Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition

Lu, Juwei; Plataniotis, Konstantinos N.; Venetsanopoulos, A.N.

doi:10.1016/j.patrec.2004.09.014

Cited by 276 publications

(152 citation statements)

References 27 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…This in turn increases the likelihood that S w is degenerate, and further necessitates the need for a method such as RS-LDA. Other LDA variants offer solutions to this small sample size problem [13,7]; however, RS-LDA is preferred due to the ease of implementation and wider range of successful applications in face recognition [23,11,8,9].…”

Section: Random Subspace Face Recognitionmentioning

confidence: 99%

Face recognition across time lapse: On learning feature subspaces

Klare

Jain

2011

2011 International Joint Conference on Biometrics (IJCB)

View full text Add to dashboard Cite

There is a growing interest in understanding the impact of aging on face recognition performance, as well as designing recognition algorithms that are mostly invariant to temporal changes. While some success has been made on this front, a fundamental questions has yet to be answered: do face recognition systems that compensate for the effects of aging compromise recognition performance for faces that have not undergone any aging? The studies in this paper help confirm that age invariant systems do seem to decrease performance in non-aging scenarios. This is demonstrated by performing training experiments on the largest face aging dataset studied in the literature to date (over 200,000 images from roughly 64,000 subjects). Further experiments conducted in this research help demonstrate the impact of aging on two leading commercial face recognition systems. We also determine the regions of the face that remain the most stable over time.

show abstract

Section: Random Subspace Face Recognitionmentioning

confidence: 99%

Face recognition across time lapse: On learning feature subspaces

Klare

Jain

2011

2011 International Joint Conference on Biometrics (IJCB)

View full text Add to dashboard Cite

show abstract

“…The representative LSL methods, including PCA (Eigenface), LPP (Laplacianface) [7], FLDA (Fisherface) [2], RLDA [4] and SPP [21], are used for comparison. The code of the proposed USCP and SSCP methods can be downloaded at http://www4.comp.polyu.edu.hk/~cslzhang/code.htm.…”

Section: Resultsmentioning

confidence: 99%

“…Representative LSL methods include principal component analysis (PCA), e.g., Eigenface [1], Fisher linear discriminant analysis (FLDA) [2][3][4], the manifold learning [5][6] based locality preserving projection (LPP) [7], local discriminant embedding (LDE) [8], graph embedding [9], etc. According to if the class label information of the training samples is exploited, the LSL methods can be categorized into unsupervised methods (e.g., PCA and LPP) and supervised methods (e.g., FLDA [2], regularized LDA (RLDA) [4] and LDE).…”

Section: Introductionmentioning

confidence: 99%

A linear subspace learning approach via sparse coding

Zhang

Zhu

2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…To this end, we first introduce a regularized Fisher's criterion [14]. The criterion, which is utilized in this work instead of the conventional one (Eq.6), can be expressed as follows:…”

Section: A Regularized Fisher's Criterionmentioning

confidence: 99%

Kernel Discriminant Learning with Application to Face Recognition

Venetsanopoulos

Rogers

2005

Support Vector Machines: Theory and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. When applied to high-dimensional pattern classification tasks such as face recognition, traditional kernel discriminant analysis methods often suffer from two problems: 1) small training sample size compared to the dimensionality of the sample (or mapped kernel feature) space, and 2) high computational complexity. In this chapter, we introduce a new kernel discriminant learning method, which attempts to deal with the two problems by using regularization and subspace decomposition techniques. The proposed method is tested by extensive experiments performed on real face databases. The obtained results indicate that the method outperforms, in terms of classification accuracy, existing kernel methods, such as kernel Principal Component Analysis and kernel Linear Discriminant Analysis, at a significantly reduced computational cost.

show abstract

Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition

Cited by 276 publications

References 27 publications

Face recognition across time lapse: On learning feature subspaces

Face recognition across time lapse: On learning feature subspaces

A linear subspace learning approach via sparse coding

Kernel Discriminant Learning with Application to Face Recognition

Contact Info

Product

Resources

About