A Mixed Approach for Handwritten Documents Structural Analysis

Malleron, Vincent; Églin, Véronique

doi:10.1109/icdar.2011.62

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Block detection and labeling were performed semiautomatically. First, an automatic identification of text areas was performed by means of horizontal and vertical border detection methods, based on the use of enhanced profiles (Malleron and Eglin, 2011;Ramel et al, 2007). After this automatic process, all detected areas were verified, labeled and (if necessary) manually corrected by means of a specialized layout editing tool.…”

Section: Text Block Detectionmentioning

confidence: 99%

Transcribing a 17th-century botanical manuscript: Longitudinal evaluation of document layout detection and interactive transcription

Toselli

Leiva

Bordes-Cabrera

et al. 2017

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

We present a process for cost-effective transcription of cursive handwritten text images that has been tested on a 1 000 pages 17th century book about botanical species. The process comprised two main tasks, namely: (1) preprocessing: page layout analysis, text line detection, and extraction; and (2) transcription of the extracted text line images. Both tasks were carried out with semiautomatic procedures, aimed at incrementally minimizing user correction effort, by means of computer-assisted line detection and interactive handwritten text recognition technologies. The contribution derived from this work is threefold. First, we provide a detailed humansupervised transcription of a relatively large historical handwritten book, ready to be searchable, indexable, and accessible to cultural heritage scholars as well as the general public. Second, we have conducted the first longitudinal study to date on interactive handwriting text recognition, for which we provide a very comprehensive user assessment of the real-world performance of the technologies involved in this work. Third, as a result of this process, we have produced a detailed transcription and document layout information (i.e., high-quality labeled data) ready to be used by researchers working on automated technologies for document analysis and recognition.

show abstract

Section: Text Block Detectionmentioning

confidence: 99%

Transcribing a 17th-century botanical manuscript: Longitudinal evaluation of document layout detection and interactive transcription

Toselli

Leiva

Bordes-Cabrera

et al. 2017

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

show abstract

“…Historical handwritten documents do not have strict layout rules and thus, a layout analysis method needs to be invariant to layout variability. Most of the state-of-the-art methods focus on modern handwritten documents and only a few deal with historical handwritten documents [8], [9].…”

Section: A Text Block Detectionmentioning

confidence: 99%

“…First, they will be uploaded to UCL's free-to-access digital repository of Bentham's manuscripts, for research purposes and to ensure the long-term digital preservation of this priceless collection 7 . The volunteers' transcripts will also feed into scholarship, making new discoveries about Bentham's life and thought, and feeding directly into the production of the critical edition of Bentham's works 8 .…”

Section: A Crowdsourcingmentioning

confidence: 99%

Ground-Truth Production in the Transcriptorium Project

Gatos

Louloudis

Causer

et al. 2014

2014 11th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

Abstract-TRANSCRIPTORIUM is a 3-years project that aims to develop innovative, cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using Handwritten Text Recognition (HTR) technology. The production of ground-truth (GT) of a dataset of handwritten document images is among the first tasks. We address novel approaches for the faster production of this GT based on crowdsourcing and on prior-knowledge methods. We also address here a novel low-cost semi-supervised procedure for obtaining pairs of correct line-level aligned detected/extracted text line images and text line transcripts, specially suitable for training models of the HTR technology employed in TRANSCRIPTORIUM.

show abstract