Method for Mathematical Expression Detection in Scientific Document Images
Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressio...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2020, Vol.8, p.83663-83684 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 83684 |
|---|---|
| container_issue | |
| container_start_page | 83663 |
| container_title | IEEE access |
| container_volume | 8 |
| creator | Phong, Bui Hai Hoang, Thang Manh Le, Thi-Lan |
| description | Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressions in scientific document images that usually consist of heterogeneous components (e.g., figures, tables, text and expressions). In the system, a hybrid method of two stages is proposed for the effective detection of mathematical expressions. First, the layout analysis of entire document images is introduced to improve the accuracy of text line and word segmentation. Then, both isolated and inline expressions in document images are detected. Both hand-crafted and deep learning features are extensively investigated and combined to improve the detection accuracy. Furthermore, a generic performance metric is applied to evaluate the system comprehensively. The proposed method has been evaluated on two public benchmark datasets (Marmot and GTDB). The obtained accuracies of isolated and inline expressions in the Marmot dataset are 91.18% and 81.35% while those in the GTDB dataset are 89.51% and 80.20%, respectively. The performance comparison is carried out with the conventional methods to show the outstanding effectiveness of the proposed system. Moreover, extensive experiments have been performed in order to point out the effect of document image resolution and post processing techniques on mathematical expression detection. |
| doi_str_mv | 10.1109/ACCESS.2020.2992067 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9085376</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9085376</ieee_id><doaj_id>oai_doaj_org_article_bd0bccf1c85d4421bc32cea28ba4ad62</doaj_id><sourcerecordid>2454092897</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-a5d3808c26c3fbb284b0f3ac9f4c219440e914d02b714d630002d8859f983fba3</originalsourceid><addsrcrecordid>eNpNUU1rAjEQXUoLFesv8BLoWZuv3U2OorYKSg-255BPjejGJivUf9_YLdK5vJlh3psZXlEMERwjBPnLZDqdbzZjDDEcY84xrOq7oodRxUekJNX9v_yxGKS0hzlYbpV1r9hMwOKiojdgbdtdMMCFCNay3dmjbL2WBzD_PkWbkg8NmNnW6vaa-QZstLdN653XYBb0-ZgLsDzKrU1PxYOTh2QHf9gvPl_nH9PFaPX-tpxOViNNIWtHsjSEQaZxpYlTCjOqoCNSc0c1RpxSaDmiBmJVZ6hIvhobxkruOMsESfrFstM1Qe7FKfqjjBcRpBe_jRC3Qsb8xMEKZaDS2iHNSkMpRkoTrK3ETEkqTYWz1nOndYrh62xTK_bhHJt8vsC0pJBjxus8RbopHUNK0brbVgTF1QzRmSGuZog_MzJr2LG8tfbG4JCVpK7ID79ShQo</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2454092897</pqid></control><display><type>article</type><title>A Hybrid Method for Mathematical Expression Detection in Scientific Document Images</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Phong, Bui Hai ; Hoang, Thang Manh ; Le, Thi-Lan</creator><creatorcontrib>Phong, Bui Hai ; Hoang, Thang Manh ; Le, Thi-Lan</creatorcontrib><description>Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressions in scientific document images that usually consist of heterogeneous components (e.g., figures, tables, text and expressions). In the system, a hybrid method of two stages is proposed for the effective detection of mathematical expressions. First, the layout analysis of entire document images is introduced to improve the accuracy of text line and word segmentation. Then, both isolated and inline expressions in document images are detected. Both hand-crafted and deep learning features are extensively investigated and combined to improve the detection accuracy. Furthermore, a generic performance metric is applied to evaluate the system comprehensively. The proposed method has been evaluated on two public benchmark datasets (Marmot and GTDB). The obtained accuracies of isolated and inline expressions in the Marmot dataset are 91.18% and 81.35% while those in the GTDB dataset are 89.51% and 80.20%, respectively. The performance comparison is carried out with the conventional methods to show the outstanding effectiveness of the proposed system. Moreover, extensive experiments have been performed in order to point out the effect of document image resolution and post processing techniques on mathematical expression detection.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2020.2992067</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Datasets ; document analysis ; Feature extraction ; fusion technique ; Hybrid systems ; Image resolution ; Image segmentation ; Layout ; machine learning ; Mathematical analysis ; Mathematical expression detection ; Measurement ; neural network ; Optical character recognition software ; Text analysis</subject><ispartof>IEEE access, 2020, Vol.8, p.83663-83684</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-a5d3808c26c3fbb284b0f3ac9f4c219440e914d02b714d630002d8859f983fba3</citedby><cites>FETCH-LOGICAL-c408t-a5d3808c26c3fbb284b0f3ac9f4c219440e914d02b714d630002d8859f983fba3</cites><orcidid>0000-0003-3555-5682 ; 0000-0001-9541-3905 ; 0000-0002-0542-0069</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9085376$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Phong, Bui Hai</creatorcontrib><creatorcontrib>Hoang, Thang Manh</creatorcontrib><creatorcontrib>Le, Thi-Lan</creatorcontrib><title>A Hybrid Method for Mathematical Expression Detection in Scientific Document Images</title><title>IEEE access</title><addtitle>Access</addtitle><description>Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressions in scientific document images that usually consist of heterogeneous components (e.g., figures, tables, text and expressions). In the system, a hybrid method of two stages is proposed for the effective detection of mathematical expressions. First, the layout analysis of entire document images is introduced to improve the accuracy of text line and word segmentation. Then, both isolated and inline expressions in document images are detected. Both hand-crafted and deep learning features are extensively investigated and combined to improve the detection accuracy. Furthermore, a generic performance metric is applied to evaluate the system comprehensively. The proposed method has been evaluated on two public benchmark datasets (Marmot and GTDB). The obtained accuracies of isolated and inline expressions in the Marmot dataset are 91.18% and 81.35% while those in the GTDB dataset are 89.51% and 80.20%, respectively. The performance comparison is carried out with the conventional methods to show the outstanding effectiveness of the proposed system. Moreover, extensive experiments have been performed in order to point out the effect of document image resolution and post processing techniques on mathematical expression detection.</description><subject>Datasets</subject><subject>document analysis</subject><subject>Feature extraction</subject><subject>fusion technique</subject><subject>Hybrid systems</subject><subject>Image resolution</subject><subject>Image segmentation</subject><subject>Layout</subject><subject>machine learning</subject><subject>Mathematical analysis</subject><subject>Mathematical expression detection</subject><subject>Measurement</subject><subject>neural network</subject><subject>Optical character recognition software</subject><subject>Text analysis</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUU1rAjEQXUoLFesv8BLoWZuv3U2OorYKSg-255BPjejGJivUf9_YLdK5vJlh3psZXlEMERwjBPnLZDqdbzZjDDEcY84xrOq7oodRxUekJNX9v_yxGKS0hzlYbpV1r9hMwOKiojdgbdtdMMCFCNay3dmjbL2WBzD_PkWbkg8NmNnW6vaa-QZstLdN653XYBb0-ZgLsDzKrU1PxYOTh2QHf9gvPl_nH9PFaPX-tpxOViNNIWtHsjSEQaZxpYlTCjOqoCNSc0c1RpxSaDmiBmJVZ6hIvhobxkruOMsESfrFstM1Qe7FKfqjjBcRpBe_jRC3Qsb8xMEKZaDS2iHNSkMpRkoTrK3ETEkqTYWz1nOndYrh62xTK_bhHJt8vsC0pJBjxus8RbopHUNK0brbVgTF1QzRmSGuZog_MzJr2LG8tfbG4JCVpK7ID79ShQo</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Phong, Bui Hai</creator><creator>Hoang, Thang Manh</creator><creator>Le, Thi-Lan</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-3555-5682</orcidid><orcidid>https://orcid.org/0000-0001-9541-3905</orcidid><orcidid>https://orcid.org/0000-0002-0542-0069</orcidid></search><sort><creationdate>2020</creationdate><title>A Hybrid Method for Mathematical Expression Detection in Scientific Document Images</title><author>Phong, Bui Hai ; Hoang, Thang Manh ; Le, Thi-Lan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-a5d3808c26c3fbb284b0f3ac9f4c219440e914d02b714d630002d8859f983fba3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Datasets</topic><topic>document analysis</topic><topic>Feature extraction</topic><topic>fusion technique</topic><topic>Hybrid systems</topic><topic>Image resolution</topic><topic>Image segmentation</topic><topic>Layout</topic><topic>machine learning</topic><topic>Mathematical analysis</topic><topic>Mathematical expression detection</topic><topic>Measurement</topic><topic>neural network</topic><topic>Optical character recognition software</topic><topic>Text analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Phong, Bui Hai</creatorcontrib><creatorcontrib>Hoang, Thang Manh</creatorcontrib><creatorcontrib>Le, Thi-Lan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials 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>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Phong, Bui Hai</au><au>Hoang, Thang Manh</au><au>Le, Thi-Lan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Hybrid Method for Mathematical Expression Detection in Scientific Document Images</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2020</date><risdate>2020</risdate><volume>8</volume><spage>83663</spage><epage>83684</epage><pages>83663-83684</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressions in scientific document images that usually consist of heterogeneous components (e.g., figures, tables, text and expressions). In the system, a hybrid method of two stages is proposed for the effective detection of mathematical expressions. First, the layout analysis of entire document images is introduced to improve the accuracy of text line and word segmentation. Then, both isolated and inline expressions in document images are detected. Both hand-crafted and deep learning features are extensively investigated and combined to improve the detection accuracy. Furthermore, a generic performance metric is applied to evaluate the system comprehensively. The proposed method has been evaluated on two public benchmark datasets (Marmot and GTDB). The obtained accuracies of isolated and inline expressions in the Marmot dataset are 91.18% and 81.35% while those in the GTDB dataset are 89.51% and 80.20%, respectively. The performance comparison is carried out with the conventional methods to show the outstanding effectiveness of the proposed system. Moreover, extensive experiments have been performed in order to point out the effect of document image resolution and post processing techniques on mathematical expression detection.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2020.2992067</doi><tpages>22</tpages><orcidid>https://orcid.org/0000-0003-3555-5682</orcidid><orcidid>https://orcid.org/0000-0001-9541-3905</orcidid><orcidid>https://orcid.org/0000-0002-0542-0069</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2020, Vol.8, p.83663-83684 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_9085376 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals |
| subjects | Datasets document analysis Feature extraction fusion technique Hybrid systems Image resolution Image segmentation Layout machine learning Mathematical analysis Mathematical expression detection Measurement neural network Optical character recognition software Text analysis |
| title | A Hybrid Method for Mathematical Expression Detection in Scientific Document Images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T14%3A35%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Hybrid%20Method%20for%20Mathematical%20Expression%20Detection%20in%20Scientific%20Document%20Images&rft.jtitle=IEEE%20access&rft.au=Phong,%20Bui%20Hai&rft.date=2020&rft.volume=8&rft.spage=83663&rft.epage=83684&rft.pages=83663-83684&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2020.2992067&rft_dat=%3Cproquest_ieee_%3E2454092897%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2454092897&rft_id=info:pmid/&rft_ieee_id=9085376&rft_doaj_id=oai_doaj_org_article_bd0bccf1c85d4421bc32cea28ba4ad62&rfr_iscdi=true |