ON PERFORMING SKEW DETECTION AND CORRECTION USING MULTIPLE EXPERTS' DECISION
Nicolae Tarbă (),
Daniel Schmidt (),
Anda - Elena Popovici (),
Eduard Stăniloiu (),
Cristian Avatavului () and
Marcel Prodan ()
Additional contact information
Nicolae Tarbă: University Politehnica of Bucharest, Bucharest, Romania
Daniel Schmidt: University Politehnica of Bucharest, Bucharest, Romania
Anda - Elena Popovici: University Politehnica of Bucharest, Bucharest, Romania
Eduard Stăniloiu: University Politehnica of Bucharest, Bucharest, Romania
Cristian Avatavului: University Politehnica of Bucharest, Bucharest, Romania
Journal of Information Systems & Operations Management, 2020, vol. 14, issue 2, 188-195
Abstract:
One of the main objectives of image processing algorithms is extracting information. An important class of such algorithms is the one responsible for Optical Character Recognition (OCR). A common problem among OCR systems is the need to work with properly oriented images. The process of finding the skew angle and rotating the initial image by its opposite is known as deskew. This paper presents a voting-based approach to solve the document deskew problem, combining results from different algorithms to cover a wide range of document types. The proposed method proved both precise and reliable, suitable to be integrated into mass-production retroconversion systems.
Date: 2020
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.rebe.rau.ro/RePEc/rau/jisomg/WI20/JISOM-WI20-A18.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:2:p:188-195
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 ().