Combined approach to face detection for biometric identification systems

Author

Paliy, Ihor ; Sachenko, Anatoly ; Kurylyak, Yuriy ; Boumbarov, Ognian ; Sokolov, Strahil

fYear

2009

fDate

21-23 Sept. 2009

Firstpage

425

Lastpage

429

Abstract

The paper describes combined approach to face detection for grayscale images using the combined cascade of neural network classifiers which consists of Haar-like features´ cascade of weak classifiers and convolutional neural network. The combined cascade with proposed face candidates´ verification method allows achieving one of the best detection rates on CMU test set and a high processing speed suitable for a video flow processing. In the last stage of our algorithm we provide extraction of salient facial features for pose estimation and recognition.

Keywords

biometrics (access control); face recognition; feature extraction; image classification; neural nets; pose estimation; video signal processing; CMU test set; Haar-like feature cascade extraction; biometric identification system; face candidate verification method; face detection; facial feature extraction; grayscale image processing; neural network classifier; pose estimation; pose recognition; video flow processing; Biometrics; Face detection; cascade of weak classifiers; combined cascade of neural network classifiers; convolutional neural network; face detection; salient features; template matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2009. IDAACS 2009. IEEE International Workshop on

Conference_Location

Rende

Print_ISBN

978-1-4244-4901-9

Electronic_ISBN

978-1-4244-4882-1

Type

conf

DOI

10.1109/IDAACS.2009.5342946

Filename

5342946