Joint Sparse Model Research Articles

Histopathological image classification through discriminative feature learning and mutual information-based multi-channel joint sparse representation

Histopathological image classification is a very challenging task because of the biological heterogeneities and rich geometrical structures. In this paper, we propose a novel histopathological image classification framework, which includes the discriminative feature learning and the mutual information-based multi-channel joint sparse representation. We first propose a stack-based discriminative prediction sparse decomposition (SDPSD) model by incorporating the class labels information to predict deep discriminant features automatically. Subsequently, a mutual information-based multi-channel joint sparse model (MIMCJSM) is presented to jointly encode the common component and particular components of the discriminative features. Especially, the main advantage of the MIMCJSM is the construction of a joint dictionary using a mutual information criterion, which contains a common sub-dictionary and three particular sub-dictionaries. Based on the joint dictionary, the MIMCJSM captures the relationship of multi-channel features, which can improve discriminative ability of joint sparse representation coefficients. Finally, the joint sparse representation coefficients of different levels can be aggregated using the spatial pyramid matching (SPM) model, and the linear support vector machine (SVM) is used as the classifier. Experimental results on ADL and BreaKHis datasets demonstrate that our proposed framework consistently performs better than popular existing classification frameworks. Additionally, it can show promising strong-robustness performance for histopathological image classification.

Image restoration based on adaptive switching between synthesis and analysis sparse regularisation

Both synthesis and analysis sparse regularisation have been successfully applied to solve various inverse vision problems. The authors find an optimisation model to combine the power of the dual sparse prior models for image restoration. Specifically, for each local patch, adaptive switching on using synthesis or analysis sparse regularisation is performed for better restoration quality. In addition, cluster-specific synthesis and analysis sub-dictionary learning, based on principal component analysis method and sequential minimal eigenvalues algorithm, is incorporated into the joint sparse models to achieve maximum indices gains. The efficient alternating strategy is exploited to solve the optimisation problem. Experimental results highlight the superiority of the proposed approach compared with the state-of-the-art methods, especially in terms of better image structures preservation.

A novel multi-focus image fusion method based on distributed compressed sensing

Multi-focus image fusion aims to produce an all-in-focus image by merging multiple partially focused images of the same scene. The main work is identifying the focused region and then composing all the focused regions. In this paper, a novel efficient multi-focus image fusion method based on distributed compressed sensing (DCS) is proposed. Firstly, the low-frequency and high-frequency images are obtained by comparing the variance of the source images, which are further utilized to get the low-frequency and high-frequency dictionaries. Secondly, DCS using joint sparsity model-1 (JSM-1) is applied to reconstruct the precise high-frequency images. Thirdly, the decision map is obtained based on all the high-frequency images and then improved by the morphological processing. Finally, the focused pixels are chosen from the source images through the decision map. Experimental results indicate that the proposed DCS-based method can be competitive with or even outperform some state-of-the-art methods in terms of both visual and quantitative metric evaluations.

Hyperspectral Unmixing Via Nonconvex Sparse and Low-Rank Constraint

In recent years, sparse unmixing has attracted significant attention, as it can effectively avoid the bottleneck problems associated with the absence of pure pixels and the estimation of the number of endmembers in hyperspectral scenes. The joint-sparsity model has outperformed the single sparse unmixing method. However, the joint-sparsity model might cause some aliasing artifacts for the pixels on the boundaries of different constituent endmembers. To address this shortcoming, researchers have developed many unmixing algorithms based on low-rank representation, which makes good use of the global structure of data. In addition, the high mutual coherence of spectral libraries strongly affects the applicability of sparse unmixing. In this study, adopting combined constraints imposing sparsity and low rankness, a novel algorithm called nonconvex joint-sparsity and low-rank unmixing with dictionary pruning is developed In particular, we impose sparsity on the abundance matrix using the $\ell _{2,p}$ mixed norm, and we also employ the weighted Schatten $p$ -norm instead of the convex nuclear norm as an approximation for the rank. The key parameter $p$ is set between 0.4 and 0.6, and a good quality sparse solution is generated. The effectiveness of the proposed algorithm is demonstrated on both simulated and real hyperspectral datasets.

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.

Manifold Constrained Low-Rank and Joint Sparse Learning for Dynamic Cardiac MRI

Reconstruction from highly accelerated dynamic magnetic resonance imaging (MRI) is of great significance for medical diagnosis. The application of low-rank and sparse matrix decomposition to MRI can improve imaging speed and efficiency. However, the consistence of the learned low-rank and sparse structures for similar input samples is not well addressed in literature. In this paper, we propose a manifold constrained low-rank and joint sparse learning model that embeds the manifold priors into low-rank and joint sparse decomposition. It is noted that the joint sparsity is investigated to exploit the shared information. Further, the manifold constraints for low-rank and joint sparse parts are forced the optimization process to satisfy the structure preservation requirement. To solve the above manifold learning problem, a manifold constrained alternating direction method of multipliers ( McADMM ) approach is designed. It is proved theoretically that the sequence generated by McADMM converges to a stationary point. Numerical comparisons on simulation data and real-world dynamic cardiac MRI data are presented to demonstrate its efficiency.

Evaluating Effect of Blanket Jamming on Radar Via Robust Time-Frequency Analysis and Peak to Average Power Ratio

Evaluating the effect of blanket jamming is at the core of performance analysis and jamming/anti-jamming design for radar. Restricted to diverse jamming types and radar’s applications, it is challenging to put forward a unified framework for quantitative evaluation. To address this issue, we come up with a composite evaluation by combining the robust time-frequency analysis (RTFA) and peak to average power ratio (PAPR). In term of signal-level evaluation, RTFA is exploited to analyze the echoes directly, providing the time-frequency (TF) spectrum for calculating two-dimensional image entropy. For system/application-level evaluation, we derive the variation of signal to jamming ratio (SJR) in radar processing chain, and thus define the PAPR to associate SJR with target detection, a type of common and fundamental application that usually affects the other subsequent ones. To refine composite evaluation, we modify the traditional RTFA by leveraging joint sparse model with convolution framelets to improve TF concentration and to avoid the crossing terms; meanwhile, we derive the quantitative relationship between SJR and detection probability, leading to theoretical guarantee of PAPR for evaluation. Finally, the feasibility and the superiority of the proposed evaluation approach are validated in numerical experiments.

Backtracking based Joint-Sparse Signal Recovery for Distributed Compressive Sensing

In Distributed Compressive Sensing (DCS), the Joint Sparsity Model (JSM) refers to an ensemble of signals being jointly sparse. In [4], a joint reconstruction scheme was proposed using a single linear program. However, for reconstruction of any individual sparse signal using that scheme, the computational complexity is high. In this paper, we propose a dual-sparse signal reconstruction method. In the proposed method, if one signal is known apriori, then any other signal in the ensemble can be efficiently estimated using the proposed method, exploiting the dual-sparsity. Simulation results show that the proposed method provides fast and efficient recovery.

Salient feature multimodal image fusion with a joint sparse model and multiscale dictionary learning

A multimodal image fusion method based on the joint sparse model (JSM), multiscale dictionary learning, and a structural similarity index (SSIM) is presented. As an effective signal representation technique, JSM is derived from distributed compressed sensing and has been successfully employed in many image-processing applications such as image classification and fusion. The highly redundant single dictionary always has difficulty satisfying the correlations between images in traditional JSM-based image fusion. Therefore, the proposed fusion model learns a more compact multiscale dictionary to effectively combine the multiscale analysis used in nonsubsampled contourlet transformation with the single-scale joint sparse representation used in image domains to solve the issues of single-scale sparse fusion and to improve fusion quality. The experimental results demonstrate that the proposed fusion method obtains the state-of-the-art performances in terms of both subjective visual quality and objective metrics, especially when fusing multimodal images.

Image Object Recognition via Deep Feature-Based Adaptive Joint Sparse Representation.

An image object recognition approach based on deep features and adaptive weighted joint sparse representation (D-AJSR) is proposed in this paper. D-AJSR is a data-lightweight classification framework, which can classify and recognize objects well with few training samples. In D-AJSR, the convolutional neural network (CNN) is used to extract the deep features of the training samples and test samples. Then, we use the adaptive weighted joint sparse representation to identify the objects, in which the eigenvectors are reconstructed by calculating the contribution weights of each eigenvector. Aiming at the high-dimensional problem of deep features, we use the principal component analysis (PCA) method to reduce the dimensions. Lastly, combined with the joint sparse model, the public features and private features of images are extracted from the training sample feature set so as to construct the joint feature dictionary. Based on the joint feature dictionary, sparse representation-based classifier (SRC) is used to recognize the objects. Experiments on face images and remote sensing images show that D-AJSR is superior to the traditional SRC method and some other advanced methods.

Multi-Hypothesis Prediction Scheme Based on the Joint Sparsity Model

Multi-Hypothesis Prediction Scheme Based on the Joint Sparsity Model

Collaborative Representation and Sparsity are Both Indispensable for Hyperspectral Imagery Classification

As a recently proposed technique, sparse representation based classifier (SRC) has been widely used for hyperspectral imagery classification and detection. The collaborative representation (CR) and the sparse coding are two key points in SRC scheme. More recently, the proposition that which one of them plays a dominant role in SRC scheme has attracted much attention from researchers in fields of image processing, computer vision, and pattern recognition. In this paper, we first discuss why CR or sparsity works and why one of them alone is not sufficient, and then analyze how CR and sparsity interact with each other. Although we focus on how sparsity augments CR, the necessity of CR for sparsity is also illustrated in both pixel-wise model and joint sparsity model. Inspired by the analysis, we indicate that CR is a powerful tool for solving the high-dimensional pattern recognition with small sample in SRC scheme; sparsity augments CR-based classification in stabilizing, making sure unique solution and rejecting outlying samples. In other words, CR and sparsity complement each other and are both indispensible for hyperspectral imagery classification. The experimental results on simulated data and real hyperspectral imagery confirm the conclusion.

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.

A probabilistic fusion of a support vector machine and a joint sparsity model for hyperspectral imagery classification

Hyperspectral imagery (HSI) is now in use for a wide range of applications such as land cover classification, climate change studies and environmental monitoring; however, the acquisition of HSI is still costly, and the curse of dimensionality i.e. the phenomenon that the amount of required training samples increases exponentially as the dimensionality increases linearly, makes it difficult to exploit the full potential of machine learning in HSI classification. To resolve the problem, we propose a novel framework for spatial-spectral HSI classification in this article. A soft support vector machine (SVM) and a probabilistic joint sparsity model (JSM) are proposed to compute a posteriori probabilities of the test pixels, respectively; and the probability scores are then fused by a linear opinion pool. Furthermore, a Markov random field (MRF) model is used as a maximum a posteriori (MAP) segmentation method for further regularization of the neighbor information to derive the labels for pixels. Extensive experiments conducted on three commonly-used benchmarking data sets show that the proposed probabilistic fusion method outperforms a number of well-known spatial-spectral HSI classification techniques.

Compressed Ultrasound Signal Reconstruction Using a Low-Rank and Joint-Sparse Representation Model.

With the introduction of very dense sensor arrays in ultrasound (US) imaging, data transfer rate and data storage can become a bottleneck in US system design. To reduce the amount of sampled channel data, we propose a new approach based on the low-rank and joint-sparse model that allows us to exploit the correlations between different US channels and transmissions. With this method, the minimum number of measurements at each channel can be lower than the sparsity in compressive sensing theory. The accuracy of the reconstruction is less dependent on the sparse basis. An optimization algorithm based on the simultaneous direction method of multipliers is proposed to efficiently solve the resulting optimization problem. Results on different data sets with different experimental settings show that the proposed method is better adapted to the US signals and can recover the image with fewer samples (e.g., 10% of the samples) than the existing compressive sensing-based methods, while maintaining reasonable image quality.

Joint-Sparse-Blocks and Low-Rank Representation for Hyperspectral Unmixing

Hyperspectral unmixing has attracted much attention in recent years. Single sparse unmixing assumes that a pixel in a hyperspectral image consists of a relatively small number of spectral signatures from large, ever-growing, and available spectral libraries. Joint-sparsity (or row-sparsity) model typically enforces all pixels in a neighborhood to share the same set of spectral signatures. The two sparse models are widely used in the literature. In this paper, we propose a joint-sparsity-blocks model for abundance estimation problem. Namely, the abundance matrix of size $m\times n$ is partitioned to have one row block and $s$ column blocks and each column block itself is joint-sparse. It generalizes both the single (i.e., $s=n$ ) and the joint (i.e., $s=1$ ) sparsities. Moreover, concatenating the proposed joint-sparsity-blocks structure and low rankness assumption on the abundance coefficients, we develop a new algorithm called joint-sparse-blocks and low-rank unmixing . In particular, for the joint-sparse-blocks regression problem, we develop a two-level reweighting strategy to enhance the sparsity along the rows within each block. Simulated and real-data experiments demonstrate the effectiveness of the proposed algorithm.

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.

Multimodal image fusion with adaptive joint sparsity model

An adaptive joint sparsity model (JSM) is presented for multimodal image fusion. As a multisignal modeling technique, JSM, which is derived from distributed compressed sensing, has been successfully employed in multimodal image fusion. In traditional JSM-based fusion, a single dictionary learned by K-singular value decomposition (SVD) has higher coherence yet may result in potential visual confusion and misleading. In the proposed model, we first learn a plurality of subdictionaries and use a supervised classification approach based on gradient information. Then, one of the learned subdictionaries is adaptively applied to JSM to obtain the common and innovative sparse coefficients.. Finally, the fused image is reconstructed by the fused sparse coefficients and the adaptive dictionary. Infrared-visible images and medical images were selected to test the proposed approach. The results were compared with those of traditional methods, such as the multiscale transform-based methods, JSM-based method, and adaptive sparse representation (ASR) model-based method. Experimental results on multimodal images demonstrate that the proposed fusion method can obtain better performance than the conventional JSM-based method and ASR-based method in terms of both visual quality and objective assessment.

Video reconstruction based on Intrinsic Tensor Sparsity model

The natural images have self-similarities which can be used to improve the image reconstruction. However, the existing video reconstruction algorithms pay more attention to modeling and ignore the importance of priors in the reconstruction. In this paper, the self-similarities are involved in the modeling when the video is reconstructed from temporally compressed video measurements. The proposed reconstruction model includes two parts: First, the video tensor sparsity model is formulated by using a spatial–temporal tensor sparse penalty for similar patches. The Intrinsic Tensor Sparsity (ITS) measure is used as the sparsity measure, which encodes both sparsity insights delivered by the Tucker and CANDECOMP/PARAFAC (CP) decomposition for tensors. Second, 3D video patches are modeled as the Gaussian Joint Sparsity (GJS) by exploiting the temporal similarity to obtain an initial image which has distinct direction structure. GJS is a combination of statistical distribution and joint sparsity model. The experimental results show that both the reconstruction models based on ITS and GJS contribute to improving the quality of the video reconstruction.

Block-Sparsity-Based Multiuser Detection for Uplink Grant-Free NOMA

Grant-free non-orthogonal multiple access has recently gained significant attention for reducing signaling overhead in machine-type communications. In this context, compressed sensing (CS) has been identified as a good candidate for joint activity and data detection due to the inherent sparsity nature of user activity. This paper augments activity and data detection for frame-based multi-user uplink scenarios where users are (in)-active for the duration of a frame, namely, the frame-wise joint sparsity model. First, we formulate the block CS (BCS)-based sparse signal recovery framework, by fully extracting and exploiting the underlying frame-wise joint sparsity of the user activity. Then, to make explicit use of the block sparsity inherent in the equivalent block-sparse model and considering the user sparsity level to be unknown for multiuser detection, two enhanced BCS-based greedy algorithms are developed, i.e., threshold aided block sparsity adaptive subspace pursuit (TA-BSASP) and cross-validation aided block sparsity adaptive subspace pursuit (CVA-BSASP). Specifically, the proposed TA-BSASP algorithm can approach the oracle least squares (LS) performance by reasonably setting the threshold based on the additive white Gaussian noise floor. Moreover, the proposed CVA-BSASP algorithm is a highly practical algorithm design that adopts the statistical and machine learning mechanism cross-validation to determine the stopping condition of the algorithm and this does not require prior knowledge. Furthermore, the convergence and the computational complexity of the proposed algorithms are derived and the superior performance of the proposed algorithms is demonstrated by numerical experiments.