Joint Sparse Representation Model Research Articles

SAR Target Recognition Method based on Adaptive Weighted Decision Fusion of Deep Features

Background: This paper proposes a synthetic aperture radar (SAR) target recognition method based on adaptive weighted decision fusion of multi-level deep features. Methods: The trained ResNet-18 is employed to extract multi-level deep features from SAR images. Afterwards, based on the joint sparse representation (JSR) model, the multi-level deep features are represented to obtain the corresponding reconstruction error vectors. Considering the differences in the abilities of different levels of features to distinguish the target, the reconstruction error vectors are analyzed based on entropy theory, and their corresponding weights are adaptively obtained. Finally, the fused reconstruction error result is obtained through adaptively weighted fusion, and the target label is determined accordingly. Results: Experiments are conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under different conditions, and the proposed method is compared with published methods, including multi-feature decision fusion, JSR-based decision fusion and other types of ResNets. Conclusion: The experimental results under standard operating condition (SOC) and extended operating conditions (EOCs) including depression angle variance and noise corruption validate the advantages of the proposed method.

A joint sparse representation and low rank prior regularization model for image deblocking

When the compression quality factor (QF) is low, JPEG images are usually accompanied by very severe block artifacts. The conventional image deblocking models based on low-rank regularization focus on eliminating block artifacts, but lack the capacity of recovering texture details on image edges. In this paper, an image deblocking model which combines sparse representation and low-rank regularization based on fractional norm is proposed. To avoid the abrupt increase in computational complexity, multiple orthogonal dictionary learning is proposed to enhance the ability to sparsify diverse image structures and eliminate correlations among the atoms in the overcomplete dictionary. To further improve the image deblocking effect, a quantization constraint and fractional norm are used to more effectively enforce the low-rank property. Finally, an alternating minimization strategy is applied to solve the derived optimization problem. The model proposed in this paper preserves more texture details while effectively removing image block artifacts compared with the mainstream image deblocking model utilizing low-rank regularization alone. Experimental results show that the proposed method outperforms the current state-of-the-art image deblocking models in terms of both subjective metrics and objective perception.

SAR Image Target Recognition Method by Global and Local Dictionary Sparse Representation

ABSTRACT Target variant detection has been challenging for Synthetic Aperture Radar (SAR), and the performance of the target variant recognition needs to be further enhanced. SAR images are widely used in the field of target recognition and are important to support reconnaissance operations. This paper proposes a novel research approach to improve the efficiency of target recognition. First, the theory surrounding sparse representation and dictionary learning is presented. Secondly, a SAR image target recognition model is constructed according to the theory. Meanwhile, a dynamic joint sparse representation model is proposed based on multi-information and applied to SAR image target recognition when sparse representation is under consideration. Finally, experiments are set up to validate the proposed model. The results are presented as follows: 1. the recognition rate range of the sample SAR image target is 0.811–0.995 and 0.867–0.990, respectively, when the two cases, without registration processing and with registration processing, utilize the recognition method of dictionary learning and sparse representation. 2. with the increase in dictionary size, the average recognition rate of SAR images based on multi-information dynamic joint sparse representation also increases under the conditions of no logarithm transformation and median filtering and after logarithm transformation and median filtering are run. Then, the average recognition rate range is 0.63–0.9 and 0.65–0.96, respectively. Thus, the recognition rate is improved by 5%-10%. 3. the recognition approach based on the sparse representation of multi-information dynamic joint has distinct sparse degrees of SAR image recognition in the case of logarithmic transformation and median filtering when the sample image has been registered and not been registered. The relative average recognition rates were 0.950–0.970 and 0.955–0.977, respectively. The key contribution of the research is to offer a workable solution to the issues plaguing SAR target variant recognition and to improve the significant limitations in the state-of-the-art literature thoroughly.

Composite Kernel of Mutual Learning on Mid-Level Features for Hyperspectral Image Classification.

By training different models and averaging their predictions, the performance of the machine-learning algorithm can be improved. The performance optimization of multiple models is supposed to generalize further data well. This requires the knowledge transfer of generalization information between models. In this article, a multiple kernel mutual learning method based on transfer learning of combined mid-level features is proposed for hyperspectral classification. Three-layer homogenous superpixels are computed on the image formed by PCA, which is used for computing mid-level features. The three mid-level features include: 1) the sparse reconstructed feature; 2) combined mean feature; and 3) uniqueness. The sparse reconstruction feature is obtained by a joint sparse representation model under the constraint of three-scale superpixels' boundaries and regions. The combined mean features are computed with average values of spectra in multilayer superpixels, and the uniqueness is obtained by the superposed manifold ranking values of multilayer superpixels. Next, three kernels of samples in different feature spaces are computed for mutual learning by minimizing the divergence. Then, a combined kernel is constructed to optimize the sample distance measurement and applied by employing SVM training to build classifiers. Experiments are performed on real hyperspectral datasets, and the corresponding results demonstrated that the proposed method can perform significantly better than several state-of-the-art competitive algorithms based on MKL and deep learning.

A Face Recognition Method Based on Multifeature Fusion

Face recognition is widely used in daily life and has an important supporting role for social management. Face recognition is mainly based on historical accumulation data to confirm people’s identities in unknown samples and obtain valuable intelligence information. For the problem of face recognition, this paper proposes a multifeature joint adaptive weighting algorithm framework. In this method, a number of different types of features are first used to describe the face characteristics. The selected features should be as complementary as possible, and the overlap redundant information should be reduced to the greatest extent, so as to ensure the performance and efficiency of multifeature fusion. In the classification stage, based on the joint sparse representation model, the multiple types of features are characterized, and their reconstruction error vectors for the corresponding features of the test sample are calculated. The joint sparse representation model can examine the correlation between different types of features, thereby improving the accuracy of representation and fully integrating the advantages of multiple types of features. At the same time, in view of the simple superposition of reconstruction errors in the traditional sparse representation model, this paper uses a random weight matrix to comprehensively consider the weighted reconstruction errors under different weight conditions, so as to obtain statistical decision quantities for the final decision. The framework proposed in this paper can adapt to different multifeature combinations and has good practicability. In the experiment, training and test sets are constructed based on public face image data sets to test the proposed method. The experimental results show that the method in this paper is more effective and robust compared with some present methods for face recognition.

Local Matrix Feature-Based Kernel Joint Sparse Representation for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is one of the hot research topics in the field of remote sensing. The performance of HSI classification greatly depends on the effectiveness of feature learning or feature design. Traditional vector-based spectral–spatial features have shown good performance in HSI classification. However, when the number of labeled samples is limited, the performance of these vector-based features is degraded. To fully mine the discriminative features in small-sample case, a novel local matrix feature (LMF) was designed to reflect both the correlation between spectral pixels and the spectral bands in a local spatial neighborhood. In particular, the LMF is a linear combination of a local covariance matrix feature and a local correntropy matrix feature, where the former describes the correlation between spectral pixels and the latter measures the similarity between spectral bands. Based on the constructed LMFs, a simple Log-Euclidean distance-based linear kernel is introduced to measure the similarity between them, and an LMF-based kernel joint sparse representation (LMFKJSR) model is proposed for HSI classification. Due to the superior performance of region covariance and correntropy descriptors, the proposed LMFKJSR shows better results than existing vector-feature-based and matrix-feature-based support vector machine (SVM) and JSR methods on three well-known HSI data sets in the case of limited labeled samples.

A Hybrid Sparse Representation Model for Image Restoration.

Group-based sparse representation (GSR) uses image nonlocal self-similarity (NSS) prior to grouping similar image patches, and then performs sparse representation. However, the traditional GSR model restores the image by training degraded images, which leads to the inevitable over-fitting of the data in the training model, resulting in poor image restoration results. In this paper, we propose a new hybrid sparse representation model (HSR) for image restoration. The proposed HSR model is improved in two aspects. On the one hand, the proposed HSR model exploits the NSS priors of both degraded images and external image datasets, making the model complementary in feature space and the plane. On the other hand, we introduce a joint sparse representation model to make better use of local sparsity and NSS characteristics of the images. This joint model integrates the patch-based sparse representation (PSR) model and GSR model, while retaining the advantages of the GSR model and the PSR model, so that the sparse representation model is unified. Extensive experimental results show that the proposed hybrid model outperforms several existing image recovery algorithms in both objective and subjective evaluations.

Combination of Joint Representation and Adaptive Weighting for Multiple Features with Application to SAR Target Recognition

For the synthetic aperture radar (SAR) target recognition problem, a method combining multifeature joint classification and adaptive weighting is proposed with innovations in fusion strategies. Zernike moments, nonnegative matrix factorization (NMF), and monogenic signal are employed as the feature extraction algorithms to describe the characteristics of original SAR images with three corresponding feature vectors. Based on the joint sparse representation model, the three types of features are jointly represented. For the reconstruction error vectors from different features, an adaptive weighting algorithm is used for decision fusion. That is, the weights are adaptively obtained under the framework of linear fusion to achieve a good fusion result. Finally, the target label is determined according to the fused error vector. Experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset under the standard operating condition (SOC) and four extended operating conditions (EOC), i.e., configuration variants, depression angle variances, noise interference, and partial occlusion. The results verify the effectiveness and robustness of the proposed method.

Robust Background Feature Extraction Through Homogeneous Region-Based Joint Sparse Representation for Hyperspectral Anomaly Detection

Various existing anomaly detection (AD) technologies focus on the background feature extraction and suppression, which serves as a crucial step to extrude anomalies from the hyperspectral imagery (HSI). In this article, motivated by the advantages of the joint sparse representation (JSR) model for adaptive background base selection, a robust background feature extraction method through homogeneous region-based JSR is proposed and used for AD. By segmenting the scene from the spatial domain through an eight-connected region division operation based on the clustering result, a series of nonoverlapping homogeneous regions each sharing a common sparsity pattern are obtained. After discarding small regions, JSR is performed on each region with the dictionary constituted by the overall spectral items in the corresponding cluster. By calculating the usage frequency of dictionary atoms, the most representative background bases describing each background cluster are adaptively selected and then combined into the global background bases. In addition, considering the interference of noise on detection accuracy, an energy deviation-based noise estimation strategy is presented by analyzing the residual obtained from JSR. Finally, the anomaly response of each pixel is measured by comparing its projection energy obtained from the background orthogonal subspace projection with the noise energy in its corresponding region. The proposed method overcomes the shortcomings of traditional neighborhood-based JSR in the common sparsity pattern and anomaly proportion. The spatial characteristics of HSI are fully explored. Furthermore, the interference of noise on detection accuracy is eliminated. Experiments on four HSI data sets demonstrate the superiority of the proposed method.

Block sparse representation approach to 2D DOA and polarisation estimation of wideband signals using a sparse vector antenna array

In this study, a multi-polarised two-dimensional (2D) planar array of sparsely located vector antennas (VAs) is designed for the block sparse representation (SR)-based 2D direction finding and polarisation parameter estimation of wideband signals. In order to alleviate the inter-VA mutual coupling effect, the minimum inter-VA spacing of the 2D sparse array is constrained to be no less than one wavelength that corresponds to the highest signal frequency. To reduce the computational complexity of parameter estimation, the 2D block SR model for the 2D difference coarray output at a certain frequency bin is established, under which the two direction cosine terms for 2D direction-of-arrival (DOA) estimation are decoupled with the polarimetric terms. This enables separated but simultaneous 2D direction finding and polarisation parameter estimation with the newly developed joint 2D block orthogonal matching pursuit (Joint-2D-BOMP) subband fused sparse recovery algorithm. Moreover, with the use of two spatial only (polarisation independent) over-complete dictionaries, the representation dimension of the new 2D block SR model is greatly reduced as compared with the traditional space-polarisation joint SR model. The efficacy of the presented VA array geometry and the associated parameter estimation method is validated by computer simulations.

Direct data domain space-time adaptive processing method based on joint sparse representation with single snapshot for MIMO radar

To improve the performance of exiting sparse recovery-based space-time adaptive processing (STAP) methods in nonstationary and heterogeneous environments, a STAP method, called the joint sparse representation (JSR)-based direct data domain STAP method using MIMO subarraying radar, is proposed. First, by exploiting the property of waveforms orthogonal diversity of MIMO subarraying radar, the received single snapshot signal of the range cell under test is expressed as multiple snapshot signals. Second, the JSR model of clutter plus target spatiotemporal spectrum estimation is established and the joint sparsity is proved. The spatiotemporal spectrum of clutter and target is then estimated by the typical JSR algorithm. At last, the clutter covariance clutter matrix and the corresponding weight vector of the STAP processor are calculated based on the clutter space-time distribution extracted by the rough priori knowledge of the target. By utilizing the data of the range cell under test only, the proposed method could achieve accurate spatiotemporal spectrum estimation and great performance of clutter suppression. Experimental simulations demonstrate the validity of the proposed method.

Selection of Multi-Level Deep Features via Spearman Rank Correlation for Synthetic Aperture Radar Target Recognition Using Decision Fusion

Convolutional neural networks (CNN) now become one of the most popular methods in synthetic aperture radar (SAR) target recognition. To fully exploit the deep features learned by CNN, this paper considers all the feature maps from different convolution layers. At each layer, the Spearman rank correlation is employed to evaluate the similarities between the feature maps and original SAR image. A certain proportion of feature maps with high similarities are selected and jointly represented based on the joint sparse representation (JSR) model. For the reconstruction error vectors from different layers, they are combined based on linear weighting using a random weight matrix. The fused reconstruction errors are analyzed to form a decision value for target recognition. The feature selection chooses the robust features and JSR considers the inner correlations between the feature maps from the same layer. In addition, the linear weighting using the random weight matrix could statistically reveal the correlations between the test sample and a certain training class. Therefore, the overall effectiveness and robustness of the proposed method can be enhanced. By performing experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset, the proposed method could achieve a very high average recognition rate of 99.32% for ten classes of ground targets under the standard operating condition (SOC). Furthermore, under the extended operating conditions (EOCs) like configuration differences, depression angle differences, noise corruption, and partial occlusion, the proposed could also achieve superior robustness over some state-of-the-art SAR target recognition methods.

A Novel Multi-Feature Joint Learning Method for Fast Polarimetric SAR Terrain Classification

Polarimetric synthetic aperture radar (PolSAR) image classification is one of the most important study areas for PolSAR image processing. Many kinds of PolSAR features can be extracted for PolSAR image classification, such as the scattering, polarimetric or image features. However, it is difficult to improve the classification accuracy of PolSAR images by using all these low-level features directly, since they may conflict with each other for classification. Hence, how to joint learn these low-level features to obtain high-level discriminating features is a challenging task. To solve this problem, a novel fast multi-feature joint learning method(fMF-JLC) is proposed for PolSAR image classification. The proposed method extract three kinds of low-level features of PolSAR data at first. Then, a multi-feature joint sparse representation model(MF-JSR) is proposed by designing joint sparse constraints on the extracted features above. Moreover, the joint sparse features are further compressed to overcome the dimension curse and acquire semantic features by the topic model. By this way, the low-level features are fused and discriminating high-level features are acquired. However, the pixel-wise feature learning method is time consuming. To speed the proposed method, a superpixel-based fast learning method is designed by involving the contextual relationship. Experiments are taken on three sets of real PolSAR data with different sensors and bands, and several compared methods are used to verify the effectiveness of the proposed method. The experimental results illustrate that the proposed method can obtain better performance than the state-of-art methods, especially for the heterogenous areas.

Log-Euclidean Kernel-Based Joint Sparse Representation for Hyperspectral Image Classification

Motivated by the superior performance of region covariance descriptor, we use covariance matrices as new features to replace the original spectral pixel features, and employ a Log-Euclidean metric to characterize the geodesic distance between symmetric positive definite (SPD) covariance matrices. Based on the covariance features and Log-Euclidean metric, we propose a Log-Euclidean kernel-based joint sparse representation (LogEKJSR) model for the classification of hyperspectral images (HSIs). In the implementation of LogEKJSR, we first reduce the dimensionality of HSI by employing extended multiattribute profile (EMAP) transformations, and then extract the region covariance matrix features associated with each pixel on the EMAPs. The EMAP can model homogeneity and texture structure of HSI by aggregating multiple morphological attribute profiles, the covariance matrix feature contains both local spectral correlation and spatial structure information, and the Log-Euclidean kernel is a matrix-to-matrix similarity metric rather than vector-to-vector similarity metric. Finally, a LogEKJSR model is obtained by replacing the traditional kernel in the KJSR with the Log-Euclidean kernel. Experimental results on three benchmark hyperspectral data sets demonstrate that our proposed LogEKJSR is more effective than existing JSR, KJSR, and support vector machine methods.

Joint Sparse Learning With Nonlocal and Local Image Priors for Image Error Concealment

Joint sparse representation (JSR) model has recently emerged as a powerful technique with wide variety of applications. In this paper, the JSR model is extended to error concealment (EC) application, being effective to recover the original image from its corrupted version. This model is based on jointly learning a dictionary pair and two mapping matrices that are trained offline from external training images. Given the trained dictionaries and mappings, the restoration is done by transferring the recovery problem into the sparse representation domain with respect to the trained dictionaries, which is further transformed into a common space using the respective mapping matrices. Then, the reconstructed image is obtained by back projection into the spatial domain. In order to improve the accuracy and stability of the proposed JSR-based EC algorithm and avoid unexpected artifacts, the local and non-local priors are seamlessly integrated into the JSR model. The non-local prior is based on the self-similarity within natural images and helps to find an accurate sparse representation by taking a weighted average of similar areas throughout the image. The local prior is based on learning the local structural regularity of the natural images and helps to regularize the sparse representation, exploiting the strong correlation in the small local areas within the image. Compared with the state-of-the-art EC algorithms, the results show that the proposed method has better reconstruction performance in terms of objective and subjective evaluations.

Identification of fungi-contaminated peanuts using hyperspectral imaging technology and joint sparse representation model.

Peanuts with fungal contamination may contain aflatoxin, a highly carcinogenic substance. We propose the use of hyperspectral imaging to quickly and noninvasively identify fungi-contaminated peanuts. The spectral data and spatial information of hyperspectral images were exploited to improve identification accuracy. In addition, successive projection was adopted to select the bands sensitive to fungal contamination. Furthermore, the joint sparse representation based classification (JSRC), which considers neighboring pixels as belonging to the same class, was adopted, and the support vector machine (SVM) classifier was used for comparison. Experimental results show that JSRC outperforms SVM regarding robustness against random noise and considering pixels at the edge of the peanut kernel. The classification accuracy of JSRC reached 99.2% and 98.8% at pixel scale, at least 98.4% and 96.8% at kernel scale for two peanut varieties, retrieving more accurate and consistent results than SVM. Moreover, fungi-contaminated peanuts were correctly marked in both learning and test images.

Hyperspectral Anomaly Detection via Background and Potential Anomaly Dictionaries Construction

In this paper, we propose a new anomaly detection method for hyperspectral images based on two well-designed dictionaries: background dictionary and potential anomaly dictionary. In order to effectively detect an anomaly and eliminate the influence of noise, the original image is decomposed into three components: background, anomalies, and noise. In this way, the anomaly detection task is regarded as a problem of matrix decomposition. Considering the homogeneity of background and the sparsity of anomalies, the low-rank and sparse constraints are imposed in our model. Then, the background and potential anomaly dictionaries are constructed using the background and anomaly priors. For the background dictionary, a joint sparse representation (JSR)-based dictionary selection strategy is proposed, assuming that the frequently used atoms in the overcomplete dictionary tend to be the background. In order to make full use of the prior information of anomalies hidden in the scene, the potential anomaly dictionary is constructed. We define a criterion, i.e., the anomalous level of a pixel, by using the residual calculated in the JSR model within its local region. Then, it is combined with a weighted term to alleviate the influence of noise and background. Experiments show that our proposed anomaly detection method based on potential anomaly and background dictionaries construction can achieve superior results compared with other state-of-the-art methods.

A Mixed Denoising Algorithm Based on Weighted Joint Sparse Representation

Joint sparse representation is not ideal for the processing of outliers in image, so a weighted joint sparse representation model for image denoising is proposed. This model introduces a weighted matrix of common information shared by data samples and reduces the influence of outliers. The greedy algorithm based on weighted simultaneous orthogonal matching pursuit is used to approximate the global optimal solution of the model effectively. The weighted noisy image block is used to remove the mixed noise of the image by jointly coding the nonlocal similar image blocks. By combining global priori knowledge and sparse errors into one unified framework, the denoising performance is further improved. Experimental results show that the denoising performance of this method is better than the existing hybrid denoising methods.

Hyperspectral image classification with a class-dependent spatial–spectral mixed metric

In this paper, we propose a class-dependent spatial–spectral mixed metric (cdSSMM) hyperspectral image (HSI) classification method, which combines the joint sparse representation (JSR) and a spectral mixed metric (SMM) for the purpose of exploiting both contextual correlation and spectral relationship within superpixel. The SMM is designed by combining the spectral information divergence (SID) and the spectral angle mapper (SAM) to exploit spectral discriminability of the two spectral measures. Specifically, a superpixel map is first generated, which is used for extracting the spatial information in an unfixed local region. Then, the SMMs are calculated separately by two models [i.e., SID multiplied by the tangent of SAM (SMMtg) and SID multiplied by the sine of SAM (SMMsn)] in a superpixel region. Next, the residuals between test and training samples are calculated by the JSR model. Finally, the results of SMM and the residuals obtained by JSR are combined to discriminate the class of each test sample based on a unified class membership function. Experimental results on two typical HSI datasets demonstrate that the proposed method can obtain better classification results compared with several well-known classification methods.

Self-Paced Joint Sparse Representation for the Classification of Hyperspectral Images

In this paper, a self-paced joint sparse representation (SPJSR) model is proposed for the classification of hyperspectral images (HSIs). It replaces the least-squares (LS) loss in the standard joint sparse representation (JSR) model with a weighted LS loss and adopts a self-paced learning (SPL) strategy to learn the weights for neighboring pixels. Rather than predefining a weight vector in the existing weighted JSR methods, both the weight and sparse representation (SR) coefficient associated with neighboring pixels are optimized by an alternating iterative strategy. According to the nature of SPL, in each iteration, neighboring pixels with nonzero weights (i.e., easy pixels) are included for the joint SR of a testing pixel. With the increase of iterations, the model size (i.e., the number of selected neighboring pixels) is enlarged and more neighboring pixels from easy to complex are gradually added into the JSR learning process. After several iterations, the algorithm can be terminated to produce a desirable model that includes easy homogeneous pixels and excludes complex inhomogeneous pixels. Experimental results on two benchmark hyperspectral data sets demonstrate that our proposed SPJSR is more accurate and robust than existing JSR methods, especially in the case of heavy noise.