Matching Methods for Automatic Face Recognition using SIFT

Matching Methods for Automatic Face Recognition using SIFT

The object of interest of this paper is Automatic Face Recognition (AFR). The usual methods need a labeled corpus and the number of training examples plays a crucial role for the recognition accuracy. Unfortunately, the corpus creation is very expensive and time consuming task. Therefore, the motivation of this work is to propose and implement new AFR approaches that could solve this issue and perform wellalso with few training examples. Our approaches extend the successful method based on the Scale Invariant Feature Transform (SIFT) proposed by Aly. We propose and evaluate two methods: Lenc-Kral matching and adapted Kepenekci approach [7]. Our approaches are evaluated on two face data-sets: the ORL database and the Czech News Agency (─îTK) corpus. We experimentally show that the proposed approaches significantly outperform the baseline Aly method on both corpora.

Keywords: automatic face recognition, czech news agency, scaleinvariant feature transform (SIFT)

Year: 2012

Download: download Full text [113 kB]

Authors of this publication:

Pavel Kr├íl

Phone: +420 377 632 454
E-mail: pkral@kiv,

Pavel is a lecturer/researcher at the Department of Computer Science and Engineering at the University of West Bohemia in Pilsen (Czech Republic). His research is focused on automatic speech processing, dialog act recognition, syntactic parsing, punctuation annotation and document classification.