|The Fisher{Rao linear discriminant analysis (LDA) is a valuable tool for multi-class clas-siication and data reduction. We investigate LDA within the maximum likelihood framework and propose a general formulation to handle heteroscedastic-ity. Small size numerical experiments with randomly generated data verify the validity of our formulation.

This paper develops a method for automatically incorporating variable selection in Fisher’s linear discriminant analysis (LDA). Utilizing the connection of Fisher’s LDA and a generalized eigenvalue problem, our approach applies the method of regularization to obtain sparse linear discriminant vectors, where “sparse” means that the discriminant vectors have only a small number of nonzero compone...

Linear discriminant analysis (LDA) is commonly used for dimensionality reduction. In real-world applications where labeled data are scarce, LDA does not work very well. However, unlabeled data are often available in large quantities. We propose a novel semi-supervised discriminant analysis algorithm called SSDACCCP . We utilize unlabeled data to maximize an optimality criterion of LDA and use t...

This paper presents a constructive method for deriving an updated discriminant eigenspace for classification, when bursts of new classes of data is being added to an initial discriminant eigenspace in the form of random chunks. The proposed Chunk incremental linear discriminant analysis (I-LDA) can effectively evolve a discriminant eigenspace over a fast and large data stream, and extract featu...

In this paper, the method of kernel Fisher discriminant (KFD) is analyzed and its nature is revealed, i.e., KFD is equivalent to kernel principal component analysis (KPCA) plus Fisher linear discriminant analysis (LDA). Based on this result, a more transparent KFD algorithm is proposed. That is, KPCA is ;rst performed and then LDA is used for a second feature extraction in the KPCA-transformed ...

The performance of supervised learning-based seganalysis depends on the choice of both classifier and features which represent the image. Features extracted from images may contain irrelevant and redundant features which makes them inefficient for machine learning. Relevant features not only decrease the processing time to train a classifier but also provide better generalisation. Linear discri...

Fisher{Rao Linear Discriminant Analysis (LDA), a valuable tool for multi-group classiication and data reduction, has been investigated in the maximum likelihood framework. It has been shown that the LDA solution is a special case from the more general class of solutions. Generalizations of the LDA formulation have been proposed to handle the case where the within class variances are unequal, an...

It is well-known that the applicability of both linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) to high-dimensional pattern classification tasks such as face recognition (FR) often suffers from the socalled ‘‘small sample size’’ (SSS) problem arising from the small number of available training samples compared to the dimensionality of the sample space. In this paper...

In this paper we describe a face recognition method based on PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis). The method consists of two steps: rst we project the face image from the original vector space to a face subspace via PCA, second we use LDA to obtain a best linear clas-siier. The basic idea of combining PCA and LDA is to improve the generalization capability ...

Problem statement: In facial biometrics, face features are used as the required human traits for automatic recognition. Feature extracted from face images are significant for face biometrics system performance. Approach: In this thesis, a framework of facial biometric was designed based on two subspace methods i.e., Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Firs...