Mobile application on a scene text spotting

Scene text detection methods in computer vision and object detection relying heavily on neural network and deep learning have emerged recently, showing promising results. The topic of object recognition is a subject of ongoing active research and have been used in applications such as text localizat...

Full description

Saved in:
Bibliographic Details
Main Author: Chua, Kah Yong
Other Authors: Loke Yuan Ren
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/138067
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-138067
record_format dspace
spelling sg-ntu-dr.10356-1380672020-04-23T04:18:34Z Mobile application on a scene text spotting Chua, Kah Yong Loke Yuan Ren School of Computer Science and Engineering yrloke@ntu.edu.sg Engineering::Computer science and engineering Scene text detection methods in computer vision and object detection relying heavily on neural network and deep learning have emerged recently, showing promising results. The topic of object recognition is a subject of ongoing active research and have been used in applications such as text localization, surveillance, aerial imaging and autonomous driving. In addition, applications of scene text detection include multilingual text translation on mobile phone aiding users with instant translation, blind-navigation and image information retrieval.While recent advancement in the field have led to improved accuracies, precisions and f-measures, text extraction from natural scenes still pose as a challenging problem often involve with complex issues. These problems include, dis-oriented text, perspective distortion, arbitrary shaped text, variation in text sizes, uneven lighting and blurring. State-of-the-art object detector localize text of interest accurately by drawing horizontal/vertical, rectangular shaped bounding boxes over an object. These methods fail to address the issue of perspective distortion, variation in text sizes and arbitrary shaped text resulting in reduced text localization and limiting downstream task. To overcome these limitations, this research paper introduces two solutions that addresses these issues to achieve more precise detections producing better fitted and tighter bounding boxes. Specifically,by adding a new parameter call angle in the anchor box parameter definition and predict a rotation of clockwise or anti-clockwise around it’s midpoint and by allowing the anchor boxes to morph around it four point definitions. As a result, further improving the text localization network accuracy with minimum impact in its reliability and speed. Bachelor of Engineering (Computer Engineering) 2020-04-23T04:18:34Z 2020-04-23T04:18:34Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138067 en SCSE19-0105 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
spellingShingle Engineering::Computer science and engineering
Chua, Kah Yong
Mobile application on a scene text spotting
description Scene text detection methods in computer vision and object detection relying heavily on neural network and deep learning have emerged recently, showing promising results. The topic of object recognition is a subject of ongoing active research and have been used in applications such as text localization, surveillance, aerial imaging and autonomous driving. In addition, applications of scene text detection include multilingual text translation on mobile phone aiding users with instant translation, blind-navigation and image information retrieval.While recent advancement in the field have led to improved accuracies, precisions and f-measures, text extraction from natural scenes still pose as a challenging problem often involve with complex issues. These problems include, dis-oriented text, perspective distortion, arbitrary shaped text, variation in text sizes, uneven lighting and blurring. State-of-the-art object detector localize text of interest accurately by drawing horizontal/vertical, rectangular shaped bounding boxes over an object. These methods fail to address the issue of perspective distortion, variation in text sizes and arbitrary shaped text resulting in reduced text localization and limiting downstream task. To overcome these limitations, this research paper introduces two solutions that addresses these issues to achieve more precise detections producing better fitted and tighter bounding boxes. Specifically,by adding a new parameter call angle in the anchor box parameter definition and predict a rotation of clockwise or anti-clockwise around it’s midpoint and by allowing the anchor boxes to morph around it four point definitions. As a result, further improving the text localization network accuracy with minimum impact in its reliability and speed.
author2 Loke Yuan Ren
author_facet Loke Yuan Ren
Chua, Kah Yong
format Final Year Project
author Chua, Kah Yong
author_sort Chua, Kah Yong
title Mobile application on a scene text spotting
title_short Mobile application on a scene text spotting
title_full Mobile application on a scene text spotting
title_fullStr Mobile application on a scene text spotting
title_full_unstemmed Mobile application on a scene text spotting
title_sort mobile application on a scene text spotting
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/138067
_version_ 1681056092089483264