Detecting text in floor maps using Histogram of Oriented Gradients

Hima Bindu Maguluri, Qiongjie Tian, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Automatic detection of text labels in maps is essential for applications requiring automatic map understanding. This task is challenging due to factors such as varying font size and style, slanted words/phrases, and interfering graphics that are similar to text. This paper presents an approach for text detection in indoor floor maps. We exploit the difference in spatial frequency of edge orientations between text and non-text regions through Histogram of Oriented Gradients (HOG) features, and design a gradient-filtered Support Vector Machine (SVM) classifier based on such features. Special care was taken in conditioning the data for proper training of the classifier. The proposed approach was evaluated on a data set that had been collected and manually labeled. Experimental results show that the proposed method attained improved performance, outperforming a couple of reference methods/systems.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages1932-1936
Number of pages5
DOIs
StatePublished - Oct 18 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: May 26 2013May 31 2013

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period5/26/135/31/13

Fingerprint

Classifiers
Support vector machines
Labels

Keywords

  • Histogram of Oriented Gradients
  • Support Vector Machine
  • Text Detection

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Maguluri, H. B., Tian, Q., & Li, B. (2013). Detecting text in floor maps using Histogram of Oriented Gradients. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 1932-1936). [6637990] https://doi.org/10.1109/ICASSP.2013.6637990

Detecting text in floor maps using Histogram of Oriented Gradients. / Maguluri, Hima Bindu; Tian, Qiongjie; Li, Baoxin.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 1932-1936 6637990.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Maguluri, HB, Tian, Q & Li, B 2013, Detecting text in floor maps using Histogram of Oriented Gradients. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6637990, pp. 1932-1936, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 5/26/13. https://doi.org/10.1109/ICASSP.2013.6637990
Maguluri HB, Tian Q, Li B. Detecting text in floor maps using Histogram of Oriented Gradients. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 1932-1936. 6637990 https://doi.org/10.1109/ICASSP.2013.6637990
Maguluri, Hima Bindu ; Tian, Qiongjie ; Li, Baoxin. / Detecting text in floor maps using Histogram of Oriented Gradients. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. pp. 1932-1936
@inproceedings{901da094d9fe4982b699a81eda076587,
title = "Detecting text in floor maps using Histogram of Oriented Gradients",
abstract = "Automatic detection of text labels in maps is essential for applications requiring automatic map understanding. This task is challenging due to factors such as varying font size and style, slanted words/phrases, and interfering graphics that are similar to text. This paper presents an approach for text detection in indoor floor maps. We exploit the difference in spatial frequency of edge orientations between text and non-text regions through Histogram of Oriented Gradients (HOG) features, and design a gradient-filtered Support Vector Machine (SVM) classifier based on such features. Special care was taken in conditioning the data for proper training of the classifier. The proposed approach was evaluated on a data set that had been collected and manually labeled. Experimental results show that the proposed method attained improved performance, outperforming a couple of reference methods/systems.",
keywords = "Histogram of Oriented Gradients, Support Vector Machine, Text Detection",
author = "Maguluri, {Hima Bindu} and Qiongjie Tian and Baoxin Li",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6637990",
language = "English (US)",
isbn = "9781479903566",
pages = "1932--1936",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Detecting text in floor maps using Histogram of Oriented Gradients

AU - Maguluri, Hima Bindu

AU - Tian, Qiongjie

AU - Li, Baoxin

PY - 2013/10/18

Y1 - 2013/10/18

N2 - Automatic detection of text labels in maps is essential for applications requiring automatic map understanding. This task is challenging due to factors such as varying font size and style, slanted words/phrases, and interfering graphics that are similar to text. This paper presents an approach for text detection in indoor floor maps. We exploit the difference in spatial frequency of edge orientations between text and non-text regions through Histogram of Oriented Gradients (HOG) features, and design a gradient-filtered Support Vector Machine (SVM) classifier based on such features. Special care was taken in conditioning the data for proper training of the classifier. The proposed approach was evaluated on a data set that had been collected and manually labeled. Experimental results show that the proposed method attained improved performance, outperforming a couple of reference methods/systems.

AB - Automatic detection of text labels in maps is essential for applications requiring automatic map understanding. This task is challenging due to factors such as varying font size and style, slanted words/phrases, and interfering graphics that are similar to text. This paper presents an approach for text detection in indoor floor maps. We exploit the difference in spatial frequency of edge orientations between text and non-text regions through Histogram of Oriented Gradients (HOG) features, and design a gradient-filtered Support Vector Machine (SVM) classifier based on such features. Special care was taken in conditioning the data for proper training of the classifier. The proposed approach was evaluated on a data set that had been collected and manually labeled. Experimental results show that the proposed method attained improved performance, outperforming a couple of reference methods/systems.

KW - Histogram of Oriented Gradients

KW - Support Vector Machine

KW - Text Detection

UR - http://www.scopus.com/inward/record.url?scp=84890532648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890532648&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6637990

DO - 10.1109/ICASSP.2013.6637990

M3 - Conference contribution

SN - 9781479903566

SP - 1932

EP - 1936

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -