Fully automatic face recognition system using a combined audio-visual approach

Get BibTex-formatted data

Download

PDF

Author

A Albiol, L Torres, EJ Delp

Entry type

article

Abstract

This paper presents a novel audio and video information fusion approach that greatly improves automatic recognition of people in video sequences. To that end, audio and video information is first used independently to obtain confidence values that indicate the likelihood that a specific person appears in a video shot. Finally, a post-classifier is applied to fuse audio and visual confidence values. The system has been tested on several news sequences and the results indicate that a significant improvement in the recognition rate can be achieved when both modalities are used together.

Download

PDF

Date

2005 – 06

Journal

Vision, Image and Signal Processing, IEE Proceedings

Key alpha

Delp

Number

152

Pages

318-326

Volume

Publication Date

2005-06-01

Keywords

lassification, face recognition, speaker recognition audio-video information fusion, combined audio-visual method, fully automatic face recognition system, news sequences, post-classifier, recognition likelihood confidence values, recognition rate, video sequences

BibTex-formatted data

To refer to this entry, you may select and copy the text below and paste it into your BibTex document. Note that the text may not contain all macros that BibTex supports.

@Article{ Delp,
	title = "Fully automatic face recognition system using a combined audio-visual approach",
	author = "A Albiol, L Torres, EJ Delp",
	year = "2005",
	month = "06",
	journal = "Vision, Image and Signal Processing, IEE Proceedings",
	number = "152",
	pages = "318-326",
	volume = "3",
	abstract = "This paper presents a novel audio and video information fusion approach that greatly improves automatic recognition of people in video sequences. To that end, audio and video information is first used independently to obtain confidence values that indicate the likelihood that a specific person appears in a video shot. Finally, a post-classifier is applied to fuse audio and visual confidence values. The system has been tested on several news sequences and the results indicate that a significant improvement in the recognition rate can be achieved when both modalities are used together.",
	keywords = "lassification, face recognition, speaker recognition audio-video information fusion, combined audio-visual method, fully automatic face recognition system, news sequences, post-classifier, recognition likelihood confidence values, recognition rate, video sequences",
}