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