Yue-Fei Guo

Discriminant neighborhood embedding for classification

In this paper a novel subspace learning method called discriminant neighborhood embedding (DNE) is proposed for pattern classification. We suppose that multi-class data points in high-dimensional space tend to move due to local intra-class attraction or inter-class repulsion and the optimal embedding from the point of view of classification is discovered consequently. After being embedded into a low-dimensional subspace, data points in the same class form compact submanifod whereas the gaps between submanifolds corresponding to different classes become wider than before. Experiments on the UMIST and MNIST databases demonstrate the effectiveness of our method.

Optimal dimensionality of metric space for classification

In many real-world applications, Euclidean distance in the original space is not good due to the curse of dimensionality. In this paper, we propose a new method, called Discriminant Neighborhood Embedding (DNE), to learn an appropriate metric space for classification given finite training samples. We define a discriminant adjacent matrix in favor of classification task, i.e., neighboring samples in the same class are squeezed but those in different classes are separated as far as possible. The optimal dimensionality of the metric space can be estimated by spectral analysis in the proposed method, which is of great significance for high-dimensional patterns. Experiments with various datasets demonstrate the effectiveness of our method.

Metric learning by discriminant neighborhood embedding

In this paper, we learn a distance metric in favor of classification task from available labeled samples. Multi-class data points are supposed to be pulled or pushed by discriminant neighbors. We define a discriminant adjacent matrix in favor of classification task and learn a map transforming input data into a new space such that intra-class neighbors become even more nearby while extra-class neighbors become as far away from each other as possible. Our method is non-parametric, non-iterative, and immune to small sample size (SSS) problem. Target dimensionality of the new space is selected by spectral analysis in the proposed method. Experiments on real-world data sets demonstrate the effectiveness of our method.

Null Foley–Sammon transform

Abstract In this paper, an important conclusion for linear discriminant analysis is proved: in the case of the small sample size, ( number-of-classes -1) null projection directions (NPDs) do exist, on which, the within-class distance equals zero and the between-class distance is positive. The Null Foley–Sammon Transform (NFST), which is constituted by NPDs, is also proposed. Its effectiveness is evidenced by experiments on face recognition.

A covariance-free iterative algorithm for distributed principal component analysis on vertically partitioned data

In this paper, a covariance-free iterative algorithm is developed to achieve distributed principal component analysis on high-dimensional data sets that are vertically partitioned. We have proved that our iterative algorithm converges monotonously with an exponential rate. Different from existing techniques that aim at approximating the global PCA, our covariance-free iterative distributed PCA (CIDPCA) algorithm can estimate the principal components directly without computing the sample covariance matrix. Therefore a significant reduction on transmission costs can be achieved. Furthermore, in comparison to existing distributed PCA techniques, CIDPCA can provide more accurate estimations of the principal components and classification results. We have demonstrated the superior performance of CIDPCA through the studies of multiple real-world data sets.

Rapid and brief communication: Null Foley-Sammon transform

Abstract In this paper, an important conclusion for linear discriminant analysis is proved: in the case of the small sample size, ( number-of-classes -1) null projection directions (NPDs) do exist, on which, the within-class distance equals zero and the between-class distance is positive. The Null Foley–Sammon Transform (NFST), which is constituted by NPDs, is also proposed. Its effectiveness is evidenced by experiments on face recognition.

Efficient Feature Extraction for Image Classification

In many image classification applications, input feature space is often high-dimensional and dimensionality reduction is necessary to alleviate the curse of dimensionality or to reduce the cost of computation. In this paper, we extract discriminant features for image classification by learning a low-dimensional embedding from finite labeled samples. In the new feature space, intra-class compactness and extra-class separability are achieved simultaneously. Target dimensionality of the embedding is selected by spectral analysis. Our method is designed suitable for data with both uni- and multi-modal class distributions. We also develop its two-dimensional variant which makes use of the matrix representation of images. Experimental results on three real image datasets demonstrate the efficacy of our method compared to the state of the art.

Leveraging Color Harmony and Spatial Context for Aesthetic Assessment of Photographs

Computer aesthetic assessment of pictures is aimed at automatically computed aesthetic values of pictures. It has potential wide areas of application in real world. We apply color harmony, one of the most important aesthetic standards, and explore the spatial context of features. Based on the framework ofi¾?[9], we provide a color harmony descriptor which includes the circular region sampling method, and follow the principle of Ordered-Bag-of-Features to explore the spatial context. And we conduct experiments on a public and large-scale aesthetic assessment dataset. Experimental results demonstrate the effectiveness of the proposed method.

Quotient Set-based Nonlinear Manifold for Image Restoration

In this paper we propose a patch-wise coarse-to-fine algorithm for image restoration using the manifold way of visual perception. All undistorted image patches are supposed to lie on a quotient set-based nonlinear manifold, and restoration of each degraded image patch can be implemented by projecting it to a locally linear region of such nonlinear manifold. The details of the original image can be learned from the undistorted training samples. Moreover, there is no need for us to assume that the degradation function is linear or to estimate some parameters of the blurs and noises beforehand. Experimental results demonstrate the effectiveness of the proposed method

Rapid and brief communicationNull Foley–Sammon transform

Abstract In this paper, an important conclusion for linear discriminant analysis is proved: in the case of the small sample size, ( number-of-classes -1) null projection directions (NPDs) do exist, on which, the within-class distance equals zero and the between-class distance is positive. The Null Foley–Sammon Transform (NFST), which is constituted by NPDs, is also proposed. Its effectiveness is evidenced by experiments on face recognition.