dc.contributor.advisor | Fernandez Quilez, Alvaro. | |
dc.contributor.advisor | Miranda Husebø, Ivan-Louis. | |
dc.contributor.author | Preus Dovland, Fredrik. | |
dc.contributor.author | Fagerjord, Isak. | |
dc.contributor.author | Tasic, Stefan. | |
dc.date.accessioned | 2023-07-04T15:52:39Z | |
dc.date.available | 2023-07-04T15:52:39Z | |
dc.date.issued | 2023 | |
dc.identifier | no.uis:inspera:130505068:70620800 | |
dc.identifier.uri | https://hdl.handle.net/11250/3075648 | |
dc.description | Full text not available | |
dc.description.abstract | This thesis presents the development of an internal Optical Character Recognition
(OCR) system for receipt scanning, aimed at replacing Direktoratet for Forvaltning og
Økonomistyring’s current system with an in-house one. The primary motivation behind
the development of a new solution is to minimize costs, improve data privacy and security,
increase efficiency and accuracy, and extract more data which the company requires. The
current system is designed to detect and recognize text on receipts.
The OCR is built using two components: a Convolutional Neural Networks (CNN)
based object detector to localize regions of interest (ROI) and a Transformer based text
recognizer to convert the ROIs into a text output. The study uses receipts acquired
from DFØ, which have been manually labeled, annotated, and pre-processed as part
of the work before used for the training and evaluation of the two component models.
Cross-validation and bootstrapping were used to assess the models’ performance.
Experimental results demonstrate promising performance for both models when used
independently, with the object detection model achieving 92% global average accuracy for
all the classes. The text recognition results were also promising, with 2% CER and 92%
precision when bootstrapping. As a bonus, we provide an API and a hosted web-page
that will be available until censorship deadline intended to depict the use of the developed
system.
Our findings suggest that it is feasible to develop an OCR system capable of replacing
the external solution currently used by DFØ. This work lays a strong foundation for
the development of a fully operational in-house solution and has the potential to yield
significant cost savings, improved efficiency and accuracy, and extraction of more data. | |
dc.description.abstract | This thesis presents the development of an internal Optical Character Recognition
(OCR) system for receipt scanning, aimed at replacing Direktoratet for Forvaltning og
Økonomistyring’s current system with an in-house one. The primary motivation behind
the development of a new solution is to minimize costs, improve data privacy and security,
increase efficiency and accuracy, and extract more data which the company requires. The
current system is designed to detect and recognize text on receipts.
The OCR is built using two components: a Convolutional Neural Networks (CNN)
based object detector to localize regions of interest (ROI) and a Transformer based text
recognizer to convert the ROIs into a text output. The study uses receipts acquired
from DFØ, which have been manually labeled, annotated, and pre-processed as part
of the work before used for the training and evaluation of the two component models.
Cross-validation and bootstrapping were used to assess the models’ performance.
Experimental results demonstrate promising performance for both models when used
independently, with the object detection model achieving 92% global average accuracy for
all the classes. The text recognition results were also promising, with 2% CER and 92%
precision when bootstrapping. As a bonus, we provide an API and a hosted web-page
that will be available until censorship deadline intended to depict the use of the developed
system.
Our findings suggest that it is feasible to develop an OCR system capable of replacing
the external solution currently used by DFØ. This work lays a strong foundation for
the development of a fully operational in-house solution and has the potential to yield
significant cost savings, improved efficiency and accuracy, and extraction of more data. | |
dc.language | eng | |
dc.publisher | uis | |
dc.title | Automatic DFØ Bill Recognition based on Deep Learning | |
dc.type | Bachelor thesis | |