Haar-like Features for Robust Real-Time Face Recognition

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

Face recognition is still a very challenging task when the input
face image is noisy, occluded by some obstacles, of very
low-resolution, not facing the camera, and not properly illuminated.
These problems make the feature extraction and
consequently the face recognition system unstable. The proposed
system in this paper introduces the novel idea of using
Haar-like features, which have commonly been used for
object detection, along with a probabilistic classifier for face
recognition. The proposed system is simple, real-time, effective
and robust against most of the mentioned problems. Experimental
results on public databases show that the proposed
system indeed outperforms the state-of-the-art face recognition
systems.
Luk

Detaljer

Face recognition is still a very challenging task when the input
face image is noisy, occluded by some obstacles, of very
low-resolution, not facing the camera, and not properly illuminated.
These problems make the feature extraction and
consequently the face recognition system unstable. The proposed
system in this paper introduces the novel idea of using
Haar-like features, which have commonly been used for
object detection, along with a probabilistic classifier for face
recognition. The proposed system is simple, real-time, effective
and robust against most of the mentioned problems. Experimental
results on public databases show that the proposed
system indeed outperforms the state-of-the-art face recognition
systems.
OriginalsprogEngelsk
TitelIEEE International Conference on Image Processing
ForlagIEEE Signal Processing Society
Publikationsdato15 sep. 2013
DOI
StatusUdgivet - 15 sep. 2013
PublikationsartForskning
Peer reviewJa
BegivenhedIEEE International Conference on Image Processing - Melbourne, Australien
Varighed: 15 sep. 201318 sep. 2013

Konference

KonferenceIEEE International Conference on Image Processing
LandAustralien
ByMelbourne
Periode15/09/201318/09/2013

Download-statistik

Ingen data tilgængelig
ID: 77951261