Handbook of Document Image Processing and Recognition

doi:10.1007/978-0-85729-859-1

Cited by 81 publications

(12 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Example confusion table showing the desired output (GT), the actual output (OCR), the absolute number of occurrences (CNT), and the corresponding percentage with respect to all errors (PERC). Given are the five most frequent errors including substitutions (4), deletions (2,5), and insertions (1,3). output where the line-based OCR results are concatenated in reading order and stored as a text file in two variants, one for each individual page and one for the entire book.…”

Section: Results Generationmentioning

confidence: 99%

See 1 more Smart Citation

OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

Reul¹,

Christ²,

Hartelt³

et al. 2019

Preprint

View full text Add to dashboard Cite

Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.

show abstract

Section: Results Generationmentioning

confidence: 99%

“…Books printed before 1501. 1. Preprocessing: First of all, the input images have to be prepared for further processing.…”

Section: Steps Of a Typical Ocr Workflowmentioning

confidence: 99%

OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

Reul¹,

Christ²,

Hartelt³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…While Optical Character Recognition (OCR) is regularly considered to be a solved problem [1], gathering the textual content of historical printings using OCR can still be a very challenging and cumbersome task, due to various reasons. Among the problems that need to be addressed for early printings is the often intricate layout containing images, artistic border elements and ornaments, marginal notes, and swash capitals at section beginnings whose positioning is often highly irregular.…”

Section: Introductionmentioning

confidence: 99%

OCR4all—An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

et al. 2019

View full text Add to dashboard Cite

Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19 th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.

show abstract

“…Contents of the collections are one of the key elements of usefulness of the collections, but also presentation of the contents for the user is important [2,3]. According to Dengel and Shafait [4] "availability of logical structure facilitates navigation and advanced search inside the document as well as enables better presentation of the document in a possibly restructured format." Possibility to use article structure will also improve further analysis stages of the content, such as topic modeling or any other kind of content analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Several digitized historical newspaper collections have implemented article extraction on their pages. Good examples are for example Italian La Stampa 2 , British Newspaper Archive 3 , and Australian Trove 4 . The historical digital newspaper archive environment of the NLF is based on commercial docWorks 5 software.…”

Section: Introductionmentioning

confidence: 99%

Clipping the Page – Automatic Article Detection and Marking Software in Production of Newspaper Clippings of a Digitized Historical Journalistic Collection

Kettunen

Pääkkönen

Liukkonen

2019

Digital Libraries for Open Knowledge

View full text Add to dashboard Cite

This paper describes utilization of article detection and extraction on the Finnish Digi 1 newspaper material of the National Library of Finland (NLF) using data of one newspaper, Uusi Suometar 1869-1918. We use PIVAJ software [1] for detection and marking of articles in our collection. Out of the separated articles we can produce automatic clippings for the user. The user can collect clippings for own use both as images and as OCRed text. Together these functionalities improve usability of the digitized journalistic collection by providing a structured access to the contents of a page.

show abstract

Handbook of Document Image Processing and Recognition

Cited by 81 publications

References 57 publications

OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

OCR4all—An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

Clipping the Page – Automatic Article Detection and Marking Software in Production of Newspaper Clippings of a Digitized Historical Journalistic Collection

Contact Info

Product

Resources

About