Multi-view face detection and pose discrimination in video

Hong Song; Feng Shi

Multi-view face detection and pose discrimination in video

Hong Song^*
, Feng Shi

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

Symmetrical frame difference was used to detect the motion area and a skin-color segmentation algorithm based on BP neural network was used to extract the face candidates. Then, a combination of multiple neural networks, each corresponding to a certain range of face orientation, is used for face verification as well as for pose discrimination. Experimental results show that the algorithm is robust for human faces under deep-view rotation, and is adaptive to various lighting conditions and different face sizes.

Original language	English
Pages (from-to)	90-95
Number of pages	6
Journal	Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics
Volume	19
Issue number	1
Publication status	Published - Jan 2007

Keywords

BP neural network
Multi-view face detection
Poses discrimination

Cite this

@article{b2f7a80ef674456ba60eeaf42d4c4e17,

title = "Multi-view face detection and pose discrimination in video",

abstract = "Symmetrical frame difference was used to detect the motion area and a skin-color segmentation algorithm based on BP neural network was used to extract the face candidates. Then, a combination of multiple neural networks, each corresponding to a certain range of face orientation, is used for face verification as well as for pose discrimination. Experimental results show that the algorithm is robust for human faces under deep-view rotation, and is adaptive to various lighting conditions and different face sizes.",

keywords = "BP neural network, Multi-view face detection, Poses discrimination",

author = "Hong Song and Feng Shi",

year = "2007",

month = jan,

language = "English",

volume = "19",

pages = "90--95",

journal = "Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics",

issn = "1003-9775",

publisher = "Institute of Computing Technology",

number = "1",

}

TY - JOUR

T1 - Multi-view face detection and pose discrimination in video

AU - Song, Hong

AU - Shi, Feng

PY - 2007/1

Y1 - 2007/1

N2 - Symmetrical frame difference was used to detect the motion area and a skin-color segmentation algorithm based on BP neural network was used to extract the face candidates. Then, a combination of multiple neural networks, each corresponding to a certain range of face orientation, is used for face verification as well as for pose discrimination. Experimental results show that the algorithm is robust for human faces under deep-view rotation, and is adaptive to various lighting conditions and different face sizes.

AB - Symmetrical frame difference was used to detect the motion area and a skin-color segmentation algorithm based on BP neural network was used to extract the face candidates. Then, a combination of multiple neural networks, each corresponding to a certain range of face orientation, is used for face verification as well as for pose discrimination. Experimental results show that the algorithm is robust for human faces under deep-view rotation, and is adaptive to various lighting conditions and different face sizes.

KW - BP neural network

KW - Multi-view face detection

KW - Poses discrimination

UR - https://www.scopus.com/pages/publications/33847368081

M3 - Article

AN - SCOPUS:33847368081

SN - 1003-9775

VL - 19

SP - 90

EP - 95

JO - Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics

JF - Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics

IS - 1

ER -

Multi-view face detection and pose discrimination in video

Abstract

Keywords

Other files and links

Fingerprint

Cite this