Semi-automatic method of face recognition based on extended training set

Olga Krutikova, Aleksandrs Glazs

Abstract


The existing algorithms of face recognition are designed to be used with adequate training samples (different positions of the face, special conditions, etc.). Therefore, in this paper we propose a semi-automatic method of face recognition that is based on extending the training sample by using a 3D model of a head. The recognition algorithm uses control points and relations between them. The experimental results show the efficiency of the proposed approach.


Full Text: PDF

Refbacks

  • There are currently no refbacks.


 

 

 

_______________________________________________________________________________________________________________________________________

BIOMEDICAL ENGINEERING CONFERENCE ORGANIZING COMMITEE,

BIOMEDICAL ENGINEERING INSTITUTE,

KAUNAS UNIVERSITY OF TECHNOLOGY.