PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large num...
Gespeichert in:
| Veröffentlicht in: | 2020 25th International Conference on Pattern Recognition (ICPR) S. 4363 - 4370 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
10.01.2021
|
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on realworld datasets have been conducted to show that our method outperforms baselines methods by significant margins. Our code is available at https://github.com/wenwenyu/PICK-pytorch. |
|---|---|
| AbstractList | Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on realworld datasets have been conducted to show that our method outperforms baselines methods by significant margins. Our code is available at https://github.com/wenwenyu/PICK-pytorch. |
| Author | Yu, Wenwen Gong, Ping Xiao, Rong Lu, Ning Qi, Xianbiao |
| Author_xml | – sequence: 1 givenname: Wenwen surname: Yu fullname: Yu, Wenwen email: yuwenwen62@gmail.com – sequence: 2 givenname: Ning surname: Lu fullname: Lu, Ning email: jiangxiluning@gmail.com – sequence: 3 givenname: Xianbiao surname: Qi fullname: Qi, Xianbiao email: qixianbiao@gmail.com organization: Visual Computing Group, Ping An Property & Casualty Insurance Company,Shenzhen,China – sequence: 4 givenname: Ping surname: Gong fullname: Gong, Ping email: gongping@xzhmu.edu.cn organization: School of Medical Imaging, Xuzhou Medical University,Xuzhou,China – sequence: 5 givenname: Rong surname: Xiao fullname: Xiao, Rong email: rongxiao@gmail.com organization: Visual Computing Group, Ping An Property & Casualty Insurance Company,Shenzhen,China |
| BookMark | eNotUF1PgzAUrYk-uOkvMDH9AyC3LVB8Mzgn2aLE6PPSlVslQksKzO3fi3M5D-fmfNyHMyPn1lkk5BaiECDK7oq8fBNSRknIIgZhJoBlLD0jM0iZhMmQ_JK4sshX97T0TmPf1_aTrvBAC2ucb9VQO0sX-8ErfTyNdy19dHps0Q49HY_5ou2822FFl151X3SNyttJD3Jnd64Z_4qqoS84_Dj_3V-RC6OaHq9PPCcfT4v3_DlYvy6L_GEd1CziQyBirZNKoEQRx3GVGcW5EJnSoBLNJyQMYJtKIwRqwYwyqRQJTG6iwWwNn5Ob_781Im46X7fKHzanDfgvmdZZJw |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICPR48806.2021.9412927 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 1728188083 9781728188089 |
| EndPage | 4370 |
| ExternalDocumentID | 9412927 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i203t-45cc6d4e8e4555d9fa33449ac1a6c3c3c6211b78f44ec42faf784611a66c1fbf3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 74 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000678409204065&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Thu Jun 29 18:39:16 EDT 2023 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i203t-45cc6d4e8e4555d9fa33449ac1a6c3c3c6211b78f44ec42faf784611a66c1fbf3 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_9412927 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-Jan.-10 |
| PublicationDateYYYYMMDD | 2021-01-10 |
| PublicationDate_xml | – month: 01 year: 2021 text: 2021-Jan.-10 day: 10 |
| PublicationDecade | 2020 |
| PublicationTitle | 2020 25th International Conference on Pattern Recognition (ICPR) |
| PublicationTitleAbbrev | ICPR |
| PublicationYear | 2021 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 2.5468469 |
| Snippet | Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 4363 |
| SubjectTerms | Deep learning Feature extraction Information retrieval Layout Semantics Text recognition Visualization |
| Title | PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks |
| URI | https://ieeexplore.ieee.org/document/9412927 |
| WOSCitedRecordID | wos000678409204065&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NawMhEJUk9NBTW5LSbzz02E1WV9e11zRpQyAspYXcgqtjCZSkZDeh_ffVXUkp9FIEERUHnsLoOG8GodusoAoSwyNpChUxSGkk_XchI1Zl4N7NTKo62YSYzbL5XOYtdLfnwgBA7XwGfd-s__LNWm-9qWwgmdNOVLRRW4i04WoF0i-J5WAyzJ_9cfSOB5T0w-RfWVNqpTE--p-4Y9T7Yd_hfK9XTlALVl20zifD6T0Ofv2uH0_hCwcykQcXjz6rTcNSwJ4zgh-CgBJv6_mN-QAMfvQxqnEIrPoWOam7cP7UO541buFlD72ORy_DpygkS4iWNE6qiHGtU8MgA8Y5N9KqJGEOaE1UqhNXUvfUK0RmGQPNqFVWuKsHcaOpJrawySnqrNYrOENYMsG1NdZSxR0EXJkYXG1FUaRuCXmOuh6sxUcTD2MRcLr4u_sSHfr98GYLEl-hTrXZwjU60LtqWW5u6k38BrrMojA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5zCvqksom_zYOPdmvTpG18nZsbm6XIhL2NNLnIYGyydUP_e5M2TARfJBBCEnLwJXDJ5b47hO6TnAgIFfO4yoVHISIet9-FNNAiAfNuplyUySbiNE0mE57V0MOOCwMApfMZtGyz_MtXS7mxprI2p0Y7kXgP7TNKiV-xtRztN_B5e9DJXu2BtK4HJGi56b_yppRqo3f8P4EnqPnDv8PZTrOcohosGmiZDTrDR-w8-00_HsIXdnQiCy_ufhariqeALWsEPzkBa7wp51cGBFD42Uapxi606rtnpG7dCRRznFaO4esmeut1x52-59IleDPih4VHmZSRopAAZYwprkUYUgO1DEQkQ1Mi89jL40RTCpISLXRsLh-BGY1koHMdnqH6YrmAc4Q5jZnUSmsimIGACeWDqXWc55FZgl-ghgVr-lFFxJg6nC7_7r5Dh_3xy2g6GqTDK3Rk98YaMQL_GtWL1QZu0IHcFrP16rbc0G9UwKV3 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2020+25th+International+Conference+on+Pattern+Recognition+%28ICPR%29&rft.atitle=PICK%3A+Processing+Key+Information+Extraction+from+Documents+using+Improved+Graph+Learning-Convolutional+Networks&rft.au=Yu%2C+Wenwen&rft.au=Lu%2C+Ning&rft.au=Qi%2C+Xianbiao&rft.au=Gong%2C+Ping&rft.date=2021-01-10&rft.pub=IEEE&rft.spage=4363&rft.epage=4370&rft_id=info:doi/10.1109%2FICPR48806.2021.9412927&rft.externalDocID=9412927 |