Staff View: Delaunay triangulation based text detection from multi-view images of natural scene

Delaunay triangulation based text detection from multi-view images of natural scene

Text detection in the wild is still considered as a challenging issue to the researchers because of its several real time applications like forensic application, where CCTV camera captures images at different angles of the same scene. Unlike the existing methods that consider a single view captured...

Full description

Saved in:

Bibliographic Details
Main Authors:	Roy, Soumyadip, Shivakumara, Palaiahnakote, Pal, Umapada, Lu, Tong, Kumar, Govindaraj Hemantha
Format:	Article
Published:	Elsevier 2020
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://eprints.um.edu.my/25238/ https://doi.org/10.1016/j.patrec.2019.11.021
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.25238
record_format	eprints
spelling	my.um.eprints.252382020-08-05T01:25:05Z http://eprints.um.edu.my/25238/ Delaunay triangulation based text detection from multi-view images of natural scene Roy, Soumyadip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kumar, Govindaraj Hemantha QA75 Electronic computers. Computer science Text detection in the wild is still considered as a challenging issue to the researchers because of its several real time applications like forensic application, where CCTV camera captures images at different angles of the same scene. Unlike the existing methods that consider a single view captured orthogonally for text detection, this paper considers multi-view (view-1 and view-2 of the same spot) of the same scene captured at different angles or different height distances for text detection. For each pair of the same scene, the proposed method extracts features that describe characteristics of text components based on Delaunay Triangulation (DT), namely corner points, area and cavity of the DT. The features of corresponding DT in view-1 and view-2 are compared through cosine distance measure to estimate the similarity between two components of respective view-1 and view-2. If the pair satisfies the similarity condition, the components are considered as Candidate Text Components (CTC). In other words, these are the common components for view-1 and view-2 that satisfy the similarity condition. From each CTC of view-1 and view-2, the proposed method finds nearest neighbor components to restore the components of the same text line based on estimating degree of similarly between CTC and neighbor components using Chi-square and cosine distance measures. Furthermore, the proposed method uses a recognition step to detect correct texts by comparing recognition results of view-1 and view-2. The same recognition step is used for removing false positives to improve the performance of the proposed method. Experimental results on our own dataset, which contains pair of images of different situations, and the standard datasets, namely, ICDAR 2013, MSRATD-500, CTW1500, Total-text, ICDAR 2017 MLT and COCO-text, show that the proposed method outperforms the existing methods. © 2019 Elsevier 2020 Article PeerReviewed Roy, Soumyadip and Shivakumara, Palaiahnakote and Pal, Umapada and Lu, Tong and Kumar, Govindaraj Hemantha (2020) Delaunay triangulation based text detection from multi-view images of natural scene. Pattern Recognition Letters, 129. pp. 92-100. ISSN 0167-8655 https://doi.org/10.1016/j.patrec.2019.11.021 doi:10.1016/j.patrec.2019.11.021
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Roy, Soumyadip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kumar, Govindaraj Hemantha Delaunay triangulation based text detection from multi-view images of natural scene
description	Text detection in the wild is still considered as a challenging issue to the researchers because of its several real time applications like forensic application, where CCTV camera captures images at different angles of the same scene. Unlike the existing methods that consider a single view captured orthogonally for text detection, this paper considers multi-view (view-1 and view-2 of the same spot) of the same scene captured at different angles or different height distances for text detection. For each pair of the same scene, the proposed method extracts features that describe characteristics of text components based on Delaunay Triangulation (DT), namely corner points, area and cavity of the DT. The features of corresponding DT in view-1 and view-2 are compared through cosine distance measure to estimate the similarity between two components of respective view-1 and view-2. If the pair satisfies the similarity condition, the components are considered as Candidate Text Components (CTC). In other words, these are the common components for view-1 and view-2 that satisfy the similarity condition. From each CTC of view-1 and view-2, the proposed method finds nearest neighbor components to restore the components of the same text line based on estimating degree of similarly between CTC and neighbor components using Chi-square and cosine distance measures. Furthermore, the proposed method uses a recognition step to detect correct texts by comparing recognition results of view-1 and view-2. The same recognition step is used for removing false positives to improve the performance of the proposed method. Experimental results on our own dataset, which contains pair of images of different situations, and the standard datasets, namely, ICDAR 2013, MSRATD-500, CTW1500, Total-text, ICDAR 2017 MLT and COCO-text, show that the proposed method outperforms the existing methods. © 2019
format	Article
author	Roy, Soumyadip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kumar, Govindaraj Hemantha
author_facet	Roy, Soumyadip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kumar, Govindaraj Hemantha
author_sort	Roy, Soumyadip
title	Delaunay triangulation based text detection from multi-view images of natural scene
title_short	Delaunay triangulation based text detection from multi-view images of natural scene
title_full	Delaunay triangulation based text detection from multi-view images of natural scene
title_fullStr	Delaunay triangulation based text detection from multi-view images of natural scene
title_full_unstemmed	Delaunay triangulation based text detection from multi-view images of natural scene
title_sort	delaunay triangulation based text detection from multi-view images of natural scene
publisher	Elsevier
publishDate	2020
url	http://eprints.um.edu.my/25238/ https://doi.org/10.1016/j.patrec.2019.11.021
_version_	1680857011896451072
score	13.211869

Delaunay triangulation based text detection from multi-view images of natural scene

Similar Items