Low-Rank Embedding for Robust Image Feature Extraction

Low-Rank Representation with Empirical Kernel Space Embedding of Manifolds

Low-Rank Representation (LRR) methods integrate low-rank constraints and projection operators to model the mapping from the sample space to low-dimensional manifolds. Nonetheless, existing approaches typically apply Euclidean algorithms directly to manifold data in the original input space, leading to suboptimal classification accuracy. To mitigate this limitation, we introduce an unsupervised low-rank projection learning method named Low-Rank Representation with Empirical Kernel Space Embedding of Manifolds (LRR-EKM). LRR-EKM leverages an empirical kernel mapping to project samples into the Reproduced Kernel Hilbert Space (RKHS), enabling the linear separability of non-linearly structured samples and facilitating improved low-dimensional manifold representations through Euclidean distance metrics. By incorporating a row sparsity constraint on the projection matrix, LRR-EKM not only identifies discriminative features and removes redundancies but also enhances the interpretability of the learned subspace. Additionally, we introduce a manifold structure preserving constraint to retain the original representation and distance information of the samples during projection. Comprehensive experimental evaluations across various real-world datasets validate the superior performance of our proposed method compared to the state-of-the-art methods. The code is publicly available at https://github.com/ff-raw-war/LRR-EKM.

Enhanced Multimodal Low-Rank Embedding-Based Feature Selection Model for Multimodal Alzheimer's Disease Diagnosis

Identification of Alzheimer's disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the -norm, EMLE exploits an -norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The -norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the -norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix -norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer's Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.

Partial Tubal Nuclear Norm-Regularized Multiview Subspace Learning

In this article, a unified multiview subspace learning model, called partial tubal nuclear norm-regularized multiview subspace learning (PTN2MSL), was proposed for unsupervised multiview subspace clustering (MVSC), semisupervised MVSC, and multiview dimension reduction. Unlike most of the existing methods which treat the above three related tasks independently, PTN2MSL integrates the projection learning and the low-rank tensor representation to promote each other and mine their underlying correlations. Moreover, instead of minimizing the tensor nuclear norm which treats all singular values equally and neglects their differences, PTN2MSL develops the partial tubal nuclear norm (PTNN) as a better alternative solution by minimizing the partial sum of tubal singular values. The PTN2MSL method was applied to the above three multiview subspace learning tasks. It demonstrated that these tasks organically benefited from each other and PTN2MSL has achieved better performance in comparison to state-of-the-art methods.

Spatially aware self-representation learning for tissue structure characterization and spatial functional genes identification

Spatially resolved transcriptomics (SRT) enable the comprehensive characterization of transcriptomic profiles in the context of tissue microenvironments. Unveiling spatial transcriptional heterogeneity needs to effectively incorporate spatial information accounting for the substantial spatial correlation of expression measurements. Here, we develop a computational method, SpaSRL (spatially aware self-representation learning), which flexibly enhances and decodes spatial transcriptional signals to simultaneously achieve spatial domain detection and spatial functional genes identification. This novel tunable spatially aware strategy of SpaSRL not only balances spatial and transcriptional coherence for the two tasks, but also can transfer spatial correlation constraint between them based on a unified model. In addition, this joint analysis by SpaSRL deciphers accurate and fine-grained tissue structures and ensures the effective extraction of biologically informative genes underlying spatial architecture. We verified the superiority of SpaSRL on spatial domain detection, spatial functional genes identification and data denoising using multiple SRT datasets obtained by different platforms and tissue sections. Our results illustrate SpaSRL's utility in flexible integration of spatial information and novel discovery of biological insights from spatial transcriptomic datasets.

Robust Dimensionality Reduction via Low-rank Laplacian Graph Learning

Manifold learning is a widely used technique for dimensionality reduction as it can reveal the intrinsic geometric structure of data. However, its performance decreases drastically when data samples are contaminated by heavy noise or occlusions, which leads to unsatisfying data processing performance. We propose a novel robust dimensionality reduction method via low-rank Laplacian graph learning for classification and clustering tasks to solve the above problem. First, we construct a low-rank Laplacian graph by combining manifold learning and subspace learning. This graph can capture both global and local structural information of the data. And we introduce rank constraints for the Laplacian graph to make it more discriminative. Second, we put the learning of projection matrix and sample affinity graph into a unified framework. The projection matrix is embedded into a robust low-rank Laplacian graph so that the low-dimensional mapping of data can maintain the structural information in the graph well. Finally, we add a regularization term to the projection matrix to make it have the ability of both feature extraction and feature selection. Therefore, the proposed model can resist the interference of noise or data damage to learn the optimal projection to achieve better performance in dimensionality reduction through such a data dimensionality reduction joint framework. Comprehensive experiments on various benchmark datasets with varying degrees of occlusions or corruptions are carried out to evaluate the performance of the proposed method. Compared with the state-of-the-art dimensionality reduction methods in the literature, the experimental results are inspiring, showing our method’s effectiveness and robustness in classification and clustering, especially in object recognition scenarios with noise or occlusions.

An Unsupervised Feature Extraction Approach Based on Self-Expression

Feature extraction algorithms lack good interpretability during the projection learning. To solve this problem, an unsupervised feature extraction algorithm, that is, block diagonal projection (BDP), based on self-expression is proposed. Specifically, if the original data are projected into a low-dimensional subspace by a feature extraction algorithm, although the data may be more compact, the new features obtained may not be as explanatory as the original sample features. Therefore, by imposing L2,1 norm constraint on the projection matrix, the projection matrix can be of row sparsity. On one hand, discriminative features can be selected to make the projection matrix to be more interpretable. On the other hand, irrelevant or redundant features can be suppressed. The proposed model integrates feature extraction and selection into one framework. In addition, since self-expression can well excavate the correlation between samples or sample features, the unsupervised feature extraction task can be better guided using this property between them. At the same time, the block diagonal representation regular term is introduced to directly pursue the block diagonal representation. Thus, the accuracy of pattern recognition tasks such as clustering and classification can be improved. Finally, the effectiveness of BDP in linear dimensionality reduction and classification is proved on various reference datasets. The experimental results show that this algorithm is superior to previous feature extraction counterparts.

PolSAR Scene Classification via Low-Rank Constrained Multimodal Tensor Representation

Polarimetric synthetic aperture radar (PolSAR) data can be acquired at all times and are not impacted by weather conditions. They can efficiently capture geometrical and geographical structures on the ground. However, due to the complexity of the data and the difficulty of data availability, PolSAR image scene classification remains a challenging task. To this end, in this paper, a low-rank constrained multimodal tensor representation method (LR-MTR) is proposed to integrate PolSAR data in multimodal representations. To preserve the multimodal polarimetric information simultaneously, the target decompositions in a scene from multiple spaces (e.g., Freeman, H/A/α, Pauli, etc.) are exploited to provide multiple pseudo-color images. Furthermore, a representation tensor is constructed via the representation matrices and constrained by the low-rank norm to keep the cross-information from multiple spaces. A projection matrix is also calculated by minimizing the differences between the whole cascaded data set and the features in the corresponding space. It also reduces the redundancy of those multiple spaces and solves the out-of-sample problem in the large-scale data set. To support the experiments, two new PolSAR image data sets are built via ALOS-2 full polarization data, covering the areas of Shanghai, China, and Tokyo, Japan. Compared with state-of-the-art (SOTA) dimension reduction algorithms, the proposed method achieves the best quantitative performance and demonstrates superiority in fusing multimodal PolSAR features for image scene classification.

Autoencoder-Based Latent Block-Diagonal Representation for Subspace Clustering

Block-diagonal representation (BDR) is an effective subspace clustering method. The existing BDR methods usually obtain a self-expression coefficient matrix from the original features by a shallow linear model. However, the underlying structure of real-world data is often nonlinear, thus those methods cannot faithfully reflect the intrinsic relationship among samples. To address this problem, we propose a novel latent BDR (LBDR) model to perform the subspace clustering on a nonlinear structure, which jointly learns an autoencoder and a BDR matrix. The autoencoder, which consists of a nonlinear encoder and a linear decoder, plays an important role to learn features from the nonlinear samples. Meanwhile, the learned features are used as a new dictionary for a linear model with block-diagonal regularization, which can ensure good performances for spectral clustering. Moreover, we theoretically prove that the learned features are located in the linear space, thus ensuring the effectiveness of the linear model using self-expression. Extensive experiments on various real-world datasets verify the superiority of our LBDR over the state-of-the-art subspace clustering approaches.

Multiview Consensus Structure Discovery

Multiview subspace learning has attracted much attention due to the efficacy of exploring the information on multiview features. Most existing methods perform data reconstruction on the original feature space and thus are vulnerable to noisy data. In this article, we propose a novel multiview subspace learning method, called multiview consensus structure discovery (MvCSD). Specifically, we learn the low-dimensional subspaces corresponding to different views and simultaneously pursue the structure consensus over subspace clustering for multiple views. In such a way, latent subspaces from different views regularize each other toward a common consensus that reveals the underlying cluster structure. Compared to existing methods, MvCSD leverages the consensus structure derived from the subspaces of diverse views to better exploit the intrinsic complementary information that well reflects the essence of data. Accordingly, the proposed MvCSD is capable of producing a more robust and accurate representation structure which is crucial for multiview subspace learning. The proposed method can be optimized effectively, with theoretical convergence guarantee, by alternatively iterating the argument Lagrangian multiplier algorithm and the eigendecomposition. Extensive experiments on diverse datasets demonstrate the advantages of our method over the state-of-the-art methods.

Research on Real-Time Face Key Point Detection Algorithm Based on Attention Mechanism

The existing face detection methods were affected by the network model structure used. Most of the face recognition methods had low recognition rate of face key point features due to many parameters and large amount of calculation. In order to improve the recognition accuracy and detection speed of face key points, a real-time face key point detection algorithm based on attention mechanism was proposed in this paper. Due to the multiscale characteristics of face key point features, the deep convolution network model was adopted, the attention module was added to the VGG network structure, the feature enhancement module and feature fusion module were combined to improve the shallow feature representation ability of VGG, and the cascade attention mechanism was used to improve the deep feature representation ability. Experiments showed that the proposed algorithm not only can effectively realize face key point recognition but also has better recognition accuracy and detection speed than other similar methods. This method can provide some theoretical basis and technical support for face detection in complex environment.

Research on Face Image Digital Processing and Recognition Based on Data Dimensionality Reduction Algorithm

Because face recognition is greatly affected by external environmental factors and the partial lack of face information challenges the robustness of face recognition algorithm, while the existing methods have poor robustness and low accuracy in face image recognition, this paper proposes a face image digital processing and recognition based on data dimensionality reduction algorithm. Based on the analysis of the existing data dimensionality reduction and face recognition methods, according to the face image input, feature composition, and external environmental factors, the face recognition and processing technology flow is given, and the face feature extraction method is proposed based on nonparametric subspace analysis (NSA). Finally, different methods are used to carry out comparative experiments in different face databases. The results show that the method proposed in this paper has a higher correct recognition rate than the existing methods and has an obvious effect on the XM2VTS face database. This method not only improves the shortcomings of existing methods in dealing with complex face images but also provides a certain reference for face image feature extraction and recognition in complex environment.

Gaussian noise level estimation for color image denoising

Noise level is an important parameter in many visual applications, especially in image denoising. How to accurately estimate the noise level from a noisy image is a challenging problem. However, for color image denoising, it is not that the more accurate the noise level is, the better the denoising performance is, but that the noise level higher than the true noise can achieve a better denoising result. For better denoising, we propose a statistical iterative method based on low-rank image patches. We select the low-rank patches in the image and calculate the eigenvalues of the covariance matrix of these patches. Unlike the existing methods that take the smallest eigenvalue as the estimated noise level, the proposed method analyzes the relationship between the median value and the mean value of the eigenvalue according to the statistical property and selects an appropriate number of eigenvalues to average as the estimated noise level. Extensive experiments are conducted, demonstrating that our estimated noise level reaches the highest value of all comparison methods. And the denoising results on color images of our method outperform all the state-of-the-art methods and the true noise level.

scDA: Single cell discriminant analysis for single-cell RNA sequencing data

•

Cell-to-Cell representation graph could be constructed.

•

Cell groups and Discriminant metagenes could be identified simultaneously.

•

scDA less sensitive to drop-out events and capable to label a mass of cells after learning even from a small set of data.

•

scDA can avoid unnecessary re-clustering, and is actually a combinational approach simultaneously performing both clustering and classification.

Single-cell RNA-sequencing (scRNA-seq) techniques provide unprecedented opportunities to investigate phenotypic and molecular heterogeneity in complex biological systems. However, profiling massive amounts of cells brings great computational challenges to accurately and efficiently characterize diverse cell populations. Single cell discriminant analysis (scDA) solves this problem by simultaneously identifying cell groups and discriminant metagenes based on the construction of cell-by-cell representation graph, and then using them to annotate unlabeled cells in data. We demonstrate scDA is effective to determine cell types, revealing the overall variabilities between cells from eleven data sets. scDA also outperforms several state-of-the-art methods when inferring the labels of new samples. In particular, we found scDA less sensitive to drop-out events and capable to label a mass of cells within or across datasets after learning even from a small set of data. The scDA approach offers a new way to efficiently analyze scRNA-seq profiles of large size or from different batches. scDA was implemented and freely available at https://github.com/ZCCQQWork/scDA.

Discriminative Label Relaxed Regression with Adaptive Graph Learning

The traditional label relaxation regression (LRR) algorithm directly fits the original data without considering the local structure information of the data. While the label relaxation regression algorithm of graph regularization takes into account the local geometric information, the performance of the algorithm depends largely on the construction of graph. However, the traditional graph structures have two defects. First of all, it is largely influenced by the parameter values. Second, it relies on the original data when constructing the weight matrix, which usually contains a lot of noise. This makes the constructed graph to be often not optimal, which affects the subsequent work. Therefore, a discriminative label relaxation regression algorithm based on adaptive graph (DLRR_AG) is proposed for feature extraction. DLRR_AG combines manifold learning with label relaxation regression by constructing adaptive weight graph, which can well overcome the problem of label overfitting. Based on a large number of experiments, it can be proved that the proposed method is effective and feasible.

Low-Rank Preserving t-Linear Projection for Robust Image Feature Extraction

As the cornerstone for joint dimension reduction and feature extraction, extensive linear projection algorithms were proposed to fit various requirements. When being applied to image data, however, existing methods suffer from representation deficiency since the multi-way structure of the data is (partially) neglected. To solve this problem, we propose a novel Low-Rank Preserving t-Linear Projection (LRP-tP) model that preserves the intrinsic structure of the image data using t-product-based operations. The proposed model advances in four aspects: 1) LRP-tP learns the t-linear projection directly from the tensorial dataset so as to exploit the correlation among the multi-way data structure simultaneously; 2) to cope with the widely spread data errors, e.g., noise and corruptions, the robustness of LRP-tP is enhanced via self-representation learning; 3) LRP-tP is endowed with good discriminative ability by integrating the empirical classification error into the learning procedure; 4) an adaptive graph considering the similarity and locality of the data is jointly learned to precisely portray the data affinity. We devise an efficient algorithm to solve the proposed LRP-tP model using the alternating direction method of multipliers. Extensive experiments on image feature extraction have demonstrated the superiority of LRP-tP compared to the state-of-the-arts.

Robust Flexible Preserving Embedding

Neighborhood preserving embedding (NPE) has been proposed to encode overall geometry manifold embedding information. However, the class-special structure of the data is destroyed by noise or outliers existing in the data. To address this problem, in this article, we propose a novel embedding approach called robust flexible preserving embedding (RFPE). First, RFPE recovers the noisy data by low-rank learning and obtains clean data. Then, the clean data are used to learn the projection matrix. In this way, the projective learning is totally unaffected by noise or outliers. By encoding a flexible regularization term, RFPE can keep the property of the data points with a nonlinear manifold and be more flexible. RFPE searches the optimal projective subspace for feature extraction. In addition, we also extend the proposed RFPE to a kernel case and propose kernel RFPE (KRFPE). Extensive experiments on six public image databases show the superiority of the proposed methods over other state-of-the-art methods.

Dual Shared-Specific Multiview Subspace Clustering

Multiview subspace clustering has received significant attention as the availability of diverse of multidomain and multiview real-world data has rapidly increased in the recent years. Boosting the performance of multiview clustering algorithms is challenged by two major factors. First, since original features from multiview data are highly redundant, reconstruction based on these attributes inevitably results in inferior performance. Second, since each view of such multiview data may contain unique knowledge as against the others, it remains a challenge to exploit complimentary information across multiple views while simultaneously investigating the uniqueness of each view. In this paper, we present a novel dual shared-specific multiview subspace clustering (DSS-MSC) approach that simultaneously learns the correlations between shared information across multiple views and also utilizes view-specific information to depict specific property for each independent view. Further, we formulate a dual learning framework to capture shared-specific information into the dimensional reduction and self-representation processes, which strengthens the ability of our approach to exploit shared information while preserving view-specific property effectively. The experimental results on several benchmark datasets have demonstrated the effectiveness of the proposed approach against other state-of-the-art techniques.

Low-rank discriminative regression learning for image classification

As a famous multivariable analysis technique, regression methods, such as ridge regression, are widely used for image representation and dimensionality reduction. However, the metric of ridge regression and its variants is always the Frobenius norm (F-norm), which is sensitive to outliers and noise in data. At the same time, the performance of the ridge regression and its extensions is limited by the class number of the data. To address these problems, we propose a novel regression learning method which named low-rank discriminative regression learning (LDRL) for image representation. LDRL assumes that the input data is corrupted and thus the L₁ norm can be used as a sparse constraint on the noised matrix to recover the clean data for regression, which can improve the robustness of the algorithm. Due to learn a novel project matrix that is not limited by the number of classes, LDRL is suitable for classifying the data set no matter whether there is a small or large number of classes. The performance of the proposed LDRL is evaluated on six public image databases. The experimental results prove that LDRL obtains better performance than existing regression methods.

Nonpeaked Discriminant Analysis for Data Representation

Of late, there are many studies on the robust discriminant analysis, which adopt L₁-norm as the distance metric, but their results are not robust enough to gain universal acceptance. To overcome this problem, the authors of this article present a nonpeaked discriminant analysis (NPDA) technique, in which cutting L₁-norm is adopted as the distance metric. As this kind of norm can better eliminate heavy outliers in learning models, the proposed algorithm is expected to be stronger in performing feature extraction tasks for data representation than the existing robust discriminant analysis techniques, which are based on the L₁-norm distance metric. The authors also present a comprehensive analysis to show that cutting L₁-norm distance can be computed equally well, using the difference between two special convex functions. Against this background, an efficient iterative algorithm is designed for the optimization of the proposed objective. Theoretical proofs on the convergence of the algorithm are also presented. Theoretical insights and effectiveness of the proposed method are validated by experimental tests on several real data sets.

Learning Latent Low-Rank and Sparse Embedding for Robust Image Feature Extraction

To defy the curse of dimensionality, the inputs are always projected from the original high-dimensional space into the target low-dimension space for feature extraction. However, due to the existence of noise and outliers, the feature extraction task for corrupted data is still a challenging problem. Recently, a robust method called low rank embedding (LRE) was proposed. Despite the success of LRE in experimental studies, it also has many disadvantages: 1) The learned projection cannot quantitatively interpret the importance of features. 2) LRE does not perform data reconstruction so that the features may not be capable of holding the main energy of the original "clean" data. 3) LRE explicitly transforms error into the target space. 4) LRE is an unsupervised method, which is only suitable for unsupervised scenarios. To address these problems, in this paper, we propose a novel method to exploit the latent discriminative features. In particular, we first utilize an orthogonal matrix to hold the main energy of the original data. Next, we introduce an l_2,1 -norm term to encourage the features to be more compact, discriminative and interpretable. Then, we enforce a columnwise l_2,1 -norm constraint on an error component to resist noise. Finally, we integrate a classification loss term into the objective function to fit supervised scenarios. Our method performs better than several state-of-the-art methods in terms of effectiveness and robustness, as demonstrated on six publicly available datasets.

Constrained Discriminative Projection Learning for Image Classification

Projection learning is widely used in extracting discriminative features for classification. Although numerous methods have already been proposed for this goal, they barely explore the label information during projection learning and fail to obtain satisfactory performance. Besides, many existing methods can learn only a limited number of projections for feature extraction which may degrade the performance in recognition. To address these problems, we propose a novel constrained discriminative projection learning (CDPL) method for image classification. Specifically, CDPL can be formulated as a joint optimization problem over subspace learning and classification. The proposed method incorporates the low-rank constraint to learn a robust subspace which can be used as a bridge to seamlessly connect the original visual features and objective outputs. A regression function is adopted to explicitly exploit the class label information so as to enhance the discriminability of subspace. Unlike existing methods, we use two matrices to perform feature learning and regression, respectively, such that the proposed approach can obtain more projections and achieve superior performance in classification tasks. The experiments on several datasets show clearly the advantages of our method against other state-of-the-art methods.

Robust auto-weighted projective low-rank and sparse recovery for visual representation

Most existing low-rank and sparse representation models cannot preserve the local manifold structures of samples adaptively, or separate the locality preservation from the coding process, which may result in the decreased performance. In this paper, we propose an inductive Robust Auto-weighted Low-Rank and Sparse Representation (RALSR) framework by joint feature embedding for the salient feature extraction of high-dimensional data. Technically, the model of our RALSR seamlessly integrates the joint low-rank and sparse recovery with robust salient feature extraction. Specifically, RALSR integrates the adaptive locality preserving weighting, joint low-rank/sparse representation and the robustness-promoting representation into a unified model. For accurate similarity measure, RALSR computes the adaptive weights by minimizing the joint reconstruction errors over the recovered clean data and salient features simultaneously, where L1-norm is also applied to ensure the sparse properties of learnt weights. The joint minimization can also potentially enable the weight matrix to have the power to remove noise and unfavorable features by reconstruction adaptively. The underlying projection is encoded by a joint low-rank and sparse regularization, which can ensure it to be powerful for salient feature extraction. Thus, the calculated low-rank sparse features of high-dimensional data would be more accurate for the subsequent classification. Visual and numerical comparison results demonstrate the effectiveness of our RALSR for data representation and classification.

Low-Rank Preserving Projection Via Graph Regularized Reconstruction

Preserving global and local structures during projection learning is very important for feature extraction. Although various methods have been proposed for this goal, they commonly introduce an extra graph regularization term and the corresponding regularization parameter that needs to be tuned. However, tuning the parameter manually not only is time-consuming, but also is difficult to find the optimal value to obtain a satisfactory performance. This greatly limits their applications. Besides, projections learned by many methods do not have good interpretability and their performances are commonly sensitive to the value of the selected feature dimension. To solve the above problems, a novel method named low-rank preserving projection via graph regularized reconstruction (LRPP_GRR) is proposed. In particular, LRPP_GRR imposes the graph constraint on the reconstruction error of data instead of introducing the extra regularization term to capture the local structure of data, which can greatly reduce the complexity of the model. Meanwhile, a low-rank reconstruction term is exploited to preserve the global structure of data. To improve the interpretability of the learned projection, a sparse term with l_2,1 norm is imposed on the projection. Furthermore, we introduce an orthogonal reconstruction constraint to make the learned projection hold main energy of data, which enables LRPP_GRR to be more flexible in the selection of feature dimension. Extensive experimental results show the proposed method can obtain competitive performance with other state-of-the-art methods.

A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification

Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples.

Brain-Wide Genome-Wide Association Study for Alzheimer's Disease via Joint Projection Learning and Sparse Regression Model

Brain-wide and genome-wide association (BW-GWA) study is presented in this paper to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants [i.e., single nucleotide polymorphism (SNP)] in Alzheimer's disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes into an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes into a diagnostic-label-guided joint feature space, where the intraclass projected points are constrained to be close to each other. In addition, we use l2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers and also to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using AD neuroimaging initiative dataset, and the results show that our proposed method outperforms several state-of-the-art methods in term of the average root-mean-square error of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions identified in this study have also been shown in the previous AD-related studies, thus verifying the effectiveness and potential of our proposed method in AD pathogenesis study.

Low-Rank Sparse Preserving Projections for Dimensionality Reduction

Learning an efficient projection to map high-dimensional data into a lower dimensional space is a rather challenging task in the community of pattern recognition and computer vision. Manifold learning is widely applied because it can disclose the intrinsic geometric structure of data. However, it only concerns the geometric structure and may lose its effectiveness in case of corrupted data. To address this challenge, we propose a novel dimensionality reduction method by combining the manifold learning and low-rank sparse representation, termed low-rank sparse preserving projections (LSPP), which can simultaneously preserve the intrinsic geometric structure and learn a robust representation to reduce the negative effects of corruptions. Therefore, LSPP is advantageous to extract robust features. Because the formulated LSPP problem has no closed-form solution, we use the linearized alternating direction method with adaptive penalty and eigen-decomposition to obtain the optimal projection. The convergence of LSPP is proven, and we also analyze its complexity. To validate the effectiveness and robustness of LSPP in feature extraction and dimensionality reduction, we make a critical comparison between LSPP and a series of related dimensionality reduction methods. The experimental results demonstrate the effectiveness of LSPP.

Jointly Sparse Hashing for Image Retrieval

Recently, hash learning attracts great attentions since it can obtain fast image retrieval on large-scale datasets by using a series of discriminative binary codes. The popular methods include manifold-based hashing methods, which aim to learn the binary codes by embedding the original high-dimensional data into low-dimensional intrinsic subspace. However, most of these methods tend to relax the discrete constraint to compute the final binary codes in an easier way. Therefore, the information loss will increase. In this paper, we propose a novel jointly sparse regression model to minimize the locality information loss and obtain jointly sparse hashing method. The proposed model integrates locality, joint sparsity and rotation operation together with a seamless formulation. Thus, the drawback in previous methods using two separated and independent stages such as PCA-ITQ and the similar methods can be addressed. Moreover, since we introduce the joint sparsity, the feature extraction and jointly sparse feature selection can also be realized in a single projection operation, which has the potentials to select more discriminant features. The convergence of the proposed algorithm is proved, and the essences of the iterative procedures are also revealed. The experimental results on large-scale datasets demonstrate the performance of the proposed method.

An Effective Palmprint Recognition Approach for Visible and Multispectral Sensor Images

Among several palmprint feature extraction methods the HOG-based method is attractive and performs well against changes in illumination and shadowing of palmprint images. However, it still lacks the robustness to extract the palmprint features at different rotation angles. To solve this problem, this paper presents a hybrid feature extraction method, named HOG-SGF that combines the histogram of oriented gradients (HOG) with a steerable Gaussian filter (SGF) to develop an effective palmprint recognition approach. The approach starts by processing all palmprint images by David Zhang’s method to segment only the region of interests. Next, we extracted palmprint features based on the hybrid HOG-SGF feature extraction method. Then, an optimized auto-encoder (AE) was utilized to reduce the dimensionality of the extracted features. Finally, a fast and robust regularized extreme learning machine (RELM) was applied for the classification task. In the evaluation phase of the proposed approach, a number of experiments were conducted on three publicly available palmprint databases, namely MS-PolyU of multispectral palmprint images and CASIA and Tongji of contactless palmprint images. Experimentally, the results reveal that the proposed approach outperforms the existing state-of-the-art approaches even when a small number of training samples are used.