Video shot classification using human faces

Yin Chan; Shang Hung Lin; Yap Peng Tan; S. Y. Kung

Video shot classification using human faces

Yin Chan, Shang Hung Lin, Yap Peng Tan, S. Y. Kung

Research output: Contribution to conference › Paper › peer-review

Abstract

People usually make up a lot of information contents in videos. The abilities to answer queries and facilitate browsing related to people in videos are crucial. In a single video sequence, a particular person may appear multiple number of times. In this paper, we propose a scheme to automatically detect the repeated occurrences of the same people to enable fast people related searching. In particular, we propose a video shot classification scheme using human faces, regardless of scale and background. Video shots are classified by clustering facial features extracted from these shots. Potential applications include video indexing and browsing. Employing unsupervised clustering algorithms, this scheme requires no human intervention. Experimental results on a 4-minute news sequence show that it achieves encouraging results (cf. figures 4 & 5).

Original language	English (US)
Pages	843-846
Number of pages	4
State	Published - 1996
Event	Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz Duration: Sep 16 1996 → Sep 19 1996

Other

Other	Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)
City	Lausanne, Switz
Period	9/16/96 → 9/19/96

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Cite this

@conference{271b75ecd4b843d0adf940a742f41bf9,

title = "Video shot classification using human faces",

abstract = "People usually make up a lot of information contents in videos. The abilities to answer queries and facilitate browsing related to people in videos are crucial. In a single video sequence, a particular person may appear multiple number of times. In this paper, we propose a scheme to automatically detect the repeated occurrences of the same people to enable fast people related searching. In particular, we propose a video shot classification scheme using human faces, regardless of scale and background. Video shots are classified by clustering facial features extracted from these shots. Potential applications include video indexing and browsing. Employing unsupervised clustering algorithms, this scheme requires no human intervention. Experimental results on a 4-minute news sequence show that it achieves encouraging results (cf. figures 4 & 5).",

author = "Yin Chan and Lin, {Shang Hung} and Tan, {Yap Peng} and Kung, {S. Y.}",

year = "1996",

language = "English (US)",

pages = "843--846",

note = "Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) ; Conference date: 16-09-1996 Through 19-09-1996",

}

TY - CONF

T1 - Video shot classification using human faces

AU - Chan, Yin

AU - Lin, Shang Hung

AU - Tan, Yap Peng

AU - Kung, S. Y.

PY - 1996

Y1 - 1996

N2 - People usually make up a lot of information contents in videos. The abilities to answer queries and facilitate browsing related to people in videos are crucial. In a single video sequence, a particular person may appear multiple number of times. In this paper, we propose a scheme to automatically detect the repeated occurrences of the same people to enable fast people related searching. In particular, we propose a video shot classification scheme using human faces, regardless of scale and background. Video shots are classified by clustering facial features extracted from these shots. Potential applications include video indexing and browsing. Employing unsupervised clustering algorithms, this scheme requires no human intervention. Experimental results on a 4-minute news sequence show that it achieves encouraging results (cf. figures 4 & 5).

AB - People usually make up a lot of information contents in videos. The abilities to answer queries and facilitate browsing related to people in videos are crucial. In a single video sequence, a particular person may appear multiple number of times. In this paper, we propose a scheme to automatically detect the repeated occurrences of the same people to enable fast people related searching. In particular, we propose a video shot classification scheme using human faces, regardless of scale and background. Video shots are classified by clustering facial features extracted from these shots. Potential applications include video indexing and browsing. Employing unsupervised clustering algorithms, this scheme requires no human intervention. Experimental results on a 4-minute news sequence show that it achieves encouraging results (cf. figures 4 & 5).

UR - http://www.scopus.com/inward/record.url?scp=0030410626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030410626&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030410626

SP - 843

EP - 846

T2 - Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)

Y2 - 16 September 1996 through 19 September 1996

ER -

Video shot classification using human faces

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this