Accurate car plate detection via car face landmark localization

Hailiang Li; Man Yau Chiu; Kangheng Wu; Zhibin Lei; Kin Man Lam

doi:10.1117/12.2281924

Accurate car plate detection via car face landmark localization

Hailiang Li, Man Yau Chiu, Kangheng Wu, Zhibin Lei, Kin Man Lam

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

For intelligent vehicle surveillance systems, it is a big challenge to detect small, blurred car plates of vehicles driving on a highway. In this paper, we present a novel, two-stage detection scheme for small, blurred car-plate detection in large surveillance images. Our proposed scheme firstly detects vehicles, and then locates the car plates in specific regions of detected vehicles based on our proposed car-face landmark localization algorithm. Our scheme can also solve the high false-alarming rate problem with small, blurred car-plate detection. Experimental results show that our proposed method is accurate, and able to reduce the false-alarming rate, without any compromise in speed.

Original language	English
Title of host publication	Ninth International Conference on Digital Image Processing, ICDIP 2017
Publisher	SPIE
Volume	10420
ISBN (Electronic)	9781510613041
DOIs	https://doi.org/10.1117/12.2281924
Publication status	Published - 1 Jan 2017
Event	9th International Conference on Digital Image Processing, ICDIP 2017 - Hong Kong, Hong Kong Duration: 19 May 2017 → 22 May 2017

Conference

Conference	9th International Conference on Digital Image Processing, ICDIP 2017
Country/Territory	Hong Kong
City	Hong Kong
Period	19/05/17 → 22/05/17

Keywords

Car-plate detection
Intelligent traffic
Surveillance system.
Vehicle detection and tracking

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

More information

10.1117/12.2281924

Cite this

@inproceedings{9851452a61654c2da61448a57c4947bc,

title = "Accurate car plate detection via car face landmark localization",

abstract = "For intelligent vehicle surveillance systems, it is a big challenge to detect small, blurred car plates of vehicles driving on a highway. In this paper, we present a novel, two-stage detection scheme for small, blurred car-plate detection in large surveillance images. Our proposed scheme firstly detects vehicles, and then locates the car plates in specific regions of detected vehicles based on our proposed car-face landmark localization algorithm. Our scheme can also solve the high false-alarming rate problem with small, blurred car-plate detection. Experimental results show that our proposed method is accurate, and able to reduce the false-alarming rate, without any compromise in speed.",

keywords = "Car-plate detection, Intelligent traffic, Surveillance system., Vehicle detection and tracking",

author = "Hailiang Li and Chiu, {Man Yau} and Kangheng Wu and Zhibin Lei and Lam, {Kin Man}",

year = "2017",

month = jan,

day = "1",

doi = "10.1117/12.2281924",

language = "English",

volume = "10420",

booktitle = "Ninth International Conference on Digital Image Processing, ICDIP 2017",

publisher = "SPIE",

address = "United States",

note = "9th International Conference on Digital Image Processing, ICDIP 2017 ; Conference date: 19-05-2017 Through 22-05-2017",

}

TY - GEN

T1 - Accurate car plate detection via car face landmark localization

AU - Li, Hailiang

AU - Chiu, Man Yau

AU - Wu, Kangheng

AU - Lei, Zhibin

AU - Lam, Kin Man

PY - 2017/1/1

Y1 - 2017/1/1

N2 - For intelligent vehicle surveillance systems, it is a big challenge to detect small, blurred car plates of vehicles driving on a highway. In this paper, we present a novel, two-stage detection scheme for small, blurred car-plate detection in large surveillance images. Our proposed scheme firstly detects vehicles, and then locates the car plates in specific regions of detected vehicles based on our proposed car-face landmark localization algorithm. Our scheme can also solve the high false-alarming rate problem with small, blurred car-plate detection. Experimental results show that our proposed method is accurate, and able to reduce the false-alarming rate, without any compromise in speed.

AB - For intelligent vehicle surveillance systems, it is a big challenge to detect small, blurred car plates of vehicles driving on a highway. In this paper, we present a novel, two-stage detection scheme for small, blurred car-plate detection in large surveillance images. Our proposed scheme firstly detects vehicles, and then locates the car plates in specific regions of detected vehicles based on our proposed car-face landmark localization algorithm. Our scheme can also solve the high false-alarming rate problem with small, blurred car-plate detection. Experimental results show that our proposed method is accurate, and able to reduce the false-alarming rate, without any compromise in speed.

KW - Car-plate detection

KW - Intelligent traffic

KW - Surveillance system.

KW - Vehicle detection and tracking

UR - http://www.scopus.com/inward/record.url?scp=85030698768&partnerID=8YFLogxK

U2 - 10.1117/12.2281924

DO - 10.1117/12.2281924

M3 - Conference article published in proceeding or book

VL - 10420

BT - Ninth International Conference on Digital Image Processing, ICDIP 2017

PB - SPIE

T2 - 9th International Conference on Digital Image Processing, ICDIP 2017

Y2 - 19 May 2017 through 22 May 2017

ER -

Accurate car plate detection via car face landmark localization

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this