Training deep network models for accurate detection of text in scenes

Training deep network models for accurate detection of text in scenes

With rising interest in both computer vision and deep learning, scene text detection and recognition have become an active research topic. Texts in images contains semantic information about the environment shown in the image and being able to analyse and understand this information is immensely hel...

Full description

Saved in:
Bibliographic Details
Main Author: Teow, Jeslynna Zhini
Other Authors: Lu Shijian
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2020
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies
Online Access:https://hdl.handle.net/10356/138006
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-138006
record_format dspace
spelling sg-ntu-dr.10356-1380062020-05-06T07:16:05Z Training deep network models for accurate detection of text in scenes Teow, Jeslynna Zhini Lu Shijian School of Computer Science and Engineering shijian.lu@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies With rising interest in both computer vision and deep learning, scene text detection and recognition have become an active research topic. Texts in images contains semantic information about the environment shown in the image and being able to analyse and understand this information is immensely helpful. In this project, we will implement deep learning network models, namely Textboxes++ and EAST for the detection of various texts in scenes via optimization of hyper-parameters for optimal performance. Bachelor of Engineering (Computer Science) 2020-04-22T00:35:21Z 2020-04-22T00:35:21Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138006 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies
Teow, Jeslynna Zhini
Training deep network models for accurate detection of text in scenes
description With rising interest in both computer vision and deep learning, scene text detection and recognition have become an active research topic. Texts in images contains semantic information about the environment shown in the image and being able to analyse and understand this information is immensely helpful. In this project, we will implement deep learning network models, namely Textboxes++ and EAST for the detection of various texts in scenes via optimization of hyper-parameters for optimal performance.
author2 Lu Shijian
author_facet Lu Shijian
Teow, Jeslynna Zhini
format Final Year Project
author Teow, Jeslynna Zhini
author_sort Teow, Jeslynna Zhini
title Training deep network models for accurate detection of text in scenes
title_short Training deep network models for accurate detection of text in scenes
title_full Training deep network models for accurate detection of text in scenes
title_fullStr Training deep network models for accurate detection of text in scenes
title_full_unstemmed Training deep network models for accurate detection of text in scenes
title_sort training deep network models for accurate detection of text in scenes
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/138006
_version_ 1681057726831001600

Similar Items