Text restoration using image super resolution

Text Recognition and scene text recognition have gained high prominence with the emergence of advanced deep learning techniques, such as CNNs. However, when the scene data is of low resolution, most models fail to provide accurate results. To this extent, super resolution is proposed as a pre proces...

Full description

Saved in:
Bibliographic Details
Main Author: Bodipati, Kiran
Other Authors: Chen Change Loy
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/166103
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-166103
record_format dspace
spelling sg-ntu-dr.10356-1661032023-04-21T15:38:39Z Text restoration using image super resolution Bodipati, Kiran Chen Change Loy School of Computer Science and Engineering Multimedia and Interacting Computing Lab ccloy@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Text Recognition and scene text recognition have gained high prominence with the emergence of advanced deep learning techniques, such as CNNs. However, when the scene data is of low resolution, most models fail to provide accurate results. To this extent, super resolution is proposed as a pre processing technique to improve the resolution of the images. Traditional Super Resolution models are developed for natural scenes and tend to fail in the case of scene text, due to several characteristics of the text that make it challenging for text super resolution. The lack of high quality datasets for this task is a factor in the poor performance of existing models. In our study, we provide a comprehensive review of existing super resolution techniques and the techniques specific to the context of scene text data. In this study, we build a new practical dataset that can be used to this extent. We create high resolution synthetic text data and collect high resolution images crawling the web. The corresponding low resolution images are created using a practical higher order degradation model. We train on the architecture of Real-ESRGAN and provide a qualitative and qualitative study of the datasets proposed and demonstrate the performance of the new models. Comparisons against the pre-trained Real-ESRGAN model is provided. The limitations of the proposed datasets and models are discussed. Bachelor of Science in Data Science and Artificial Intelligence 2023-04-21T06:59:53Z 2023-04-21T06:59:53Z 2023 Final Year Project (FYP) Bodipati, K. (2023). Text restoration using image super resolution. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166103 https://hdl.handle.net/10356/166103 en SCSE22-0310 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Bodipati, Kiran
Text restoration using image super resolution
description Text Recognition and scene text recognition have gained high prominence with the emergence of advanced deep learning techniques, such as CNNs. However, when the scene data is of low resolution, most models fail to provide accurate results. To this extent, super resolution is proposed as a pre processing technique to improve the resolution of the images. Traditional Super Resolution models are developed for natural scenes and tend to fail in the case of scene text, due to several characteristics of the text that make it challenging for text super resolution. The lack of high quality datasets for this task is a factor in the poor performance of existing models. In our study, we provide a comprehensive review of existing super resolution techniques and the techniques specific to the context of scene text data. In this study, we build a new practical dataset that can be used to this extent. We create high resolution synthetic text data and collect high resolution images crawling the web. The corresponding low resolution images are created using a practical higher order degradation model. We train on the architecture of Real-ESRGAN and provide a qualitative and qualitative study of the datasets proposed and demonstrate the performance of the new models. Comparisons against the pre-trained Real-ESRGAN model is provided. The limitations of the proposed datasets and models are discussed.
author2 Chen Change Loy
author_facet Chen Change Loy
Bodipati, Kiran
format Final Year Project
author Bodipati, Kiran
author_sort Bodipati, Kiran
title Text restoration using image super resolution
title_short Text restoration using image super resolution
title_full Text restoration using image super resolution
title_fullStr Text restoration using image super resolution
title_full_unstemmed Text restoration using image super resolution
title_sort text restoration using image super resolution
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/166103
_version_ 1764208038538903552