Discriminant Locality Preserving Projections Research Articles

An Image Retrieval Model Based on Local Fisher Discriminant Analysis

This paper introduces an image retrieval model based on dimensionality reduction. The proposed model is divided into two main techniques, the first one is concerned with the feature extraction from image database, and the second one is performing a dimensionality reduction. In the first technique, the color histogram and Color Texture Moment are used to extract the color and texture features, respectively. In the second technique, Local Fisher Discriminant Analysis (LFDA) which is a supervised linear dimensionality reduction algorithm is used to performing dimensionality. LFDA combines the ideas of Fisher Discriminant Analysis (FDA) and Locality Preserving Projection (LPP). LFDA can preserve both manifold of data and discriminant information. Experiments demonstrate that the proposed image retrieval scheme based on dimensionality reduction can achieve satisfactory results.

Orthogonal Complete Discriminant Locality Preserving Projections for Face Recognition

In this paper, we propose a novel orthogonal complete discriminant locality preserving projections for facial feature extraction and recognition (OCDLPP). All training samples are projected into the range of a so-called locality preserving total scatterto reduce dimensionality without loss of discriminative information. The transformation matrix of OCDLPP is orthogonal and is found simultaneously using QR decomposition technique. Moreover, a feasible and effective procedure is proposed to alleviate the computational burden of high dimensional matrix for typical face image data. Experiments results on the ORL, Yale, FERET and PIE face databases show the effectiveness of the proposed OCDLPP.

Face recognition using regularised generalised discriminant locality preserving projections

Discriminant locality preserving projection (DLPP) is a recently proposed algorithm, which is an extension of locality preserving projections (LPP) and can encode both the geometrical and discriminant structure of the data manifold. However, DLPP suffers from small sample size (SSS) problem which is often encountered in face recognition tasks. To deal with this problem, the authors propose a novel regularised generalised discriminant locality preserving projections (RGDLPP) method for facial feature extraction and recognition. First, locality preserving within-class scatter in DLPP method is replaced by locality preserving total scatter and all the training samples are projected into the range of locality preserving total scatter. Then the authors regularise the small and zero eigenvalues of locality preserving within-class scatter since the small eigenvalues are sensitive to noise. RGDLPP address SSS problem by removing the null space of locality preserving total scatter without loss of discriminant information. Meanwhile, RGDLPP can alleviate the problem of noise disturbance of the small eigenvalues. Experiments on the ORL, Yale, FERET and PIE face databases show the effectiveness of the proposed RGDLPP.

Complete Discriminant Locality Preserving Projections for Face Recognition

To efficiently utilize the discriminant information in the range space of locality preserving total scatter, this paper proposes a complete discriminant locality preserving projections (CDLPP) algorithm for face recognition. Since Fisher discriminant analysis and locality preserving projections (LPP) have been widely used in face recognition, CDLPP algorithm integrates them together and analyzes the discriminant information contained in the principal spaces and null spaces of locality preserving within-class scatter, locality preserving between-class scatter and locality preserving total scatter. First, CDLPP algorithm removes the null space of locality preserving total scatter, in which no discriminant information is contained, using singular value decomposition (SVD). Then, regular discriminant features and irregular discriminant features of CDLPP are extracted severally in the null space and principal space of the locality preserving within-class scatter. Finally, both regular discriminant features and irregular discriminant features are concatenated to be used for face recognition. Extensive experiments on ORL face database, FERET subset and PIE subset illustrate that the performances of CDLPP outperform those of current subspace face recognition algorithms, such as LDA, LPP and discriminant LPP, which proves the effectiveness of the proposed algorithm.

Comment on “Facial expression recognition based on two-dimensional discriminant locality preserving projections” [Neurocomputing 71 (2008) 1730-1734

In this note, we show that the mathematical formulation of the two-dimensional discriminant locality preserving projections (2D-DLPP) proposed in the paper [R. Zhi, Q. Ruan, Facial expression recognition based on two-dimensional discriminant locality preserving projections, Neurocomputing 71 (2008) 1730–1734] is not very sound. The rigorous version is thus given. We also point out that 2D-DLPP can be viewed from the perspective of the discriminant locality preserving projections (DLPP).

Null space discriminant locality preserving projections for face recognition

In this paper, we propose a null space discriminant locality preserving projections (NDLPP) method for facial feature extraction and recognition. Based on locality preserving projections (LPP) and discriminant locality preserving projections (DLPP) methods, NDLPP comes into the characteristics of DLPP that encodes both the geometrical and discriminant structure of the data manifold, and addresses the small sample size problem by solving an eigenvalue problem in null space. Experiments on synthetic data and ORL, Yale, and FERET face databases are performed to test and evaluate the proposed algorithm. The results demonstrate the effectiveness of NDLPP.

Uncorrelated Discriminant Locality Preserving Projections

In this letter, a new manifold learning algorithm, called uncorrelated discriminant locality preserving projections (UDLPP), is proposed. The aim of UDLPP is to preserve the within-class geometric structure, while maximizing the between-class distance. By introducing a simple uncorrelated constraint into the objective function, we show that the extracted features via UDLPP are statistically uncorrelated, which is desirable for many pattern analysis applications. Moreover, UDLPP can be performed in reproducing kernel Hilbert space, which gives rise to kernel UDLPP. Experimental results on both face recognition and radar target recognition demonstrate the effectiveness of the proposed algorithm.

Face recognition using discriminant locality preserving projections

Locality Preserving Projections (LPP) is a linear projective map that arises by solving a variational problem that optimally preserves the neighborhood structure of the data set. Though LPP has been applied in many domains, it has limits to solve recognition problem. Thus, Discriminant Locality Preserving Projections (DLPP) is presented in this paper. The improvement of DLPP algorithm over LPP method benefits mostly from two aspects: One aspect is that DLPP tries to find the subspace that best discriminates different face classes by maximizing the between-class distance, while minimizing the within-class distance; The other aspect is that DLPP reduces the energy of noise and transformation difference as much as possible without sacrificing much of intrinsic difference. In the experiments, DLPP achieves better face recognition performance than LPP.