Haar-like Features for Robust Real-Time Face Recognition

Kamal Nasrollahi; Thomas B. Moeslund

doi:10.1109/ICIP.2013.6738633

Haar-like Features for Robust Real-Time Face Recognition

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

10 Citations (Scopus)

973 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Publisher	IEEE Signal Processing Society
Publication date	15 Sept 2013
DOIs	https://doi.org/10.1109/ICIP.2013.6738633
Publication status	Published - 15 Sept 2013
Event	IEEE International Conference on Image Processing - Melbourne, Australia Duration: 15 Sept 2013 → 18 Sept 2013

Conference

Conference	IEEE International Conference on Image Processing
Country/Territory	Australia
City	Melbourne
Period	15/09/2013 → 18/09/2013

Keywords

Haar-like rectangular features
face recognition
integral images

Access to Document

10.1109/ICIP.2013.6738633

icip-2013Submitted manuscript, 555 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6738633&queryText%3DHaar-like+Features+for+Robust+Real-Time+Face+Recognition

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{7015062bb12c4b22843003afc0c003ca,

title = "Haar-like Features for Robust Real-Time Face Recognition",

abstract = "Face recognition is still a very challenging task when the inputface image is noisy, occluded by some obstacles, of verylow-resolution, not facing the camera, and not properly illuminated.These problems make the feature extraction andconsequently the face recognition system unstable. The proposedsystem in this paper introduces the novel idea of usingHaar-like features, which have commonly been used forobject detection, along with a probabilistic classifier for facerecognition. The proposed system is simple, real-time, effectiveand robust against most of the mentioned problems. Experimentalresults on public databases show that the proposedsystem indeed outperforms the state-of-the-art face recognitionsystems.",

keywords = "Haar-like rectangular features, face recognition, integral images",

author = "Kamal Nasrollahi and Moeslund, {Thomas B.}",

year = "2013",

month = sep,

day = "15",

doi = "10.1109/ICIP.2013.6738633",

language = "English",

booktitle = "IEEE International Conference on Image Processing",

publisher = "IEEE Signal Processing Society",

address = "United States",

note = "IEEE International Conference on Image Processing ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Haar-like Features for Robust Real-Time Face Recognition

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2013/9/15

Y1 - 2013/9/15

N2 - Face recognition is still a very challenging task when the inputface image is noisy, occluded by some obstacles, of verylow-resolution, not facing the camera, and not properly illuminated.These problems make the feature extraction andconsequently the face recognition system unstable. The proposedsystem in this paper introduces the novel idea of usingHaar-like features, which have commonly been used forobject detection, along with a probabilistic classifier for facerecognition. The proposed system is simple, real-time, effectiveand robust against most of the mentioned problems. Experimentalresults on public databases show that the proposedsystem indeed outperforms the state-of-the-art face recognitionsystems.

AB - Face recognition is still a very challenging task when the inputface image is noisy, occluded by some obstacles, of verylow-resolution, not facing the camera, and not properly illuminated.These problems make the feature extraction andconsequently the face recognition system unstable. The proposedsystem in this paper introduces the novel idea of usingHaar-like features, which have commonly been used forobject detection, along with a probabilistic classifier for facerecognition. The proposed system is simple, real-time, effectiveand robust against most of the mentioned problems. Experimentalresults on public databases show that the proposedsystem indeed outperforms the state-of-the-art face recognitionsystems.

KW - Haar-like rectangular features

KW - face recognition

KW - integral images

U2 - 10.1109/ICIP.2013.6738633

DO - 10.1109/ICIP.2013.6738633

M3 - Article in proceeding

BT - IEEE International Conference on Image Processing

PB - IEEE Signal Processing Society

T2 - IEEE International Conference on Image Processing

Y2 - 15 September 2013 through 18 September 2013

ER -

Haar-like Features for Robust Real-Time Face Recognition

Abstract

Conference

Keywords

Access to Document

AUB Link

Fingerprint

Cite this