Real-time Korean traffic sign detection and recognition

Jihie Kim, Seung Gyu Kim, Kwangyong Lim, Yeongwoo Choi, Young Jung Uh, Hyeran Byun

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

Abstract

In this paper, we propose a real-time Korean traffic sign detection and recognition method based on color properties and shape geometries of images. The proposed method supports detecting and recognizing various shapes of traffic signs in realtime. Our method consists of four stages: 1) color based image segmentation; 2) region of interest (ROI) detection; 3) shape classification; and 4) numeral recognition. The proposed method can classify even the signs that are partially occluded. In addition, we improve efficiency of shape classification by using simple shape geometry measurements. Our experiment shows that our approach can provide high classification accuracies for octagonal shape signs (92%) and speed-limit signs (94.5%).

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
DOIs
Publication statusPublished - 2013 Apr 10
Event7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013 - Kota Kinabalu, Malaysia
Duration: 2013 Jan 172013 Jan 19

Publication series

NameProceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013

Other

Other7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
CountryMalaysia
CityKota Kinabalu
Period13/1/1713/1/19

Fingerprint

Traffic signs
Color
Geometry
Image segmentation
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems

Cite this

Kim, J., Kim, S. G., Lim, K., Choi, Y., Uh, Y. J., & Byun, H. (2013). Real-time Korean traffic sign detection and recognition. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013 [19] (Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013). https://doi.org/10.1145/2448556.2448575
Kim, Jihie ; Kim, Seung Gyu ; Lim, Kwangyong ; Choi, Yeongwoo ; Uh, Young Jung ; Byun, Hyeran. / Real-time Korean traffic sign detection and recognition. Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013. (Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013).
@inproceedings{d378e679b4914647b4029da26821ccc8,
title = "Real-time Korean traffic sign detection and recognition",
abstract = "In this paper, we propose a real-time Korean traffic sign detection and recognition method based on color properties and shape geometries of images. The proposed method supports detecting and recognizing various shapes of traffic signs in realtime. Our method consists of four stages: 1) color based image segmentation; 2) region of interest (ROI) detection; 3) shape classification; and 4) numeral recognition. The proposed method can classify even the signs that are partially occluded. In addition, we improve efficiency of shape classification by using simple shape geometry measurements. Our experiment shows that our approach can provide high classification accuracies for octagonal shape signs (92{\%}) and speed-limit signs (94.5{\%}).",
author = "Jihie Kim and Kim, {Seung Gyu} and Kwangyong Lim and Yeongwoo Choi and Uh, {Young Jung} and Hyeran Byun",
year = "2013",
month = "4",
day = "10",
doi = "10.1145/2448556.2448575",
language = "English",
isbn = "9781450319584",
series = "Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013",
booktitle = "Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013",

}

Kim, J, Kim, SG, Lim, K, Choi, Y, Uh, YJ & Byun, H 2013, Real-time Korean traffic sign detection and recognition. in Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013., 19, Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013, 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013, Kota Kinabalu, Malaysia, 13/1/17. https://doi.org/10.1145/2448556.2448575

Real-time Korean traffic sign detection and recognition. / Kim, Jihie; Kim, Seung Gyu; Lim, Kwangyong; Choi, Yeongwoo; Uh, Young Jung; Byun, Hyeran.

Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013. 19 (Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013).

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

TY - GEN

T1 - Real-time Korean traffic sign detection and recognition

AU - Kim, Jihie

AU - Kim, Seung Gyu

AU - Lim, Kwangyong

AU - Choi, Yeongwoo

AU - Uh, Young Jung

AU - Byun, Hyeran

PY - 2013/4/10

Y1 - 2013/4/10

N2 - In this paper, we propose a real-time Korean traffic sign detection and recognition method based on color properties and shape geometries of images. The proposed method supports detecting and recognizing various shapes of traffic signs in realtime. Our method consists of four stages: 1) color based image segmentation; 2) region of interest (ROI) detection; 3) shape classification; and 4) numeral recognition. The proposed method can classify even the signs that are partially occluded. In addition, we improve efficiency of shape classification by using simple shape geometry measurements. Our experiment shows that our approach can provide high classification accuracies for octagonal shape signs (92%) and speed-limit signs (94.5%).

AB - In this paper, we propose a real-time Korean traffic sign detection and recognition method based on color properties and shape geometries of images. The proposed method supports detecting and recognizing various shapes of traffic signs in realtime. Our method consists of four stages: 1) color based image segmentation; 2) region of interest (ROI) detection; 3) shape classification; and 4) numeral recognition. The proposed method can classify even the signs that are partially occluded. In addition, we improve efficiency of shape classification by using simple shape geometry measurements. Our experiment shows that our approach can provide high classification accuracies for octagonal shape signs (92%) and speed-limit signs (94.5%).

UR - http://www.scopus.com/inward/record.url?scp=84875855586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875855586&partnerID=8YFLogxK

U2 - 10.1145/2448556.2448575

DO - 10.1145/2448556.2448575

M3 - Conference contribution

AN - SCOPUS:84875855586

SN - 9781450319584

T3 - Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013

BT - Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013

ER -

Kim J, Kim SG, Lim K, Choi Y, Uh YJ, Byun H. Real-time Korean traffic sign detection and recognition. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013. 19. (Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013). https://doi.org/10.1145/2448556.2448575