A cascade detector for rapid face detection

Ning Jiang; Wenxin Yu; Shaopeng Tang; Satoshi Goto

doi:10.1109/CSPA.2011.5759863

A cascade detector for rapid face detection

Ning Jiang^*, Wenxin Yu, Shaopeng Tang, Satoshi Goto

^*Corresponding author for this work

Waseda University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

In recent years, LBP feature based svm detector and Haar feature based cascade detector are the two types of efficient detectors for face detection. In this paper, we proposed to improve the performance on Haar feature based cascade detector. First, we describe a new feature for cascade detector. The feature is called Separate Haar Feature. Secondly, we describe a new decision algorithm in cascade detection to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. The second is the algorithm for selecting the best width for this don't-care area. Finally, we proposed a new decision algorithm which makes the decision by not only a stage result in cascade detection process to improve the detection rate.

Original language	English
Title of host publication	Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
Pages	155-158
Number of pages	4
DOIs	https://doi.org/10.1109/CSPA.2011.5759863
Publication status	Published - 2011
Event	2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 - Penang Duration: 2011 Mar 4 → 2011 Mar 6

Other

Other	2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
City	Penang
Period	11/3/4 → 11/3/6

Keywords

Adaboost
cascade detector
Face detection
Separate Haar Feature

ASJC Scopus subject areas

Signal Processing

Access to Document

10.1109/CSPA.2011.5759863

Cite this

@inproceedings{6a329f0130ee47268aaa601e8d6a39a3,

title = "A cascade detector for rapid face detection",

abstract = "In recent years, LBP feature based svm detector and Haar feature based cascade detector are the two types of efficient detectors for face detection. In this paper, we proposed to improve the performance on Haar feature based cascade detector. First, we describe a new feature for cascade detector. The feature is called Separate Haar Feature. Secondly, we describe a new decision algorithm in cascade detection to improve the detection rate. There are three key contributions. The first is {"}Separate Haar Feature{"}, which adds a don't-care area between the rectangles of Haar Feature. The second is the algorithm for selecting the best width for this don't-care area. Finally, we proposed a new decision algorithm which makes the decision by not only a stage result in cascade detection process to improve the detection rate.",

keywords = "Adaboost, cascade detector, Face detection, Separate Haar Feature",

author = "Ning Jiang and Wenxin Yu and Shaopeng Tang and Satoshi Goto",

year = "2011",

doi = "10.1109/CSPA.2011.5759863",

language = "English",

isbn = "9781612844145",

pages = "155--158",

booktitle = "Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011",

note = "2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 ; Conference date: 04-03-2011 Through 06-03-2011",

}

TY - GEN

T1 - A cascade detector for rapid face detection

AU - Jiang, Ning

AU - Yu, Wenxin

AU - Tang, Shaopeng

AU - Goto, Satoshi

PY - 2011

Y1 - 2011

N2 - In recent years, LBP feature based svm detector and Haar feature based cascade detector are the two types of efficient detectors for face detection. In this paper, we proposed to improve the performance on Haar feature based cascade detector. First, we describe a new feature for cascade detector. The feature is called Separate Haar Feature. Secondly, we describe a new decision algorithm in cascade detection to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. The second is the algorithm for selecting the best width for this don't-care area. Finally, we proposed a new decision algorithm which makes the decision by not only a stage result in cascade detection process to improve the detection rate.

AB - In recent years, LBP feature based svm detector and Haar feature based cascade detector are the two types of efficient detectors for face detection. In this paper, we proposed to improve the performance on Haar feature based cascade detector. First, we describe a new feature for cascade detector. The feature is called Separate Haar Feature. Secondly, we describe a new decision algorithm in cascade detection to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. The second is the algorithm for selecting the best width for this don't-care area. Finally, we proposed a new decision algorithm which makes the decision by not only a stage result in cascade detection process to improve the detection rate.

KW - Adaboost

KW - cascade detector

KW - Face detection

KW - Separate Haar Feature

UR - http://www.scopus.com/inward/record.url?scp=79957489824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957489824&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2011.5759863

DO - 10.1109/CSPA.2011.5759863

M3 - Conference contribution

AN - SCOPUS:79957489824

SN - 9781612844145

SP - 155

EP - 158

BT - Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011

T2 - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011

Y2 - 4 March 2011 through 6 March 2011

ER -

A cascade detector for rapid face detection

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this