Face detection in video sequence with complex background

Author

Sheng, Minglan ; Lan, Zhangli

Author_Institution

Sch. of Comput. & Inf., Chongqing Jiaotong Univ., Chongqing

fYear

2008

fDate

5-8 Aug. 2008

Firstpage

432

Lastpage

437

Abstract

Face detection is a key technique of face recognition using images in video sequences. In order to improve the accuracy of face location in video sequences, the paper presents a method for locating face in video sequences through analysis of face features in video sequences. Background removing, skin region detecting, horizontal brightness projection and face template with gradient calculating, feature component fitting are adopted for this method. The experiments demonstrate that this method can meet the requirements of actual application. In addition, face recognition-based access control system has been developed using this method.

Keywords

face recognition; image sequences; video signal processing; face detection; face location; face recognition-based access control system; face template; feature component fitting; gradient calculation; horizontal brightness projection; skin region detection; video sequence; Access control; Brightness; Eyes; Face detection; Face recognition; Fingerprint recognition; Humans; Pattern recognition; Skin; Video sequences; Background Removing; Face Location; Face Template; Skin Region; Video Sequence;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, 2008. ICMA 2008. IEEE International Conference on

Conference_Location

Takamatsu

Print_ISBN

978-1-4244-2631-7

Electronic_ISBN

978-1-4244-2632-4

Type

conf

DOI

10.1109/ICMA.2008.4798793

Filename

4798793