Bc. Dávid Meluš

Master's thesis

Enhancing Quality of Optical Character Recognition for Financial Document Processing

Enhancing Quality of Optical Character Recognition for Financial Document Processing
Abstract:
Optické rozpoznávanie znakov (OCR) hrá kľúčovú úlohu pri spracovaní dokumentov. Typické spracovanie dokumentov začína práve s procesom OCR, čo ovplyvňuje následujúce úlohy, ako je rozpoznávanie entít alebo získavanie informácií z dokumentov. Táto práca sa zaoberá špecializáciou univerzálných OCR modelov na konkrétne domény so zameraním na české faktúry. Táto diplomová práca sa zaoberá implementáciou …more
Abstract:
Optical Character Recognition (OCR) plays a crucial role in document processing, impacting downstream tasks like Named-Entity Recognition and Information Retrieval. This thesis investigates the fine-tuning of general-purpose OCR models to specific domains, focusing on Czech invoice documents. This thesis involves implementing and evaluating techniques within the invoice processing pipeline that comes …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2023

Thesis defence

  • Date of defence: 8. 2. 2024
  • Supervisor: Mgr. Michal Štefánik
  • Reader: Mgr. Jiří Polcar

Citation record

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky

Masaryk University

Faculty of Informatics

Master programme / field:
Artificial intelligence and data processing / Bioinformatics and systems biology