Quad phase minimum average correlation energy filters for reduced memory illumination tolerant face authentication

Authors:
Marios Savvides;B. V. K. Vijaya Kumar
Affiliations:
Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh, PA;Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh, PA
Venue:
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Year:
2003

Citing 0
Cited 7

Adaptive feature representation for robust face recognition using context-aware approach

Neurocomputing
Fingerprint verification using correlation filters

AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
"Corefaces"- robust shift invariant PCA based correlation filter for illumination tolerant face recognition

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Machinery fault diagnosis using cyclostationary statistics and quad phase minimum average correlation energy filters

ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Adaptive context-aware filter fusion for face recognition on bad illumination

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
On the filter combination for efficient image preprocessing under uneven illumination

ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
Hybrid filter fusion for robust visual information processing

KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we propose reduced memory biometric filters for performing distortion tolerant face authentication. The focus of this research is on implementing authentication algorithms on small factor devices with limited memory and computational resources. We compare the full complexity minimum average correlation energy filters for performing illumination tolerant face authentication with our proposed quad phase minimum average correlation energy filters[1] utilizing a Four-Level correlator. The proposed scheme requires only 2bits/frequency in the frequency domain achieving a compression ratio of up to 32:1 for each biometric filter while still attaining very good verification performance (100% in some cases). The results we show are based on the illumination subsets of the CMU PIE database[2] on 65 people with 21 facial images per person.