Vis enkel innførsel

dc.contributor.advisorSkretting, Karl
dc.contributor.advisorStråbø, Kristian
dc.contributor.authorFadul, Fadul Elwalid
dc.contributor.authorLindland, Christoffer
dc.date.accessioned2023-07-04T15:51:46Z
dc.date.available2023-07-04T15:51:46Z
dc.date.issued2023
dc.identifierno.uis:inspera:130505068:70611460
dc.identifier.urihttps://hdl.handle.net/11250/3075625
dc.description.abstractThe purpose of this thesis is to develop a semi-automated interface that uses Optical Character Recognition (OCR) routines to identify text-based information from a large volume of digitized drawings associated with the oil and gas industry. The identified information is presented in an appropriate interface for any necessary manual modifica- tion, with the target of improving the efficiency of maintaining large amounts of older documents. The thesis outlines the design of the interface and the implementation of Tesseract OCR engine, in combination with tailor-made functions and classes that lever- age OpenCV to enhance the recognition process.
dc.description.abstractThe purpose of this thesis is to develop a semi-automated interface that uses Optical Character Recognition (OCR) routines to identify text-based information from a large volume of digitized drawings associated with the oil and gas industry. The identified information is presented in an appropriate interface for any necessary manual modifica- tion, with the target of improving the efficiency of maintaining large amounts of older documents. The thesis outlines the design of the interface and the implementation of Tesseract OCR engine, in combination with tailor-made functions and classes that lever- age OpenCV to enhance the recognition process.
dc.languageeng
dc.publisheruis
dc.titleInterface Development for Digitization of Documents Using OCR
dc.typeBachelor thesis


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel