Mass Digitization of Archival Documents using Mobile Phones

Kleber, Florian; Diem, Markus; Hollaus, Fabian; Fiel, Stefan

doi:10.1145/3151509.3151526

Record link:

https://resolver.obvsg.at/urn:nbn:at:at-ubtuw:3-3361
http://hdl.handle.net/20.500.12708/882

Title:

Mass Digitization of Archival Documents using Mobile Phones

Citation:

Kleber, F., Diem, M., Hollaus, F., & Fiel, S. (2017). Mass Digitization of Archival Documents using Mobile Phones. In 4th International Workshop on Historical Document Imaging and Processing, November 10-11, 2017. Kyoto, Japan. https://doi.org/10.1145/3151509.3151526

CatalogPlus:

AC11365319

Publisher DOI:

10.1145/3151509.3151526

Publication Type:

Inproceedings - Full-Paper Contribution

Konferenzbeitrag - Full-Paper Contribution

Language:

English

Authors:

Kleber, Florian
Diem, Markus
Hollaus, Fabian
Fiel, Stefan

Organisational Unit:

E193 - Institut für Rechnergestützte Automation

ISBN:

9781450353908

Date (published):

2017

Publisher:

Kyoto, Japan

Keywords:

ScanTent; Document Scanning; Page Detection; Pattern Recognition; Image Processing; Document Analysis

Abstract:

Digital copies of historical documents are needed for the Digital Humanities. Currently, cameras of standard mobile phones are able to capture documents with a resolution of about 330 dpi for document sizes up to DIN A4 (German standard, 297 x 210 mm), which allows a digitization of documents using a standard device. Thus, scholars are able to take images of documents in archives themselves without the need of book scanners or other devices. This paper presents a scanning app, which comprises a real time page detection, quality assessment (focus measure) and an automated detection of a page turn over if books are scanned. Additionally, a portable device - the ScanTent - to place the mobile phone during scanning is presented. The page detection is evaluated on the ICDAR2015 SmartDoc competition dataset and shows a reliable page detection with an average Jaccard index of 75%.

Additional information:

The final publication is available via <a href="https://doi.org/10.1145/3151509.3151526" target="_blank">https://doi.org/10.1145/3151509.3151526</a>.

License:

In Copyright

Appears in Collections:

Conference Paper