0 Multilinear Supervised Neighborhood Preserving
نویسنده
چکیده
Subspace learning based pattern recognition methods have attracted considerable interests in recent years, including Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA), and some extensions for 2D analysis. However, a disadvantage of all these approaches is that they perform subspace analysis directly on the reshaped vector or matrix of pixel-level intensity, which is usually unstable under appearance variance. In this chapter, we propose to represent an image as a local descriptor tensor, which is a combination of the descriptor of local regions (K*K-pixel patch) in the image, and is more efficient than the popular Bag-Of-Feature (BOF) model for local descriptor combination. As we know that the idea of BOF is to quantize local invariant descriptors, e.g., obtained using some interest-point detector techniques by Harris & Stephens (1998), and a description with SIFT by Lowe (2004) into a set of visual words by Lazebnik et al. (2006). The frequency vector of the visual words then represents the image, and an inverted file system is used for efficient comparison of such BOFs. However. the BOF model approximately represents each local descriptor feature as a predefined visual word, and vectorizes the local descriptors of an image into a orderless histogram, which may lose some important (discriminant) information of local features and spatial information hold in the local regions of the image. Therefore, this paper proposes to combine the local features of an image as a descriptor tensor. Because the local descriptor tensor retains all information of local features, it will be more efficient for image representation than the BOF model and then can use a moderate amount of local regions to extract the descriptor for image representation, which will be more effective in computational time than the BOF model. For feature representation of image regions, SIFT proposed by Lowe (2004) is improved to be a powerful local descriptor by Lazebnik et al. (2006) for object or scene recognition, which is somewhat invariant to small illumination change. However, in some benchmark database such as YALE and PIE face data sets by Belhumeur et al. (1997), the illumination variance is very large. Then, in order to extract robust features invariant to large illumination, we explore an improved gradient (intensity-normalized gradient) of the image and use histogram of orientation weighed with the improved gradient for local region representation.
منابع مشابه
Orthogonal Tensor Sparse Neighborhood Preserving Embedding for Two-dimensional Image
Orthogonal Tensor Neighborhood Preserving Embedding (OTNPE) is an efficient dimensionality reduction algorithm for two-dimensional images. However, insufficiencies of the robustness performance and deficiencies of supervised discriminant information are remained. Motivated by the sparse learning, an algorithm called Orthogonal Tensor Sparse Neighborhood Embedding (OTSNPE) for two-dimensional im...
متن کاملSemi-supervised Neighborhood Preserving Discriminant Embedding: A Semi-supervised Subspace Learning Algorithm
Over the last decade, supervised and unsupervised subspace learning methods, such as LDA and NPE, have been applied for face recognition. In real life applications, besides unlabeled image data, prior knowledge in the form of labeled data is also available, and can be incorporated in subspace learning algorithm resulting in improved performance. In this paper, we propose a subspace learning met...
متن کاملThe target HRRP recognition with supervised discrimination sparse neighbourhood preserving embedding
In this paper, we combine the objective function of three methods together and propose a new method, called supervised discrimination sparse neighborhood preserving embedding (SDSNPE). The proposed method can preserve the local and global manifold structure of the samples simultaneously. In addition, the supervised information is introduced into the neighborhood preserving embedding (NPE) and s...
متن کاملConstraint Sparse Neighborhood Preserving Embedding
Neighborhood Preserving Embedding (NPE) and extensions of NPE are hot research topics of data mining at present. An algorithm called Constraint Sparse Neighborhood Preserving Embedding (CSNPE) for dimensionality reduction is proposed in the paper. The algorithm firstly creates the local sparse reconstructive relation information of samples; then, exacts the pairwise constrain information of sam...
متن کاملDiscriminative Supervised Neighborhood Preserving Embedding Feature Extraction for Hyperspectral-image Classification
A novel discriminative supervised neighborhood preserving embedding (DSNPE) method is proposed for feature extraction in classifying hyperspectral remote sensing imagery. DSNPE can preserve the local manifold structure and the neighborhood structure. What’s more, for each data point, DSNPE aims at pulling the neighboring points with the same class label towards it as near as possible, while sim...
متن کاملThe number of solutions of an equation related to a product of multilinear polynomials
We look at the number of solutions of an equation of the form f1f2...fk = a in a finite field, where each fi is a multilinear polynomial. We use two methods to construct a solution of this problem for the cases a = 0, a 6= 0, and we generally get a semi-explicit formula. We show that this formula can generate a more efficient algorithm than the traditional algorithm which consists to make a sys...
متن کامل