Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification

Kyperountas, Marios; Tefas, Anastasios; Pitas, Ioannis

doi:10.1109/tnn.2006.885038

Cited by 85 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For overcoming the small sample size problem, regularization techniques have also been employed [11], [12]. Moreover, in an indirect way to deal with the singularity problem, another method (2D-LDA), where the data are represented as matrices has been proposed in [10].…”

Section: Related Workmentioning

confidence: 99%

Subclass Marginal Fisher Analysis

Maronidis

Tefas

Pitas

2015

2015 IEEE Symposium Series on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Abstract-Subspace learning techniques have been extensively used for dimensionality reduction (DR) in many pattern classification problem domains. Recently, Discriminant Analysis (DA) methods, which use subclass information for the discrimination between the data classes, have attracted much attention. As DA methods are strongly dependent on the underlying distribution of the data, techniques whose functionality is based on neighbourhood information among the data samples have emerged. For instance, based on the Graph Embedding (GE) framework, which is a platform for developing novel DR methods, Marginal Fisher Analysis (MFA) has been proposed. Although MFA surpasses the above distribution limitations, it fails to model potential subclass structure that might lie within the several classes of the data. In this paper, motivated by the need to alleviate the above shortcomings, we propose a novel DR technique, called Subclass Marginal Fisher Analysis (SMFA), which combines the strength of subclass DA methods with the versatility of MFA. The new method is built by extending the GE framework so as to include subclass information. Through a series of experiments on various real-world datasets, it is shown that SMFA outperforms in most of the cases the state-of-the-art demonstrating the potential of exploiting subclass neighbourhood information in the DR process.

show abstract

Section: Related Workmentioning

confidence: 99%

Subclass Marginal Fisher Analysis

Maronidis

Tefas

Pitas

2015

2015 IEEE Symposium Series on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…This fact has also been demonstrated in the evaluation results that processed the ORL and XM2VTS data. This malady is justified by the fact that the SSS problem is very severe since the lack of sufficient training samples causes improper estimation of a linear separation hyperplane between the classes, thus discriminant analysis cannot be modelled properly [45]. In order to make salient comparisons with other relevant methods, we chose to implement, to the best of our understanding, the related state-of-the-art HDA algorithm in Ref.…”

Section: Evaluation Of Performance With Respect To Available Number Omentioning

confidence: 99%

Dynamic training using multistage clustering for face recognition

Kyperountas

Tefas

Pitas

2008

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

“…Supervised feature extraction [28] methods use the labels of the data to find the most discriminatory features. The best known supervised method is Fisher linear discriminant analysis (FLD), which maximizes the separability measure (1) The between-class scatter and the within-class matrices are defined as (2) (3) where is the class-conditional covariance matrix for the class , is the class-conditional sample mean, and is the global sample mean.…”

Section: A Feature Extractionmentioning

confidence: 99%

Shared Feature Extraction for Nearest Neighbor Face Recognition

Masip

Vitrià

2008

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-In this paper, we propose a new supervised linear feature extraction technique for multiclass classification problems that is specially suited to the nearest neighbor classifier (NN). The problem of finding the optimal linear projection matrix is defined as a classification problem and the Adaboost algorithm is used to compute it in an iterative way. This strategy allows the introduction of a multitask learning (MTL) criterion in the method and results in a solution that makes no assumptions about the data distribution and that is specially appropriated to solve the small sample size problem. The performance of the method is illustrated by an application to the face recognition problem. The experiments show that the representation obtained following the multitask approach improves the classic feature extraction algorithms when using the NN classifier, especially when we have a few examples from each class.Index Terms-Face recognition, feature extraction, multitask learning (MTL), nearest neighbor classification (NN), small sample size problem.

show abstract

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification

Cited by 85 publications

References 30 publications

Subclass Marginal Fisher Analysis

Subclass Marginal Fisher Analysis

Dynamic training using multistage clustering for face recognition

Shared Feature Extraction for Nearest Neighbor Face Recognition

Contact Info

Product

Resources

About