Robust text line detection in historical documents: learning and evaluation methods

Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from...

Full description

Saved in:

Bibliographic Details
Published in:	International journal on document analysis and recognition Vol. 25; no. 2; pp. 95 - 114
Main Authors:	Boillet, Mélodie, Kermorvant, Christopher, Paquet, Thierry
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2022 Springer Nature B.V Springer Verlag
Subjects:	Annotations Computer Science Datasets Documents Engineering Sciences Fonts Image Processing and Computer Vision Original Paper Pattern Recognition Segmentation Signal and Image processing Generic architecture Evaluation strategy Text line detection Historical documents Goal-directed evaluation Text line detection ; Historical documents;Generic architecture;Evaluation strategy ; Goal-directed evaluation
ISSN:	1433-2833, 1433-2825
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from building line segmentation models with a high generalization capacity. We present a study conducted using three state-of-the-art systems Doc-UFCN, dhSegment and ARU-Net and show that it is possible to build generic models trained on a wide variety of historical document datasets that can correctly segment diverse unseen pages. This paper also highlights the importance of the annotations used during training: Each existing dataset is annotated differently. We present a unification of the annotations and show its positive impact on the final text recognition results. In this end, we present a complete evaluation strategy using standard pixel-level metrics, object-level ones and introducing goal-oriented metrics.
AbstractList	Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from building line segmentation models with a high generalization capacity. We present a study conducted using three state-of-the-art systems Doc-UFCN, dhSegment and ARU-Net and show that it is possible to build generic models trained on a wide variety of historical document datasets that can correctly segment diverse unseen pages. This paper also highlights the importance of the annotations used during training: Each existing dataset is annotated differently. We present a unification of the annotations and show its positive impact on the final text recognition results. In this end, we present a complete evaluation strategy using standard pixel-level metrics, object-level ones and introducing goal-oriented metrics.
Author	Kermorvant, Christopher Boillet, Mélodie Paquet, Thierry
Author_xml	– sequence: 1 givenname: Mélodie orcidid: 0000-0002-0618-7852 surname: Boillet fullname: Boillet, Mélodie email: boillet@teklia.com organization: TEKLIA, LITIS, Normandie University – sequence: 2 givenname: Christopher surname: Kermorvant fullname: Kermorvant, Christopher organization: TEKLIA, LITIS, Normandie University – sequence: 3 givenname: Thierry surname: Paquet fullname: Paquet, Thierry organization: LITIS, Normandie University
BackLink	https://hal.science/hal-03923710$$DView record in HAL
BookMark	eNp9kElLAzEYhoNUsC5_wFPAk4fRbJNMvZWiVigILueQmWRsZJrUJFP03xs7LuChhyyE5_l48x6CkfPOAHCK0QVGSFzGvFNSIJIXopOyEHtgjBmlBalIOfq9U3oADmN8RQgLLqoxeHzwdR8TTOY9wc46A7VJpknWO2gdXNqYfLCN6qD2Tb8yLsUr2BkVnHUvUDkNzUZ1vdoKK5OWXsdjsN-qLpqT7_MIPN9cP83mxeL-9m42XRQNLWkqFJ1UWjRtWzNKECuR0WWLBeFCc1ZXlUJMlNjUCGumOVUtYxrVohEUcy24okfgfJi7VJ1cB7tS4UN6ZeV8upBfb7kJQgVGG5zZs4FdB__Wm5jkq--Dy_Ek4ZwhzkrMM1UNVBN8jMG0srFp-7cUlO0kRvKrbjnULXPdclu3FFkl_9SfRDslOkgxw-7FhL9UO6xPpoGTfQ
CitedBy_id	crossref_primary_10_1109_TPAMI_2023_3235826 crossref_primary_10_1007_s10032_025_00526_w crossref_primary_10_2514_1_B38960 crossref_primary_10_1016_j_culher_2024_02_001 crossref_primary_10_3390_jimaging10030065 crossref_primary_10_1007_s10044_024_01235_6 crossref_primary_10_1016_j_eswa_2025_126453
Cites_doi	10.1109/ICPR48806.2021.9412447 10.1109/ICDAR.2017.222 10.1007/s10032-009-0083-y 10.1109/ICDAR.2017.311 10.1109/ICFHR-2018.2018.00072 10.1109/ICIP.2014.7025525 10.1109/ICDAR.2019.00208 10.1109/CVPR.2016.90 10.1109/ICDAR.2017.155 10.1109/CVPR.2017.462 10.1109/ICDAR.2017.226 10.1109/ICASSP.2014.6854572 10.1016/j.patrec.2020.01.026.ISSN0167-8655 10.1145/3352631.3352633 10.1109/ICCV.2017.242 10.1109/CVPR42600.2020.01472 10.1007/s10032-018-0304-3 10.1109/34.476511 10.1007/978-3-030-01231-1_23 10.1109/ICDAR.2019.00066 10.1109/ICDAR.2019.00111 10.1007/s100320200071 10.1109/ICDAR.2017.307 10.1117/1.3446803 10.51964/hlcs9299 10.1007/978-3-030-57058-3_31 10.1109/DAS.2018.38 10.1109/ICFHR2020.2020.00023 10.1109/ICFHR2020.2020.00025 10.1109/CVPR.2017.690 10.1109/ICFHR.2016.0014 10.1145/3352631.3352636 10.1109/CVPR.2016.91 10.1007/s10032-019-00332-1 10.1109/ICCV.2015.169 10.1109/CVPR.2014.81 10.1007/s10032-006-0014-0
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	AAYXX CITATION JQ2 1XC VOOES
DOI	10.1007/s10032-022-00395-7
DatabaseName	CrossRef ProQuest Computer Science Collection Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef ProQuest Computer Science Collection
DatabaseTitleList	ProQuest Computer Science Collection
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Computer Science
EISSN	1433-2825
EndPage	114
ExternalDocumentID	oai:HAL:hal-03923710v1 10_1007_s10032_022_00395_7
GrantInformation_xml	– fundername: CIFRE ANRT grantid: 2020/0390 – fundername: Agence Nationale de la Recherche (ANR) grantid: ANR-17-JPCH-0006; ANR-17-CE38-0008
GroupedDBID	-59 -5G -BR -EM -Y2 -~C .86 06D 0R~ 0VY 1N0 1SB 203 29J 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5GY 5VS 67Z 6NX 8TC 95- 95. 95~ 96X AAAVM AABHQ AACDK AAGAY AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFGCZ AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BDATZ BGNMA BSONS CAG COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EBLON EBS EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV LAS LLZTM M4Y MA- MQGED N2Q NPVJJ NQJWS NU0 O9- O93 O9J OAM P9O PF0 PT4 PT5 QOS R89 R9I RNI ROL RPX RSV RZK S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7X Z83 Z88 ZMTXR ~A9 AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG AEZWR AFDZB AFFHD AFHIU AFKRA AFOHR AGQPQ AHPBZ AHWEU AIXLP ARAPS ATHPR AYFIA BENPR BGLVJ CCPQU CITATION HCIFZ K7- PHGZM PHGZT PQGLB JQ2 1XC VOOES
ID	FETCH-LOGICAL-c353t-a398d7cffb4320450ed5f17267d64b88a04751eb01d4d63af44d0b7c7316d76a3
IEDL.DBID	RSV
ISICitedReferencesCount	19
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000771889900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1433-2833
IngestDate	Tue Oct 14 20:48:48 EDT 2025 Wed Sep 17 23:57:53 EDT 2025 Tue Nov 18 21:53:33 EST 2025 Sat Nov 29 06:22:35 EST 2025 Fri Feb 21 02:47:21 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	Generic architecture Evaluation strategy Text line detection Historical documents Goal-directed evaluation Text line detection ; Historical documents;Generic architecture;Evaluation strategy ; Goal-directed evaluation
Language	English
License	Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c353t-a398d7cffb4320450ed5f17267d64b88a04751eb01d4d63af44d0b7c7316d76a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0618-7852 0000-0002-2044-7542 0000-0002-7508-4080
OpenAccessLink	https://hal.science/hal-03923710
PQID	2664064516
PQPubID	2043688
PageCount	20
ParticipantIDs	hal_primary_oai_HAL_hal_03923710v1 proquest_journals_2664064516 crossref_citationtrail_10_1007_s10032_022_00395_7 crossref_primary_10_1007_s10032_022_00395_7 springer_journals_10_1007_s10032_022_00395_7
PublicationCentury	2000
PublicationDate	2022-06-01
PublicationDateYYYYMMDD	2022-06-01
PublicationDate_xml	– month: 06 year: 2022 text: 2022-06-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg – name: Heidelberg
PublicationTitle	International journal on document analysis and recognition
PublicationTitleAbbrev	IJDAR
PublicationYear	2022
Publisher	Springer Berlin Heidelberg Springer Nature B.V Springer Verlag
Publisher_xml	– name: Springer Berlin Heidelberg – name: Springer Nature B.V – name: Springer Verlag
References	WolfCJolionJ-MObject count/area graphs for the evaluation of object detection and segmentation algorithmsInt. J. Document Anal. Recogn.20068428029610.1007/s10032-006-0014-0 Oparin, I., Kahn, J., Galibert, O.: First maurdor 2013 evaluation campaign in scanned document image processing. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5090–5094 (May 2014) Boillet, M., Bonhomme, M.-L., Stutzmann, D., Kermorvant, C.: HORAE: an annotated dataset of books of hours. In: Proceedings of the 5th International Workshop on Historical Document Imaging and Processing, HIP ’19, pp. 7-12. Association for Computing Machinery, (September 2019) Dolfing, H.J.G.A., Bellegarda, J., Chorowski, J., Marxer, R. and Laurent, A.Dolfing, H.J., Bellegarda, J., Chorowski, J., Marxer, R. and Laurent, A.: The “ScribbleLens” Dutch historical handwriting corpus. In: International Conference on Frontiers of Handwriting Recognition (ICFHR), pp. 67–72 (September 2020) Kahle, P., Colutto, S., Hackl, G., Mühlberger, G.: Transkribus - a service platform for transcription, recognition and retrieval of historical documents. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 04, pp. 19–24, (November 2017) PeskinAWilthanBMajurskiMDetection of dense, overlapping, geometric objectsInt. J. Artif. Intell. Appl. (IJAIA)2020112940 Alberti, M., Bouillon, M., Ingold, R., Liwicki, M.: Open evaluation tool for layout analysis of document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 43–47, Kyoto, Japan, (November 2017) Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587, (November 2013) Markus, D., Florian, K., Robert, S., Basilis, G.: cBAD: ICDAR2019 competition on baseline detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1494–1498 (September 2019) Vézina, H., Bournival, J-S.: An overview of the BALSAC population database. current state and future prospects. In: Historical Life Course Studies, Past Developments (2020) Arora, A., Chang, C.C., Rekabdar, B., BabaAli, B., Povey, D., Etter, D., Raj, D., Hadian, H., Trmal, J., Garcia, P., Watanabe, S., Manohar, V., Shao, Y., Khudanpur, S.: Using ASR methods for OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 663–668 (September 2019) RentonGSoullardYChatelainCAdamSKermorvantCPaquetTFully convolutional network with dilated convolutions for handwritten text line segmentationInt. J. Doc. Anal. Recogn. (IJDAR)20182117718610.1007/s10032-018-0304-3 Stutzmann, D., Torres Aguilar, S., Kermorvant, C., Miret, B.: C3PO4: A corpus of annotated medieval cartularies (image, text, named entities). Unpublished Galibert, O., Kahn, J., Oparin, I.: The zonemap metric for page segmentation and area classification in scanned documents. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2594–2598 (January 2015) Yousef, M., Bishop, To.: OrigamiNet: weakly-supervised, segmentation-free, one-step, full page text recognition by learning to unfold. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14698–14707, (June 2020) Sánchez, J.A., Romero, V., Toselli, A.H., Villegas, M., Vidal, E.: Dataset for ICDAR2017 competition on handwritten text recognition on the READ dataset (ICDAR2017 HTR), (2017) Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 29, pp. 838–846. Curran Associates, Inc., (April 2016) Barakat, B., Droby, A., Kassis, M., El-Sana, J.: Text line segmentation for challenging handwritten document images using fully convolutional network. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 374–379 (August 2018) MartiU-VBunkeHThe IAM-database: An English sentence database for offline handwriting recognitionInt. J. Document Anal. Recogn. (IJDAR)20025394610.1007/s100320200071 Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. In: arXiv:abs/1804.02767 (April 2018) Diem, M., Kleber, F., Fiel, S., Grüning, T., Gatos, B.: cBAD: ICDAR2017 competition on baseline detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 1355–1360 (November 2017) TrierODJainAKGoal-directed evaluation of binarization methodsIEEE Trans. Pattern Anal. Mach. Intell.1995171191120110.1109/34.476511 Bušta, M., Neumann, L., Matas, J.: Deep TextSpotter: an end-to-end trainable scene text localization and recognition framework. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2223–2231, (October 2017) Girshick, R.B.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (June 2015) Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517–6525, (July 2017) Moysset, B., Louradour, J., Kermorvant, C., Wolf, C.: Learning text-line localization with shared and local regression neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 1–6 (October 2016) MelnikovAZagaynovIXiangBDimosthenisKDanielLFast and lightweight text line detection on historical documentsDocument Analysis Systems2020BerlinSpringer44145010.1007/978-3-030-57058-3_31 Sánchez, J.A., Romero, V., Toselli, A.H., Vidal, E.: READ dataset Bozen (December 2016) Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Vittorio, F., Martial, H., Cristian, S., Yair, W. (Eds.), 15th European Conference on Computer Vision (ECCV), pp. 372–388. Springer International Publishing, (September 2018) Shaoqing, R., Kaiming, H., Ross, G., Jian, S.: Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 39 (June 2015) RonnebergerOFischerPBroxTU-net: convolutional networks for biomedical image segmentationLNCS20159351234241 Michael, J., Labahn, R., Gruning, T., Zollner, J.: Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1286–1293, (September 2019) Jia D., Wei D., Richard S., Li-Jia L., Kai L., and Fei-Fei L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (June 2009) Boros, E., Romero, V., Maarand, M., Zenklova, K., Kreckova, J., Vidal, E., Stutzmann, D. and Kermorvant, C.: A comparison of sequential and combined approaches for named entity recognition in a corpus of handwritten medieval charters. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 79–84, Dortmund, Germany, (September 2020). IEEE Boillet, M., Kermorvant, C., Paquet, T.: Multiple document datasets pre-training improves text line detection with deep neural networks. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2134–2141, (January 2021) GrüningTLeifertGStraußTLabahnRA Two-Stage Method for Text Line Detection in Historical DocumentsInt. J. Document Anal. Recogn. (IJDAR)20192228530210.1007/s10032-019-00332-1 Soullard, Y., Tranouez, P., Chatelain, C., Nicolas, S., Paquet, T.: Multi-scale gated fully convolutional densenets for semantic labeling of historical newspaper images. Pattern Recogn. Lett. 131, 435–441 (2020). https://doi.org/10.1016/j.patrec.2020.01.026.ISSN0167-8655 Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7–12. IEEE, (August 2018) Mechi, O., Mehri, M., Ingold, R., Amara, N.E.B.: Text line segmentation in historical document images using an adaptive U-net architecture. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 369–374 (September 2019) Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4342–4351 (June 2017) Tarride, S., Lemaitre, A., Couasnon, B., Tardivel, S.: Signature detection as a way to recognise historical parish register structure. In: HIP 2019, pp. 54–59, Sydney, Australia, (September 2019). ACM Press He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (June 2016) Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (June 2016) Grüning, T., Labahn, R., Diem, M., Kleber, F., Fiel, S.: READ-BAD: a new dataset and evaluation scheme for baseline detection in archival documents. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 351–356 (May 2017) HemeryBLaurentHEmileBRosenbergerCComparative study of localization metrics for the evaluation of image interpretation systemsJ. Electron. Imaging20101910.1117/1.3446803 RusiñolMLladósJA performance evaluation protocol for symbol spotting systems in terms of recognition and location indicesInt. J. Document Anal. Recogn. (IJDAR)200912839610.1007/s10032-009-0083-y Zhong, Z., Sun, L., Huo, Q.: Improved localization accuracy by locNet for R-CNN based text detection. In: 2017 14th IAPR International Confe 395_CR7 395_CR47 395_CR26 395_CR48 395_CR2 395_CR23 395_CR45 395_CR1 395_CR24 G Renton (395_CR25) 2018; 21 395_CR46 395_CR4 395_CR29 395_CR3 395_CR6 395_CR27 395_CR28 395_CR10 395_CR11 395_CR30 U-V Marti (395_CR9) 2002; 5 T Grüning (395_CR8) 2019; 22 O Ronneberger (395_CR22) 2015; 9351 C Wolf (395_CR35) 2006; 8 395_CR14 A Melnikov (395_CR31) 2020 395_CR36 395_CR15 A Peskin (395_CR32) 2020; 11 395_CR37 395_CR12 395_CR13 OD Trier (395_CR5) 1995; 17 395_CR18 395_CR19 B Hemery (395_CR33) 2010; 19 395_CR16 395_CR38 395_CR17 395_CR39 395_CR40 395_CR21 395_CR43 395_CR44 395_CR41 395_CR20 395_CR42 M Rusiñol (395_CR34) 2009; 12
References_xml	– reference: Tarride, S., Lemaitre, A., Couasnon, B., Tardivel, S.: Signature detection as a way to recognise historical parish register structure. In: HIP 2019, pp. 54–59, Sydney, Australia, (September 2019). ACM Press – reference: Bušta, M., Neumann, L., Matas, J.: Deep TextSpotter: an end-to-end trainable scene text localization and recognition framework. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2223–2231, (October 2017) – reference: Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 29, pp. 838–846. Curran Associates, Inc., (April 2016) – reference: Boillet, M., Bonhomme, M.-L., Stutzmann, D., Kermorvant, C.: HORAE: an annotated dataset of books of hours. In: Proceedings of the 5th International Workshop on Historical Document Imaging and Processing, HIP ’19, pp. 7-12. Association for Computing Machinery, (September 2019) – reference: Alberti, M., Bouillon, M., Ingold, R., Liwicki, M.: Open evaluation tool for layout analysis of document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 43–47, Kyoto, Japan, (November 2017) – reference: Boros, E., Romero, V., Maarand, M., Zenklova, K., Kreckova, J., Vidal, E., Stutzmann, D. and Kermorvant, C.: A comparison of sequential and combined approaches for named entity recognition in a corpus of handwritten medieval charters. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 79–84, Dortmund, Germany, (September 2020). IEEE – reference: Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4342–4351 (June 2017) – reference: Arora, A., Chang, C.C., Rekabdar, B., BabaAli, B., Povey, D., Etter, D., Raj, D., Hadian, H., Trmal, J., Garcia, P., Watanabe, S., Manohar, V., Shao, Y., Khudanpur, S.: Using ASR methods for OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 663–668 (September 2019) – reference: Jia D., Wei D., Richard S., Li-Jia L., Kai L., and Fei-Fei L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (June 2009) – reference: Markus, D., Florian, K., Robert, S., Basilis, G.: cBAD: ICDAR2019 competition on baseline detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1494–1498 (September 2019) – reference: Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. In: arXiv:abs/1804.02767 (April 2018) – reference: RentonGSoullardYChatelainCAdamSKermorvantCPaquetTFully convolutional network with dilated convolutions for handwritten text line segmentationInt. J. Doc. Anal. Recogn. (IJDAR)20182117718610.1007/s10032-018-0304-3 – reference: Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7–12. IEEE, (August 2018) – reference: RonnebergerOFischerPBroxTU-net: convolutional networks for biomedical image segmentationLNCS20159351234241 – reference: Mechi, O., Mehri, M., Ingold, R., Amara, N.E.B.: Text line segmentation in historical document images using an adaptive U-net architecture. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 369–374 (September 2019) – reference: Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (June 2016) – reference: PeskinAWilthanBMajurskiMDetection of dense, overlapping, geometric objectsInt. J. Artif. Intell. Appl. (IJAIA)2020112940 – reference: Diem, M., Kleber, F., Fiel, S., Grüning, T., Gatos, B.: cBAD: ICDAR2017 competition on baseline detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 1355–1360 (November 2017) – reference: Shaoqing, R., Kaiming, H., Ross, G., Jian, S.: Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 39 (June 2015) – reference: Moysset, B., Louradour, J., Kermorvant, C., Wolf, C.: Learning text-line localization with shared and local regression neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 1–6 (October 2016) – reference: Vézina, H., Bournival, J-S.: An overview of the BALSAC population database. current state and future prospects. In: Historical Life Course Studies, Past Developments (2020) – reference: Galibert, O., Kahn, J., Oparin, I.: The zonemap metric for page segmentation and area classification in scanned documents. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2594–2598 (January 2015) – reference: Dolfing, H.J.G.A., Bellegarda, J., Chorowski, J., Marxer, R. and Laurent, A.Dolfing, H.J., Bellegarda, J., Chorowski, J., Marxer, R. and Laurent, A.: The “ScribbleLens” Dutch historical handwriting corpus. In: International Conference on Frontiers of Handwriting Recognition (ICFHR), pp. 67–72 (September 2020) – reference: Soullard, Y., Tranouez, P., Chatelain, C., Nicolas, S., Paquet, T.: Multi-scale gated fully convolutional densenets for semantic labeling of historical newspaper images. Pattern Recogn. Lett. 131, 435–441 (2020). https://doi.org/10.1016/j.patrec.2020.01.026.ISSN0167-8655 – reference: Grüning, T., Labahn, R., Diem, M., Kleber, F., Fiel, S.: READ-BAD: a new dataset and evaluation scheme for baseline detection in archival documents. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 351–356 (May 2017) – reference: Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517–6525, (July 2017) – reference: Sánchez, J.A., Romero, V., Toselli, A.H., Villegas, M., Vidal, E.: Dataset for ICDAR2017 competition on handwritten text recognition on the READ dataset (ICDAR2017 HTR), (2017) – reference: Zhong, Z., Sun, L., Huo, Q.: Improved localization accuracy by locNet for R-CNN based text detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, pp. 923–928 (August 2017) – reference: Barakat, B., Droby, A., Kassis, M., El-Sana, J.: Text line segmentation for challenging handwritten document images using fully convolutional network. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 374–379 (August 2018) – reference: MartiU-VBunkeHThe IAM-database: An English sentence database for offline handwriting recognitionInt. J. Document Anal. Recogn. (IJDAR)20025394610.1007/s100320200071 – reference: Boillet, M., Kermorvant, C., Paquet, T.: Multiple document datasets pre-training improves text line detection with deep neural networks. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2134–2141, (January 2021) – reference: MelnikovAZagaynovIXiangBDimosthenisKDanielLFast and lightweight text line detection on historical documentsDocument Analysis Systems2020BerlinSpringer44145010.1007/978-3-030-57058-3_31 – reference: Michael, J., Labahn, R., Gruning, T., Zollner, J.: Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1286–1293, (September 2019) – reference: Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587, (November 2013) – reference: GrüningTLeifertGStraußTLabahnRA Two-Stage Method for Text Line Detection in Historical DocumentsInt. J. Document Anal. Recogn. (IJDAR)20192228530210.1007/s10032-019-00332-1 – reference: HemeryBLaurentHEmileBRosenbergerCComparative study of localization metrics for the evaluation of image interpretation systemsJ. Electron. Imaging20101910.1117/1.3446803 – reference: Oparin, I., Kahn, J., Galibert, O.: First maurdor 2013 evaluation campaign in scanned document image processing. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5090–5094 (May 2014) – reference: Sánchez, J.A., Romero, V., Toselli, A.H., Vidal, E.: READ dataset Bozen (December 2016) – reference: Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Vittorio, F., Martial, H., Cristian, S., Yair, W. (Eds.), 15th European Conference on Computer Vision (ECCV), pp. 372–388. Springer International Publishing, (September 2018) – reference: He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (June 2016) – reference: Stutzmann, D., Torres Aguilar, S., Kermorvant, C., Miret, B.: C3PO4: A corpus of annotated medieval cartularies (image, text, named entities). Unpublished – reference: TrierODJainAKGoal-directed evaluation of binarization methodsIEEE Trans. Pattern Anal. Mach. Intell.1995171191120110.1109/34.476511 – reference: Fotini, S., Mathias, S., Nicole, E., Angelika, G., Marcus, L., Rolf, I.: DIVA-HisDB: a precisely annotated large dataset of challenging medieval manuscripts. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 471–476 (October 2016) – reference: RusiñolMLladósJA performance evaluation protocol for symbol spotting systems in terms of recognition and location indicesInt. J. Document Anal. Recogn. (IJDAR)200912839610.1007/s10032-009-0083-y – reference: WolfCJolionJ-MObject count/area graphs for the evaluation of object detection and segmentation algorithmsInt. J. Document Anal. Recogn.20068428029610.1007/s10032-006-0014-0 – reference: Kahle, P., Colutto, S., Hackl, G., Mühlberger, G.: Transkribus - a service platform for transcription, recognition and retrieval of historical documents. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 04, pp. 19–24, (November 2017) – reference: Yousef, M., Bishop, To.: OrigamiNet: weakly-supervised, segmentation-free, one-step, full page text recognition by learning to unfold. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14698–14707, (June 2020) – reference: Girshick, R.B.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (June 2015) – ident: 395_CR6 doi: 10.1109/ICPR48806.2021.9412447 – ident: 395_CR16 – ident: 395_CR26 doi: 10.1109/ICDAR.2017.222 – volume: 12 start-page: 83 year: 2009 ident: 395_CR34 publication-title: Int. J. Document Anal. Recogn. (IJDAR) doi: 10.1007/s10032-009-0083-y – ident: 395_CR47 doi: 10.1109/ICDAR.2017.311 – ident: 395_CR23 doi: 10.1109/ICFHR-2018.2018.00072 – volume: 11 start-page: 29 year: 2020 ident: 395_CR32 publication-title: Int. J. Artif. Intell. Appl. (IJAIA) – ident: 395_CR36 doi: 10.1109/ICIP.2014.7025525 – ident: 395_CR1 doi: 10.1109/ICDAR.2019.00208 – ident: 395_CR28 doi: 10.1109/CVPR.2016.90 – ident: 395_CR17 doi: 10.1109/ICDAR.2017.155 – ident: 395_CR27 doi: 10.1109/CVPR.2017.462 – ident: 395_CR10 doi: 10.1109/ICDAR.2017.226 – ident: 395_CR39 – ident: 395_CR21 doi: 10.1109/ICASSP.2014.6854572 – ident: 395_CR30 doi: 10.1016/j.patrec.2020.01.026.ISSN0167-8655 – ident: 395_CR42 doi: 10.1145/3352631.3352633 – ident: 395_CR11 doi: 10.1109/ICCV.2017.242 – ident: 395_CR3 doi: 10.1109/CVPR42600.2020.01472 – volume: 21 start-page: 177 year: 2018 ident: 395_CR25 publication-title: Int. J. Doc. Anal. Recogn. (IJDAR) doi: 10.1007/s10032-018-0304-3 – ident: 395_CR45 – volume: 17 start-page: 1191 year: 1995 ident: 395_CR5 publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.476511 – ident: 395_CR4 – volume: 9351 start-page: 234 year: 2015 ident: 395_CR22 publication-title: LNCS – ident: 395_CR40 – ident: 395_CR13 doi: 10.1007/978-3-030-01231-1_23 – ident: 395_CR24 doi: 10.1109/ICDAR.2019.00066 – ident: 395_CR48 doi: 10.1109/ICDAR.2019.00111 – volume: 5 start-page: 39 year: 2002 ident: 395_CR9 publication-title: Int. J. Document Anal. Recogn. (IJDAR) doi: 10.1007/s100320200071 – ident: 395_CR19 – ident: 395_CR46 doi: 10.1109/ICDAR.2017.307 – volume: 19 year: 2010 ident: 395_CR33 publication-title: J. Electron. Imaging doi: 10.1117/1.3446803 – ident: 395_CR37 doi: 10.51964/hlcs9299 – start-page: 441 volume-title: Document Analysis Systems year: 2020 ident: 395_CR31 doi: 10.1007/978-3-030-57058-3_31 – ident: 395_CR38 – ident: 395_CR43 doi: 10.1109/DAS.2018.38 – ident: 395_CR44 doi: 10.1109/ICFHR2020.2020.00023 – ident: 395_CR41 doi: 10.1109/ICFHR2020.2020.00025 – ident: 395_CR12 doi: 10.1109/CVPR.2017.690 – ident: 395_CR20 doi: 10.1109/ICFHR.2016.0014 – ident: 395_CR2 doi: 10.1145/3352631.3352636 – ident: 395_CR18 doi: 10.1109/CVPR.2016.91 – volume: 22 start-page: 285 year: 2019 ident: 395_CR8 publication-title: Int. J. Document Anal. Recogn. (IJDAR) doi: 10.1007/s10032-019-00332-1 – ident: 395_CR7 – ident: 395_CR15 doi: 10.1109/ICCV.2015.169 – ident: 395_CR14 doi: 10.1109/CVPR.2014.81 – ident: 395_CR29 – volume: 8 start-page: 280 issue: 4 year: 2006 ident: 395_CR35 publication-title: Int. J. Document Anal. Recogn. doi: 10.1007/s10032-006-0014-0
SSID	ssj0017678
Score	2.440834
Snippet	Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles...
SourceID	hal proquest crossref springer
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	95
SubjectTerms	Annotations Computer Science Datasets Documents Engineering Sciences Fonts Image Processing and Computer Vision Original Paper Pattern Recognition Segmentation Signal and Image processing
Title	Robust text line detection in historical documents: learning and evaluation methods
URI	https://link.springer.com/article/10.1007/s10032-022-00395-7 https://www.proquest.com/docview/2664064516 https://hal.science/hal-03923710
Volume	25
WOSCitedRecordID	wos000771889900001&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
journalDatabaseRights	– providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1433-2825 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017678 issn: 1433-2833 databaseCode: RSV dateStart: 19980201 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fS8MwED7c9MEX50-sTgnimwbaJW0634Y49iBDNpW9lbRJnSCdrN3-fi9duk1RQV_Ta1rukt5Hc_d9AJcSs5zpV6SYqmPKQ85pjImT-rGUnqcMiHZLsQnR74ejUfvBNoXlVbV7dSRZfqnXmt1cnNNUn5uGUp-KGmxiuguNYMNg-Lw8OxCL7y8CAUYxeTLbKvP9HJ_SUW1siiHXkOaXw9Ey53Qb_3vbXdixGJN0FotiDzZ0tg8NizeJ3c05DlWSDtXYAQwHk3iWF8TUgxCDQInSRVmtlZHXjIyXpCJETZJZ2R53Q6zyxAuRmSIr-nCyUKfOD-Gpe_d426NWd4EmzGcFlawdKpGkaYxBRMjnauWnCHQCoQIeh6F0ufA9Hbue4ipgMuVcubFIjAiWEoFkR1DPJpk-BhJqlbaYr32hDS2MRnDCw9STrgxEG8GlA17l_iixpORGG-MtWtEpG0dG6MiodGQkHLha3vO-oOT41foCo7o0NGzavc59ZMbQoMUQYc09B5pV0CO7h_MIoQs3bH5e4MB1FeTV5Z8fefI381PYbpXrxPzaaUK9mM70GWwl8-I1n56Xa_sDF3_u6g
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fS8MwED6cCvrib3H-DOKbBtolbTrfRBwT5xCdsreQNqkTpBPb-fd76dJNRQV9Ta9puUv6fTR33wEcKUQ5W69IEapjyiPOaYzASYNYKd_XlkR7ZbMJ0e1G_X7zxhWF5VW2e3UkWX6pPxS7eTinzT63BaUBFTWY44hYVjH_9u5hcnYgxt9fJAKMIngyVyrz_Ryf4Kg2sMmQH5jml8PREnNay_972xVYchyTnI0XxSrMmGwNlh3fJG435zhUtXSoxtbh7nYYj_KC2HwQYhko0aYos7Uy8pSRwURUhOhhMirL406J6zzxSFSmyVQ-nIy7U-cbcN-66J23qeu7QBMWsIIq1oy0SNI0xiAi5fOMDlIkOqHQIY-jSHlcBL6JPV9zHTKVcq69WCS2CZYWoWKbMJsNM7MFJDI6bbDABMJYWRiD5IRHqa88FYomkss6-JX7ZeJEyW1vjGc5lVO2jpToSFk6Uoo6HE_ueRlLcvxqfYhRnRhaNe32WUfaMTRoMGRYb34ddqugS7eHc4nUhVs1Pz-sw0kV5Onlnx-5_TfzA1ho9647snPZvdqBxUa5Zuxvnl2YLV5HZg_mk7fiKX_dL9f5O1HN8c4
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dT9swED-NDiFe1o0P0Q2GNe0NLJLaidO9oY2qE6hCK6C-WU7sABJKEUn793OXj7YgQEJ7dS4f8p1zv8T3-x3AT4NZjviKHFN1zGUkJY8xcfIgNsb3LYFor2w2oYbDaDzunS-x-Mtq92ZLsuI0kEpTVhzd2_Roifjm4fWpEp3IpQFXK_BRUiE9fa-Prub7CKp6FyMoEBwTqahpMy9f40lqWrmhwsgl1Plso7TMP_32_z_5Z_hUY092XAXLF_jgsg1o1ziU1as8x6Gm1UMztgmjf5N4mheM6kQYIVNmXVFWcWXsNmM3c7ERZifJtKTN_WJ1R4prZjLLFrLirOpanW_BZf_k4veA1_0YeCICUXAjepFVSZrG6FyEgp6zQYoAKFQ2lHEUGU-qwHex51tpQ2FSKa0Xq4SaY1kVGrENrWySuR1gkbNpVwQuUI7kYhyCFhmlvvFMqHoIOjvgN67QSS1WTj0z7vRCZpkmUuNE6nIiterAwfyc-0qq403rH-jhuSGpbA-OzzSNoUFXIPKa-R3YbQJA12s71whpJKn8-WEHDhuHLw6_fsuv7zPfh7XzP3199nd4-g3Wu2XI0N-fXWgVD1O3B6vJrLjNH76XIf8I3Tf6sg
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%3Ajournal&rft.genre=article&rft.atitle=Robust+text+line+detection+in+historical+documents%3A+learning+and+evaluation+methods&rft.jtitle=International+journal+on+document+analysis+and+recognition&rft.au=M%C3%A9lodie%2C+Boillet&rft.au=Kermorvant+Christopher&rft.au=Paquet+Thierry&rft.date=2022-06-01&rft.pub=Springer+Nature+B.V&rft.issn=1433-2833&rft.eissn=1433-2825&rft.volume=25&rft.issue=2&rft.spage=95&rft.epage=114&rft_id=info:doi/10.1007%2Fs10032-022-00395-7&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1433-2833&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1433-2833&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1433-2833&client=summon