Volltext-Downloads (blau) und Frontdoor-Views (grau)

Investigation and implementation of image super-resolution using CNNs applied to OCR

  • Recent developments in the field of deep learning have shown promising advances for a wide range of historically difficult computer vision problems. Using advanced deep learning techniques, researchers manage to perform high-quality single-image super-resolution, i.e., increasing the resolution of a given image without major losses in image quality, usually encountered when using traditional approaches such as standard interpolation. This thesis examines the process of deep learning super-resolution using convolutional neural networks and investigates whether the same deep learning models can be used to increase OCR results for low-quality text images.

Download full text files

Export metadata

Statistics

frontdoor_oas
Metadaten
Author:Florian WernerORCiD
URN:urn:nbn:de:bsz:960-opus4-23425
DOI:https://doi.org/10.25968/opus-2342
Advisor:Adrian PigorsGND, Ralf BrunsORCiDGND
Document Type:Bachelor Thesis
Language:English
Year of Completion:2022
Publishing Institution:Hochschule Hannover
Granting Institution:Hochschule Hannover, Fakult├Ąt IV - Wirtschaft und Informatik
Date of final exam:2022/08/15
Release Date:2022/09/05
Tag:Super Resolution
GND Keyword:Deep learning; Neuronales Netz; Maschinelles Sehen; Optische Zeichenerkennung
Page Number:92
Link to catalogue:1818711729
Institutes:Fakult├Ąt IV - Wirtschaft und Informatik
DDC classes:004 Informatik
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International