UNSUPERVISED MERGE OF OPTICAL CHARACTER RECOGNITION RESULTS

Ioana Monica Dicher (), Ana-Georgia ÈšURCUȘ (), Eduard-Marius Cojocea (), Patricia-Steliana Penariu (), Ion Bucur (), Marcel Prodan () and Eduard Stä‚niloiu ()
Additional contact information
Ioana Monica Dicher: Politehnica University of Bucharest, Bucharest, Romania
Ana-Georgia ȚURCUȘ: Politehnica University of Bucharest, Bucharest, Romania
Eduard-Marius Cojocea: OpenGov Ltd., Bucharest, Romania
Patricia-Steliana Penariu: Politehnica University of Bucharest, Bucharest, Romania
Ion Bucur: Politehnica University of Bucharest, Bucharest, Romania
Marcel Prodan: Politehnica University of Bucharest, Bucharest, Romania
Eduard Stä‚niloiu: Politehnica University of Bucharest, Bucharest, Romania

Journal of Information Systems & Operations Management, 2020, vol. 14, issue 1, 60-67

Abstract: This paper explores an innovative Optical Character Recognition (OCR) method that aggregates the results from different methods. Due to the fact that we have to our knowledge the typical characteristics of each OCR approach in any possible situation, a decisive operation can be issued between the outcomes. The proposed method aims to use a voting-based system, apply different preprocessing operations on the input image document, in order to enhance various text characteristics and expects to retrieve the “best text†in the image where it can be “read†more confidently by the OCR engine. The obtained results proved that the proposed approach delivered robust OCR reading in all kinds of processing scenarios, thus enabling the current method to be used, alongside other voting- based techniques in an unsupervised document image processing and information extraction pipeline.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.rebe.rau.ro/RePEc/rau/jisomg/SU20/JISOM14.12020_60-67.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rau:jisomg:v:14:y:2020:i:1:p:60-67

Access Statistics for this article

More articles in Journal of Information Systems & Operations Management from Romanian-American University Contact information at EDIRC.
Bibliographic data for series maintained by Alex Tabusca ().