Kernel class-wise locality preserving projection
Introduction
In pattern recognition, feature extraction techniques are widely employed to reduce the dimensionality of data and to enhance the discriminatory information [7]. Most feature extraction methods have focused on finding the linear transformation to project the data from a high-dimensional input space into a lower dimensional feature space, and the feature vector in the feature space contains all the necessary discriminative information. In the past several decades, many dimensionality reduction techniques have been proposed. The most well-known feature extraction methods may be principal component analysis (PCA) [1] and linear discriminant analysis (LDA) [2]. PCA seeks a linear optimal transformation matrix to minimize the mean squared error criterion, and the optimal matrix is constituted by the largest eigenvectors (called principal components) of the sample covariance. The purpose of PCA is to keep the information in terms of variance as much as possible. Linear discriminant analysis (also called Fisher’s linear discriminant) is another popular linear dimensionality reduction method. In many applications, LDA has proven to be much more effective than PCA. In the previous work, PCA was generalized to the nonlinear curves such as principal curves [6] and its extension such as principal surfaces [3]. Principal curves and principal surfaces are the nonlinear generalizations of principal components and subspaces respectively. It has turned out that discretized principal curves are essentially equivalent to self-organizing maps (SOM) [13], [16]. SOM is a nonparametric latent variable model with a topological constraint, such as lines, squares, or hexagonal grids and its mapping is similar to a discrete self-similarity principle for a principal manifold. SOM is a data driven dimensionality reduction method. SOM is regarded as an approximation of the principal surface. SOM was extended to Visualisation-induced SOM (ViSOM) [27]. ViSOM represents a discrete principal curve or surface, and ViSOM produces a smooth and graded mesh in the data space and captures the nonlinear manifold of data [25]. Moreover, other nonlinear manifold algorithms have been proposed, such as Locally Linear Embedding (LLE) [17] and Isomap [22]. LLE regards dimensionality reduction as geometrical perspective, while Isomap utilizes geodesic distances to represent connected graphs and relationship among data. Both LLE and Isomap preserve the neighborhoods and geometric relationships of the data. Isomap and LLE map easily the training data points in the reduced dimensional space, but it is hard to locate the test data points. Locality preserving projection [8] locates easily the new data point in the reduced representation space. But LPP is a linear dimensionality reduction method and has no the sufficient nonlinear discriminant power for linearly non-separable classes. Kernel methods have been widely used to overcome the limitation of some linear feature extraction and classification. Kernel-based learning feature extraction methods, such as Kernel Principal Component Analysis (KPCA) [19], [11], Kernel Discriminant Analysis (KDA) [14], [26] and Support Vector Machine (SVM) [10], [24], were widely used in the pattern recognition and machine learning areas [4], [23]. Other research topics relative to kernel-based learning have attracted researchers more and more attention [12], [15], [18], [20]. LPP was successfully applied in the pattern recognition and information retrieval areas. For example, LPP based feature extraction method namely Laplacianfaces was proposed for face recognition [9]. LPP constructs the adjacency graph by doing the nearest neighbor search, and the original data are mapped to the low dimensional space for feature extraction. LPP performs well on many practical applications, such as audio, video, text documents retrieval. Moreover, all of these methods are completely unsupervised with regard to the class labels of the data, and have little to do with discriminative features optimal for classification. In this paper, a novel local structure based feature extraction method based on the idea of LPP, namely class-wise locality preserving projection (CLPP), is proposed to enhance the class structure of the data. Unlike the unsupervised learning scheme of LPP, CLPP follows the supervised learning scheme, i.e. it uses the class information to model the manifold structure. In CLPP, the local structure of the original data is constructed according to a certain way of constructing the nearest neighbor graph, which takes special consideration of both the local information and the class information. Moreover, we improve CLPP on nonlinear feature extraction with kernel trick to develop Kernel CLPP algorithm and make CLPP a robust technique for the feature extraction tasks.
The rest of this paper is organized as follows. The detailed formulation and development of KCLPP are described in Section 2. An evaluation of the proposed method on two databases is reported in Section 3. Finally, Section 4 draws a conclusion and opens a prospective for future work.
Section snippets
Kernel class-wise locality preserving projection (KCLPP)
In this section, firstly we review LPP algorithm briefly, and secondly we present the CLPP algorithm and its kernel version in detail, and finally we introduce the detailed procedure of the proposed algorithm on feature extraction and classification.
Experimental results and discussion
In this section, we implement experiments on ORL and YALE databases to evaluate the proposed algorithm. Firstly we select the procedure parameters with cross-validation method, i.e., k for k nearest neighbor measure, δ for similarity measure, kernel parameters, and secondly we evaluate the performance of proposed algorithm on computation efficiency and recognition accuracy.
Conclusion and future work
A novel supervised feature extraction method namely class-wise locality preserving projection (CLPP) and its kernel extension are proposed in this paper. Main contributions are summarized as follows. (1) Both the local structure and class labels are taken enough consideration for feature extraction based on CLPP algorithm. (2) CLPP guides the procedure of constructing the nearest neighbor graph with the information labels, and CLPP achieves the higher computation efficiency compared with LPP
Acknowledgement
The authors thank the anonymous reviewers for their constructive comments.
References (27)
A new gesture recognition algorithm and segmentation method of Korean scripts for gesture-allowed ink editor
Information Sciences
(2006)Fuzzy integral-based perceptron for two-class pattern classification problems
Information Sciences
(2007)- et al.
Support vector machines with genetic fuzzy feature transformation for biomedical data classification
Information Sciences
(2007) On detecting nonlinear patterns in discriminant problems
Information Sciences
(2006)Data visualisation and manifold mapping using the ViSOM
Neural Networks
(2002)- et al.
Self-organizing learning array and its application to economic and financial problems
Information Sciences
(2007) - et al.
Eigenfaces vs. Fisherfaces: recognition using class specific linear projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
(1997) - A.U. Batur, M.H. Hayes, Linear subspace for illumination robust face recognition, in: Proc. IEEE Intl. Conf. Computer...
- et al.
A unified model for probabilistic principal surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
(2001) - et al.
Matrix Computations
(1996)
Principal curves
Journal of the American Statistical Association
Face recognition using Laplacianfaces
IEEE Transaction on Pattern Analysis and Machine Intelligence
Cited by (122)
Linear dimensionality reduction method based on topological properties
2023, Information SciencesKernelized Supervised Laplacian Eigenmap for Visualization and Classification of Multi-Label Data
2022, Pattern RecognitionA survey on Laplacian eigenmaps based manifold learning methods
2019, NeurocomputingFace recognition based on Volterra kernels direct discriminant analysis and effective feature classification
2018, Information SciencesCitation Excerpt :However, these methods demonstrate reduced efficiency when dealing with expression and illumination changes. Several advanced methods based on global feature representation [3,6,16,17,19,25,44] were proposed recently to enhance the discriminative capability of the learned feature. Local features are more stable than global features when they are used to deal with local changes, such as illumination, expression, and inaccurate alignment.
Locality-regularized linear regression discriminant analysis for feature extraction
2018, Information Sciences