Self-learning structure for text localization

© 2017 MVA Organization All Rights Reserved. This paper presents a self-learning structure for text localization. The proposed system has an ability to improve itself automatically by analyzing unlabelled images. The system consists of three classification modules called component grader, component...

Full description

Saved in:
Bibliographic Details
Main Authors: Supakorn Intaratat, Karn Patanukhom
Format: Conference Proceeding
Published: 2018
Subjects:
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85027844078&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/57076
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-57076
record_format dspace
spelling th-cmuir.6653943832-570762018-09-05T03:34:38Z Self-learning structure for text localization Supakorn Intaratat Karn Patanukhom Computer Science © 2017 MVA Organization All Rights Reserved. This paper presents a self-learning structure for text localization. The proposed system has an ability to improve itself automatically by analyzing unlabelled images. The system consists of three classification modules called component grader, component linker, and group classifier. Firstly, the image is analyzed to obtain the character candidate components. Then, the grader evaluates the possibility of text for every component by considering their properties individually while the linker classifies the degree of connection for every two components and groups all linked components together. Then, the groups of components are classified as text or non-text by the group classifier. Since all three modules work almost independently, we can update one module by using results from the other modules. This paper also presents a strategy for updating all modules by using unlabelled images. The experiment is given to show that the grader and the linker can be initialized by using few labeled training samples and then the system can automatically collect more samples from unlabelled images by using the results from three modules. 2018-09-05T03:34:38Z 2018-09-05T03:34:38Z 2017-07-19 Conference Proceeding 2-s2.0-85027844078 10.23919/MVA.2017.7986878 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85027844078&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/57076
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Computer Science
spellingShingle Computer Science
Supakorn Intaratat
Karn Patanukhom
Self-learning structure for text localization
description © 2017 MVA Organization All Rights Reserved. This paper presents a self-learning structure for text localization. The proposed system has an ability to improve itself automatically by analyzing unlabelled images. The system consists of three classification modules called component grader, component linker, and group classifier. Firstly, the image is analyzed to obtain the character candidate components. Then, the grader evaluates the possibility of text for every component by considering their properties individually while the linker classifies the degree of connection for every two components and groups all linked components together. Then, the groups of components are classified as text or non-text by the group classifier. Since all three modules work almost independently, we can update one module by using results from the other modules. This paper also presents a strategy for updating all modules by using unlabelled images. The experiment is given to show that the grader and the linker can be initialized by using few labeled training samples and then the system can automatically collect more samples from unlabelled images by using the results from three modules.
format Conference Proceeding
author Supakorn Intaratat
Karn Patanukhom
author_facet Supakorn Intaratat
Karn Patanukhom
author_sort Supakorn Intaratat
title Self-learning structure for text localization
title_short Self-learning structure for text localization
title_full Self-learning structure for text localization
title_fullStr Self-learning structure for text localization
title_full_unstemmed Self-learning structure for text localization
title_sort self-learning structure for text localization
publishDate 2018
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85027844078&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/57076
_version_ 1681424811280039936