Intra color-shape classification for traffic sign recognition

King Hann Lim, Kah Phooi Seng, Li Minn Ang

Research output: Book chapter/Published conference paperConference paper

25 Citations (Scopus)

Abstract

This paper presents a novel traffic sign recognition system comprising of: (i) Color/shape classification, (ii) Pictogram extraction, (iii) Features selection and, (iv) Lyapunov Theory-based Radial Basis Function neural network (RBFNN). In the proposed system, traffic signs are first segmented and classified with regard to its unique color and shape in order to partition a large set of data into smaller subclasses. Within these subclasses, all redundant information except the pictogram is discarded for feature selection since the pictogram contains critical information for road users. Principle Component Analysis (PCA) is applied to extract salient points for traffic sign dimensionality reduction. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. These features are fed into RBFNN for training with a proposed weight updating scheme based on Lyapunov stability theory. The performance of the proposed system is evaluated with Malaysian road signs with promising recognition rate.

Original languageEnglish
Title of host publicationICS 2010 - International Computer Symposium
Pages642-647
Number of pages6
DOIs
Publication statusPublished - 01 Dec 2010
Event2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan, Province of China
Duration: 16 Dec 201018 Dec 2010

Conference

Conference2010 International Computer Symposium, ICS 2010
CountryTaiwan, Province of China
CityTainan
Period16/12/1018/12/10

Fingerprint

Traffic signs
Color
Feature extraction
Neural networks

Cite this

Lim, K. H., Seng, K. P., & Ang, L. M. (2010). Intra color-shape classification for traffic sign recognition. In ICS 2010 - International Computer Symposium (pp. 642-647). [5685432] https://doi.org/10.1109/COMPSYM.2010.5685432
Lim, King Hann ; Seng, Kah Phooi ; Ang, Li Minn. / Intra color-shape classification for traffic sign recognition. ICS 2010 - International Computer Symposium. 2010. pp. 642-647
@inproceedings{620013c2992241c38f9aec5c2ad0e551,
title = "Intra color-shape classification for traffic sign recognition",
abstract = "This paper presents a novel traffic sign recognition system comprising of: (i) Color/shape classification, (ii) Pictogram extraction, (iii) Features selection and, (iv) Lyapunov Theory-based Radial Basis Function neural network (RBFNN). In the proposed system, traffic signs are first segmented and classified with regard to its unique color and shape in order to partition a large set of data into smaller subclasses. Within these subclasses, all redundant information except the pictogram is discarded for feature selection since the pictogram contains critical information for road users. Principle Component Analysis (PCA) is applied to extract salient points for traffic sign dimensionality reduction. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. These features are fed into RBFNN for training with a proposed weight updating scheme based on Lyapunov stability theory. The performance of the proposed system is evaluated with Malaysian road signs with promising recognition rate.",
keywords = "Advanced driver assistance system, Classificaiton, Traffic sign recognition",
author = "Lim, {King Hann} and Seng, {Kah Phooi} and Ang, {Li Minn}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/COMPSYM.2010.5685432",
language = "English",
isbn = "9781424476404",
pages = "642--647",
booktitle = "ICS 2010 - International Computer Symposium",

}

Lim, KH, Seng, KP & Ang, LM 2010, Intra color-shape classification for traffic sign recognition. in ICS 2010 - International Computer Symposium., 5685432, pp. 642-647, 2010 International Computer Symposium, ICS 2010, Tainan, Taiwan, Province of China, 16/12/10. https://doi.org/10.1109/COMPSYM.2010.5685432

Intra color-shape classification for traffic sign recognition. / Lim, King Hann; Seng, Kah Phooi; Ang, Li Minn.

ICS 2010 - International Computer Symposium. 2010. p. 642-647 5685432.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Intra color-shape classification for traffic sign recognition

AU - Lim, King Hann

AU - Seng, Kah Phooi

AU - Ang, Li Minn

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents a novel traffic sign recognition system comprising of: (i) Color/shape classification, (ii) Pictogram extraction, (iii) Features selection and, (iv) Lyapunov Theory-based Radial Basis Function neural network (RBFNN). In the proposed system, traffic signs are first segmented and classified with regard to its unique color and shape in order to partition a large set of data into smaller subclasses. Within these subclasses, all redundant information except the pictogram is discarded for feature selection since the pictogram contains critical information for road users. Principle Component Analysis (PCA) is applied to extract salient points for traffic sign dimensionality reduction. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. These features are fed into RBFNN for training with a proposed weight updating scheme based on Lyapunov stability theory. The performance of the proposed system is evaluated with Malaysian road signs with promising recognition rate.

AB - This paper presents a novel traffic sign recognition system comprising of: (i) Color/shape classification, (ii) Pictogram extraction, (iii) Features selection and, (iv) Lyapunov Theory-based Radial Basis Function neural network (RBFNN). In the proposed system, traffic signs are first segmented and classified with regard to its unique color and shape in order to partition a large set of data into smaller subclasses. Within these subclasses, all redundant information except the pictogram is discarded for feature selection since the pictogram contains critical information for road users. Principle Component Analysis (PCA) is applied to extract salient points for traffic sign dimensionality reduction. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. These features are fed into RBFNN for training with a proposed weight updating scheme based on Lyapunov stability theory. The performance of the proposed system is evaluated with Malaysian road signs with promising recognition rate.

KW - Advanced driver assistance system

KW - Classificaiton

KW - Traffic sign recognition

UR - http://www.scopus.com/inward/record.url?scp=79851504311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851504311&partnerID=8YFLogxK

U2 - 10.1109/COMPSYM.2010.5685432

DO - 10.1109/COMPSYM.2010.5685432

M3 - Conference paper

AN - SCOPUS:79851504311

SN - 9781424476404

SP - 642

EP - 647

BT - ICS 2010 - International Computer Symposium

ER -

Lim KH, Seng KP, Ang LM. Intra color-shape classification for traffic sign recognition. In ICS 2010 - International Computer Symposium. 2010. p. 642-647. 5685432 https://doi.org/10.1109/COMPSYM.2010.5685432