Likelihood Normalization For Face Authentication In Variable Recording Conditions

DMCA

Likelihood Normalization For Face Authentication In Variable Recording Conditions (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Conrad Sanderson , Kuldip K. Paliwal

Citations:

9 - 3 self

BibTeX

@MISC{Sanderson02likelihoodnormalization,
    author = {Conrad Sanderson and Kuldip K. Paliwal},
    title = {Likelihood Normalization For Face Authentication In Variable Recording Conditions},
    year = {2002}
}

OpenURL

Abstract

In this paper we evaluate the effectiveness of two likelihood normalization techniques, the Background Model Set (BMS) and the Universal Background Model (UBM), for improving performance and robustness of four face authentication systems utilizing a Gaussian Mixture Model (GMM) classifier. The systems differ in the feature extraction method used: eigenfaces (PCA), 2-D DCT, 2-D Gabor wavelets and DCT-mod2. Experiments on the VidTIMIT database, using test images corrupted either by an illumination change or compression artefacts, suggest that likelihood normalization has little effect when using PCA derived features, while providing significant performance improvements when using the remaining features.

Keyphrases

likelihood normalization variable recording condition face authentication compression artefact illumination change feature extraction method background model set test image 2-d dct little effect face authentication system gaussian mixture model 2-d gabor wavelet vidtimit database universal background model significant performance improvement likelihood normalization technique

DMCA