Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers

Boillet, Mélodie; Maarand, Martin; Paquet, Thierry; Kermorvant, Christopher

doi:10.1145/3476887.3476905

“…Three state-of-the-art networks based on the U-Net architecture [ 13 ], namely, dhSegment [ 20 ], ARU-Net [ 21 ] and Doc-UFCN [ 22 ], are compared in [ 17 ], showing the efficiency of U-Net-based architectures, their current dominance for text line segmentation, and their limitations.…”

Section: Related Workmentioning

confidence: 99%

“…For this dataset, we evaluated Mask-RCNN on the raw output masks. On the basis of the Boillet et al's results [17], we selected three state-of-the-art U-Net architecture networks: dhSegment [20], ARU-Net [21], and Doc-UFCN [22], to compare the performance of Mask-RCNN. In the present study, we used the performance data reported by these authors in Tables 4 and 5 of their article (note, however, that we replicated these trainings in a pilot study and found approximately the same values, and, most importantly, in the same hierarchy).…”

Section: Choice Of Public Databases and U-net Networkmentioning

confidence: 99%

Historical Text Line Segmentation Using Deep Learning Algorithms: Mask-RCNN against U-Net Networks

Fizaine,

Bard,

Paindavoine

et al. 2024

J. Imaging

0

View full text Add to dashboard Cite

Text line segmentation is a necessary preliminary step before most text transcription algorithms are applied. The leading deep learning networks used in this context (ARU-Net, dhSegment, and Doc-UFCN) are based on the U-Net architecture. They are efficient, but fall under the same concept, requiring a post-processing step to perform instance (e.g., text line) segmentation. In the present work, we test the advantages of Mask-RCNN, which is designed to perform instance segmentation directly. This work is the first to directly compare Mask-RCNN- and U-Net-based networks on text segmentation of historical documents, showing the superiority of the former over the latter. Three studies were conducted, one comparing these networks on different historical databases, another comparing Mask-RCNN with Doc-UFCN on a private historical database, and a third comparing the handwritten text recognition (HTR) performance of the tested networks. The results showed that Mask-RCNN outperformed ARU-Net, dhSegment, and Doc-UFCN using relevant line segmentation metrics, that performance evaluation should not focus on the raw masks generated by the networks, that a light mask processing is an efficient and simple solution to improve evaluation, and that Mask-RCNN leads to better HTR performance.

show abstract

“…Many open-source models have been proposed to tackle text line detection from historical documents, mainly ARU-Net [19], dhSegment [3], Do-cExtractor [30] and Doc-UFCN [6]. These models have been pre-trained on multiple datasets [40,18], making them very efficient on a wide variety of historical documents.…”

Section: Text Line Detectionmentioning

confidence: 99%

“…In cases where the visual features are not sufficient to correctly detect the acts, some works have focused on combining visual and textual features. This has been achieved by using Probabilistic Index Map [34] or by enriching the image with the localization of first text lines that are detected using their textual content [6].…”

Section: Handwritten Text Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Large-scale genealogical information extraction from handwritten Quebec parish records

Tarride

¹

,

Maarand

²

,

Boillet

³

et al. 2023

IJDAR

Self Cite

5

0

View full text Add to dashboard Cite

This paper presents a complete workflow designed for extracting information from Quebec handwritten parish registers. The acts in these documents contain individual and family information highly valuable for genetic, demographic and social studies of the Quebec population. From an image of parish records, our workflow is able to identify the acts and extract personal information. The workflow is divided into successive steps: page classification, text line detection, handwritten text recognition, named entity recognition and act detection and classification. For all these steps, different machine learning models are compared. Once the information is extracted, validation rules designed by experts are then applied to standardize the extracted information and ensure its consistency with the type of act (birth, marriage, and death). This validation step is able to reject records that are considered invalid or merged. The full workflow has been used to process over two million pages of Quebec parish registers from the 19-20th centuries. On a sample comprising 65% of registers, 3.2 million acts were recognized. Verification of the birth and death acts from this sample shows that 74% of them are considered complete and valid. These records will be integrated into the BALSAC database and linked together to recreate family and genealogical relations at large scale.

show abstract

Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records

Tarride¹,

Maarand²,

Boillet³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a complete workflow designed for extracting information from Quebec handwritten parish registers. The acts in these documents contain individual and family information highly valuable for genetic, demographic and social studies of the Quebec population. From an image of parish records, our workflow is able to identify the acts and extract personal information. The workflow is divided into successive steps: page classification, text line detection, handwritten text recognition, named entity recognition and act detection and classification. For all these steps, different machine learning models are compared. Once the information is extracted, validation rules designed by experts are then applied to standardize the extracted information and ensure its consistency with the type of act (birth, marriage, and death). This validation step is able to reject records that are considered invalid or merged. The full workflow has been used to process over two million pages of Quebec parish registers from the 19-20th centuries. On a sample comprising 65% of registers, 3.2 million acts were recognized. Verification of the birth and death acts from this sample shows that 74% of them are considered complete and valid. These records will be integrated into the BALSAC database and linked together to recreate family and genealogical relations at large scale.

show abstract

Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers

Cited by 3 publications

References 9 publications

Historical Text Line Segmentation Using Deep Learning Algorithms: Mask-RCNN against U-Net Networks

Historical Text Line Segmentation Using Deep Learning Algorithms: Mask-RCNN against U-Net Networks

Large-scale genealogical information extraction from handwritten Quebec parish records

Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records

Contact Info

Product

Resources

About