Institutional Repository of Vilnius University
Automatinis formuliarų skaitmeninimas /
Abstract
dc:descriptionThe main goal of this thesis is to analyse different form digitization solutions and to create a web application that digitizes forms. The web application must be able to accept an image of a form, deskew it, process it, and recognize the input fields it contains. The solution is developed by applying computer vision algorithms. To refine the recognized elements, an optical character recognition model must be applied. Digitization of the form photo is implemented by adding HTML input elements in the places of recognized fields. In this thesis the following tasks were being solved: 1. Analyze the relevance, need and advantages of form digitization. 2. Compare the existing solutions for digitization of forms. 3. Design the structure of the backend program, the environment, and the frontend of the program. 4. Define algorithms and machine learning models required for input fields and text recognition. 5. Create the form digitization program. Implement input of the form picture, size equalization, deskewing. After preparing the form for input recognition, integrate the defined solutions into the form digitization program. Create an integration and deployment environment where the application is deployed.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Biekša, Ignas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210646809&prefLang=en_US