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
Additional Services
Statistics
| 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, Fakultät 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: | Fakultät IV - Wirtschaft und Informatik |
| DDC classes: | 004 Informatik |
| Licence (German): |  Creative Commons - CC BY - Namensnennung 4.0 International |
