Saliency-weighted holistic scene text recognition for unseen place categorization

An improvement in framework for unseen place categorization using scene text is proposed. Category score calculation using visual saliency weighting method is proposed to cope with problem of different importance of word locations on scene images. Additionally, a HOG feature extraction using sliding...

Full description

Saved in:

Bibliographic Details
Main Authors:	Phawis Thammasorn, Karn Patanukhom, Rapeeporn Pimup
Format:	Conference Proceeding
Published:	2018
Online Access:	https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84904543396&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/45585
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Chiang Mai University

id	th-cmuir.6653943832-45585
record_format	dspace
spelling	th-cmuir.6653943832-455852018-01-24T06:12:39Z Saliency-weighted holistic scene text recognition for unseen place categorization Phawis Thammasorn Karn Patanukhom Rapeeporn Pimup An improvement in framework for unseen place categorization using scene text is proposed. Category score calculation using visual saliency weighting method is proposed to cope with problem of different importance of word locations on scene images. Additionally, a HOG feature extraction using sliding window is proposed to obtain better holistic word recognition on scene images. As the result, the proposed method outperforms PHOG baseline in unseen place categorization with greater than 10 % improvement in the accuracy. © 2014 IEEE. 2018-01-24T06:12:39Z 2018-01-24T06:12:39Z 2014-01-01 Conference Proceeding 2-s2.0-84904543396 10.1109/JCSSE.2014.6841834 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84904543396&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/45585
institution	Chiang Mai University
building	Chiang Mai University Library
country	Thailand
collection	CMU Intellectual Repository
description	An improvement in framework for unseen place categorization using scene text is proposed. Category score calculation using visual saliency weighting method is proposed to cope with problem of different importance of word locations on scene images. Additionally, a HOG feature extraction using sliding window is proposed to obtain better holistic word recognition on scene images. As the result, the proposed method outperforms PHOG baseline in unseen place categorization with greater than 10 % improvement in the accuracy. © 2014 IEEE.
format	Conference Proceeding
author	Phawis Thammasorn Karn Patanukhom Rapeeporn Pimup
spellingShingle	Phawis Thammasorn Karn Patanukhom Rapeeporn Pimup Saliency-weighted holistic scene text recognition for unseen place categorization
author_facet	Phawis Thammasorn Karn Patanukhom Rapeeporn Pimup
author_sort	Phawis Thammasorn
title	Saliency-weighted holistic scene text recognition for unseen place categorization
title_short	Saliency-weighted holistic scene text recognition for unseen place categorization
title_full	Saliency-weighted holistic scene text recognition for unseen place categorization
title_fullStr	Saliency-weighted holistic scene text recognition for unseen place categorization
title_full_unstemmed	Saliency-weighted holistic scene text recognition for unseen place categorization
title_sort	saliency-weighted holistic scene text recognition for unseen place categorization
publishDate	2018
url	https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84904543396&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/45585
_version_	1681422772909113344

Saliency-weighted holistic scene text recognition for unseen place categorization

Similar Items