Showing papers in "IEEE Signal Processing Letters in 2019"

Medical Image Fusion via Convolutional Sparsity Based Morphological Component Analysis

Abstract: In this letter, a sparse representation (SR) model named convolutional sparsity based morphological component analysis (CS-MCA) is introduced for pixel-level medical image fusion. Unlike the standard SR model, which is based on single image component and overlapping patches, the CS-MCA model can simultaneously achieve multi-component and global SRs of source images, by integrating MCA and convolutional sparse representation (CSR) into a unified optimization framework. For each source image, in the proposed fusion method, the CSRs of its cartoon and texture components are first obtained by the CS-MCA model using pre-learned dictionaries. Then, for each image component, the sparse coefficients of all the source images are merged and the fused component is accordingly reconstructed using the corresponding dictionary. Finally, the fused image is calculated as the superposition of the fused cartoon and texture components. Experimental results demonstrate that the proposed method can outperform some benchmarking and state-of-the-art SR-based fusion methods in terms of both visual perception and objective assessment.

PhaseNet: A Deep Convolutional Neural Network for Two-Dimensional Phase Unwrapping

Abstract: Phase unwrapping is a crucial signal processing problem in several applications that aims to restore original phase from the wrapped phase. In this letter, we propose a novel framework for unwrapping the phase using deep fully convolutional neural network termed as PhaseNet. We reformulate the problem definition of directly obtaining continuous original phase as obtaining the wrap-count (integer jump of 2 $\pi$ ) at each pixel by semantic segmentation and this is accomplished through a suitable deep learning framework. The proposed architecture consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The relationship between the absolute phase and the wrap-count is leveraged in generating abundant simulated data of several random shapes. This deliberates the network on learning continuity in wrapped phase maps rather than specific patterns in the training data. We compare the proposed framework with the widely adapted quality-guided phase unwrapping algorithm and also with the well-known MATLAB's unwrap function for varying noise levels. The proposed framework is found to be robust to noise and computationally fast. The results obtained highlight that deep convolutional neural network can indeed be effectively applied for phase unwrapping, and the proposed framework will hopefully pave the way for the development of a new set of deep learning based phase unwrapping methods.

A Convolutional Recurrent Attention Model for Subject-Independent EEG Signal Analysis

Abstract: The electroencephalogram (EEG) signal is a medium to realize a brain–computer interface (BCI) system due to its zero clinical risk and portable acquisition devices. Current EEG-based BCI research usually requires a subject-specific adaptation step before a BCI can be employed by a new user. In contrast, the subject-independent scenario, where a well trained model can be directly applied to new users without precalibration, is particularly desired. Considering this critical gap, the focus in this letter is developing an effective EEG signal analysis adaptively applied to subject-independent settings. We present a convolutional recurrent attention model ( CRAM ) that utilizes a convolutional neural network to encode the high-level representation of EEG signals and a recurrent attention mechanism to explore the temporal dynamics of the EEG signals as well as to focus on the most discriminative temporal periods. Extensive experiments on a benchmark multiclass EEG dataset containing four movement intentions indicate that the proposed model is capable of exploiting the underlying invariant EEG patterns across different subjects and generalizing the patterns to new subjects with better performance than a series of state-of-the-art and baseline approaches by at least eight percentage points. The implementation code is made publicly available. 1 1 https://github.com/dalinzhang/CRAM .

One-Class Convolutional Neural Network

Abstract: We present a novel convolutional neural network (CNN) based approach for one-class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one-class classification. The proposed one-class CNN is evaluated on the UMDAA-02 Face, Abnormality-1001, and FounderType-200 datasets. These datasets are related to a variety of one-class application problems such as user authentication, abnormality detection, and novelty detection. Extensive experiments demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. The source code is available at: github.com/otkupjnoz/oc-cnn.

Deep Convolution Network for Direction of Arrival Estimation With Sparse Prior

Abstract: In this letter, a deep learning framework for direction of arrival (DOA) estimation is developed. We first show that the columns of the array covariance matrix can be formulated as under-sampled noisy linear measurements of the spatial spectrum. Then, a deep convolution network (DCN) that learns the inverse transformation from large training dataset is introduced. In contrast to traditional sparsity-inducing methods with computationally complex iterations, the proposed DCN-based framework could efficiently obtain DOA estimates in near real time. Moreover, the utilization of the sparsity prior improves DOA estimation performance compared to existing deep learning based methods. Simulation results have demonstrated the superiority of the proposed method in both DOA estimation precision and computation efficiency especially when SNR is low.

Fast Spectrogram Inversion Using Multi-Head Convolutional Neural Networks

Abstract: We propose the multi-head convolutional neural network (MCNN) for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN enables significantly better utilization of modern multi-core processors than commonly used iterative algorithms like Griffin–Lim, and yields very fast (more than 300 × real time) runtime. For training of MCNN, we use a large-scale speech recognition dataset and losses defined on waveforms that are related to perceptual audio quality. We demonstrate that MCNN constitutes a very promising approach for high-quality speech synthesis, without any iterative algorithms or autoregression in computations.

Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution

Abstract: Camera arrays provide spatial and angular information within a single snapshot. With refocusing methods, focal planes can be altered after exposure. In this letter, we propose a light field refocusing method to improve the imaging quality of camera arrays. In our method, the disparity is first estimated. Then, the unfocused region (bokeh) is rendered by using a depth-based anisotropic filter. Finally, the refocused image is produced by a reconstruction-based superresolution approach where the bokeh image is used as a regularization term. Our method can selectively refocus images with focused region being superresolved and bokeh being esthetically rendered. Our method also enables postadjustment of depth of field. We conduct experiments on both public and self-developed datasets. Our method achieves superior visual performance with acceptable computational cost as compared to the other state-of-the-art methods.

DOA Estimation Exploiting Moving Dilated Nested Arrays

Abstract: A novel dilated nested array is presented to obtain an enhanced fully filled difference coarray exploiting array motions. The proposed sparse array is suitable for the cases when the sensing environment can be assumed stationary over an array motion of half wavelength or shorter. Closed-form expressions of the number of degrees of freedom in the difference coarray of the combined array before and after the translation motion are presented for direction-of-arrival (DOA) estimation. It is shown that the maximum number of consecutive lags for this case is three times that of the corresponding conventional two-level nested array. Numerical results of DOA estimation using the proposed array are provided for performance comparison and to validate array analyses.

Automatic Classification of Retinal Optical Coherence Tomography Images With Layer Guided Convolutional Neural Network

Abstract: Optical coherence tomography (OCT) enables instant and direct imaging of morphological retinal tissue and has become an essential imaging modality for ophthalmology diagnosis. As one of the important morphological retinal characteristics, the structural information of retinal layers provides meaningful diagnostic information and is closely related to several retinal diseases. In this letter, we propose a novel layer guided convolutional neural network (LGCNN) to identify normal retina and three common types of macular pathologies, namely, diabetic macular edema, drusen, and choroidal neovascularization. Specifically, an efficient segmentation network is first employed to generate the retinal layer segmentation maps, which can delineate two lesion-related retinal layers associated with the meaningful retinal lesions. Then, two well-designed subnetworks in LGCNN are utilized to integrate the information of two lesion-related layers. Consequently, LGCNN can efficiently focus on the meaningful lesion-related layer regions to improve OCT classification. The experimental results conducted on two clinically acquired datasets demonstrate the effectiveness of the proposed method.

Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network

Abstract: A simple convolutional neural network is proposed in this letter and is trained end-to-end to restore clear images from hazy inputs. The proposed network is generic and agnostic in the sense that it is not designed specifically for image dehazing and, in particular, it has no knowledge of the atmosphere scattering model. Remarkably, this network achieves record-breaking dehazing performance on several standard data sets that are synthesized using the atmosphere scattering model. This surprising finding suggests that there might be a need to rethink the predominant plug-in approach to image dehazing.

One-Bit MUSIC

Abstract: In this letter, we consider the problem of direction-of-arrival (DOA) estimation with one-bit quantized array measurements. With analysis, it is shown that, under mild conditions the one-bit covariance matrix can be approximated by the sum of a scaled unquantized covariance matrix and a scaled identity matrix. Although the scaling parameters are unknown because of the extreme quantization, they do not affect the subspace-based DOA estimators. Specifically, the signal and noise subspaces can be straightforwardly determined through the eigendecomposition of the one-bit covariance matrix, without pre-processing such as unquantized covariance matrix reconstruction. With so-obtained subspaces, the most classical multiple signal classification (MUSIC) technique can be applied to determine the signal DOAs. The resulting method is thus termed as one-bit MUSIC. Thanks to the simplicity of this method, it can be very easily implemented in practical applications, whereas the DOA estimation performance is comparable to the case with unquantized covariance matrix reconstruction, as demonstrated by various simulations.

Maximum Correntropy Criterion With Variable Center

Abstract: Correntropy is a local similarity measure defined in kernel space, and the maximum correntropy criterion (mcc) has been successfully applied in many areas of signal processing and machine learning in recent years. The kernel function in correntropy is usually restricted to the Gaussian function with the center located at zero. However, the zero-mean Gaussian function may not be a good choice for many practical applications. In this letter, we propose an extended version of correntropy, whose center can be located at any position. Accordingly, we propose a new optimization criterion called maximum correntropy criterion with variable center (MCC-VC). We also propose an efficient approach to optimize the kernel width and center location in the MCC-VC. Simulation results of regression with linear-in-parameter (LIP) models confirm the desirable performance of the new method.

Per-Channel Energy Normalization: Why and How

Abstract: In the context of automatic speech recognition and acoustic event detection, an adaptive procedure named per-channel energy normalization (PCEN) has recently shown to outperform the pointwise logarithm of mel-frequency spectrogram (logmelspec) as an acoustic frontend. This letter investigates the adequacy of PCEN for spectrogram-based pattern recognition in far-field noisy recordings, both from theoretical and practical standpoints. First, we apply PCEN on various datasets of natural acoustic environments and find empirically that it Gaussianizes distributions of magnitudes while decorrelating frequency bands. Second, we describe the asymptotic regimes of each component in PCEN: temporal integration, gain control, and dynamic range compression. Third, we give practical advice for adapting PCEN parameters to the temporal properties of the noise to be mitigated, the signal to be enhanced, and the choice of time-frequency representation. As it converts a large class of real-world soundscapes into additive white Gaussian noise, PCEN is a computationally efficient frontend for robust detection and classification of acoustic events in heterogeneous environments.

Cooperative Rate Splitting for MISO Broadcast Channel With User Relaying, and Performance Benefits Over Cooperative NOMA

Abstract: Due to its promising performance in a wide range of practical scenarios, Rate-Splitting (RS) has recently received significant attention in academia for the downlink of communication systems. In this letter, we propose and analyse a Cooperative Rate-Splitting (CRS) strategy based on the three-node relay channel where the transmitter is equipped with multiple antennas. By splitting user messages and linearly precoding common and private streams at the transmitter, and opportunistically asking the relaying user to forward its decoded common message, CRS can efficiently cope with a wide range of propagation conditions (disparity of user channel strengths and directions) and compensate for the performance degradation due to deep fading. The precoder design and the resource allocation are optimized by solving the Weighted Sum Rate (WSR) maximization problem. Numerical results demonstrate that our proposed CRS scheme can achieve an explicit rate region improvement compared to its non-cooperative counterpart and other cooperative strategies (such as cooperative NOMA).

A Fast and Efficient Text Steganalysis Method

Abstract: With the rapid development of natural language processing technology in the past few years, the steganography by text synthesis has been greatly developed. These methods can analyze the statistical feature distribution of a large number of training samples, and then generate steganographic texts that conform to such statistical distribution. For these steganography methods, previous steganalysis methods show unsatisfactory detection performance, which remains an unsolved problem and poses a great threat to the security of cyberspace. In this letter, we proposed a fast and efficient text steganalysis method to solve this problem. We first analyzed the correlations between words in these generated steganographic texts. Then, we map each word to a semantic space and used a hidden layer to extract the correlations between these words. Finally, based on the extracted correlation features, we used the softmax classifier to classify the input text. Experimental results show that the proposed model can achieve a high detection accuracy, which shows a state-of-the-art performance.

A Linear Estimator for Network Localization Using Integrated RSS and AOA Measurements

Abstract: This letter addresses the problem of simultaneous localization of multiple targets in three-dimensional cooperative wireless sensor networks. To this end, integrated received signal strength and angle of arrival measurements are employed. By exploiting the convenient nature of spherical representation of the considered problem, the measurement models are linearized and a sub-optimal estimator is formulated. Unlike the maximum likelihood estimator, which is highly non-convex and difficult to tackle directly, the derived estimator is quadratic and has a closed-form solution. Its computational complexity is linear in the number of connections and its accuracy surpasses the accuracy of existing ones in all considered scenarios.

Performance Gains From Cooperative MIMO Radar and MIMO Communication Systems

Abstract: In this letter, the coexistence of a multiple-input multiple-output (MIMO) radar and a distributed MIMO communication systems is studied. Target returns contributed from both the radar transmitters and communication transmitters are employed to complete the radar task, leading to a hybrid active-passive MIMO radar network. For the communication task, not only are the communication signals received directly from communication transmitters, but also those bounced off from the target are exploited to extract useful information. The target localization Cramer–Rao bound and mutual information are derived for the radar and communication systems, respectively. It is shown that there is a performance gain due to the cooperation between the radar and communication systems.

TS-RNN: Text Steganalysis Based on Recurrent Neural Networks

Abstract: With the rapid development of natural language processing technologies, more and more text steganographic methods based on automatic text generation technology have appeared in recent years. These models use the powerful self-learning and feature extraction ability of the neural networks to learn the feature expression of massive normal texts. Then, they can automatically generate dense steganographic texts which conform to such statistical distribution based on the learned statistical patterns. In this letter, we observe that the conditional probability distribution of each word in the automatically generated steganographic texts will be distorted after embedded with hidden information. We use recurrent neural networks to extract these feature distribution differences and then classify those features into cover text and stego text categories. Experimental results show that the proposed model can achieve high detection accuracy. Besides, the proposed model can even make use of the subtle differences of the feature distribution of texts to estimate the amount of hidden information embedded in the generated steganographic text.

Aggregate Tracklet Appearance Features for Multi-Object Tracking

Abstract: Multi-object tracking (MOT) has wide applications in the fields of video analysis and signal processing. A major challenge in MOT is how to associate the noisy detections into long and continuous trajectories. In this letter, we address the association problem at the tracklet-level, and mainly focus on the appearance representation designed for tracklets. A multitask convolutional neural network is proposed to learn the discriminative features and spatial-temporal attentions jointly. In particular, we decompose an object in a static image with spatial attentions, and then aggregate multiple features in a tracklet based on the temporal attentions. Appearance misalignment that caused by occlusion and inaccurate bounding is then mitigated by multi-feature aggregation. Experimental results on two challenging MOT benchmarks have demonstrated the effectiveness of the proposed method and shown significant improvement on the quality of tracking identities.

Convolutional Neural Network Based Text Steganalysis

Abstract: The prevailing text steganalysis methods detect steganographic communication by extracting hand-crafted features and classifying them using SVM. However, these features are designed based on the statistical changes caused by steganography, thus they are difficult to adapt to different kinds of embedding algorithms and the detection performance is heavily dependent on the text size. In this letter, we propose a novel text steganalysis model based on convolutional neural network, which is able to capture complex dependencies and learn feature representations automatically from the texts. First, we use a word embedding layer to extract the semantic and syntax feature of words. Second, the rectangular convolution kernels with different sizes are used to learn the sentence features. To further improve the performance, we present a decision strategy for detecting the long texts. Experimental results show that the proposed method can effectively detect different kinds of text steganographic algorithms and achieve comparable or superior performance for a wide variety of text sizes compared with the previous methods.

Selection of Empirical Mode Decomposition Techniques for Extracting Breathing Rate From PPG

Abstract: Breathing rate (BR) is a significant bio marker that provides both prognostic and diagnostic information for monitoring physiological condition. In addition to vital bio markers, such as blood oxygen saturation and pulse rate, BR can be extracted from non-invasive and wearable pulse oximeter based photoplethysmogram (PPG). Empirical mode decomposition (EMD) and its noise-assisted variants are widely used for decomposing non-linear and non-stationary signals. In this work, the effect of all variants of EMD in extracting BR from PPG has been investigated. We have used an EMD family PCA based hybrid model in extracting BR from PPG, which is a natural extension of our previously developed ensemble EMD (EEMD) PCA hybrid model. The performance of each model has been tested using two different datasets: MIMIC and Capnobase. Median absolute error varied from 0 to 5.03 and from 2.47 to 10.55 breaths/min for MIMIC and Capnobase dataset, respectively. Among all the EMD variants, EEMD-PCA and improved complete EEMD with adaptive noise (ICEEMDAN) PCA hybrid model present better performance for both datasets. This is the first study to compare EMD variants performance for decomposing real world signal and determine that from current methods, ICEEMDAN and EEMD are optimal for estimating BR from PPG.

Lightweight Feature Fusion Network for Single Image Super-Resolution

Abstract: Single image super-resolution (SISR) has witnessed great progress as convolutional neural network (CNN) gets deeper and wider. However, enormous parameters hinder its application to real world problems. In this letter, We propose a lightweight feature fusion network (LFFN) that can fully explore multi-scale contextual information and greatly reduce network parameters while maximizing SISR results. LFFN is built on spindle blocks and a softmax feature fusion module (SFFM). Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit. and a feature refinement unit. The dimension extension layer expands low dimension to high dimension and implicitly learns the feature maps which are suitable for the next unit. The feature exploration unit performs linear and nonlinear feature exploration aimed at different feature maps. The feature refinement layer is used to fuse and refine features. SFFM fuses the features from different modules in a self-adaptive learning manner with softmax function, making full use of hierarchical information with a small amount of parameter cost. Both qualitative and quantitative experiments on benchmark datasets show that LFFN achieves favorable performance against state-of-the-art methods with similar parameters.

Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning

Abstract: While deep neural networks exhibit state-of-the-art results in the task of image super-resolution (SR) with a fixed known acquisition process (e.g., a bicubic downscaling kernel), they experience a huge performance loss when the real observation model mismatches the one used in training. Recently, two different techniques suggested to mitigate this deficiency, i.e., enjoy the advantages of deep learning without being restricted by the training phase. The first one follows the plug-and-play (P&P) approach that solves general inverse problems (e.g., SR) by using Gaussian denoisers for handling the prior term in model-based optimization schemes. The second builds on internal recurrence of information inside a single image, and trains a super-resolver network at test time on examples synthesized from the low-resolution image. Our letter incorporates these two independent strategies, enjoying the impressive generalization capabilities of deep learning, captured by the first, and further improving it through internal learning at test time. First, we apply a recent P&P strategy to SR. Then, we show how it may become image-adaptive in test time. This technique outperforms the above two strategies on popular datasets and gives better results than other state-of-the-art methods in practical cases where the observation model is inexact or unknown in advance.

A Robust NLOS Bias Mitigation Technique for RSS-TOA-Based Target Localization

Abstract: This letter proposes a novel robust mitigation technique to address the problem of target localization in adverse non-line-of-sight (NLOS) environments. The proposed scheme is based on combined received signal strength and time of arrival measurements. Influence of NLOS biases is mitigated by treating them as nuisance parameters through a robust approach. Due to a high degree of difficulty of the considered problem, it is converted into a generalized trust region sub-problem by applying certain approximations, and solved efficiently by merely a bisection procedure. Numerical results corroborate the effectiveness of the proposed approach, rendering it the most accurate one in all considered scenarios.

A Generic Receiver Architecture for MIMO Wireless Power Transfer With Nonlinear Energy Harvesting

Abstract: This letter investigates a multiple-input multiple-output (MIMO) wireless power transfer system under practical nonliner energy harvesting (EH) models. We propose a new generic energy receiver (ER) architecture consisting of $N$ receive antennas and $L$ rectifiers, for which one power splitter is inserted after each antenna to adaptively split the received radio frequency (RF) signals among the $L$ rectifiers for efficient nonlinear RF-to-direct current (dc) conversion. With the proposed architecture, we maximize the total harvested dc power at the ER, by jointly optimizing the transmit energy beamforming at the energy transmitter and the power splitting ratios at the ER. Numerical results show that our proposed design by exploiting the nonlinearity of EH significantly improves the harvested dc power at the ER, as compared to two conventional designs.

Learning Bilevel Layer Priors for Single Image Rain Streaks Removal

Abstract: Rain streaks removal is an important issue of the outdoor vision system and recently has been investigated extensively. In the past decades, maximum a posterior and network-based architecture have been attracting considerable attention for this problem. However, it is challenging to establish effective regularization priors and the cost function with complex prior is hard to optimize. On the other hand, it is still hard to incorporate data-dependent information into conventional numerical iterations. To partially address the above limits and inspired by the leader–follower gaming perspective, we introduce an unrolling strategy to incorporate data-dependent network architectures into the established iterations, i.e., a learning bilevel layer priors method to jointly investigate the learnable feasibility and optimality of rain streaks removal problem. Both visual and quantitative comparison results demonstrate that our method outperforms the state of the art.

Coherent SVR Learning for Wideband Direction-of-Arrival Estimation

Abstract: In this letter, we propose a coherent support vector regression (SVR) scheme to address the wideband direction of arrival (DOA) estimation problem. This learning-based method deals with wideband DOA estimation by treating it as a function approximation issue. The proposed approach first decomposes the wideband array outputs into several narrowband components, then approximates the functional relationship between the decomposed narrowband data and the DOA with coherent SVR scheme through training. The trained function is then capable of estimating the DOA when wideband signal with unknown impinging direction arrives. We prove the effectiveness and superiority of the presented method by simulation experiments. Simulation results show that the new technique has a better performance in terms of estimation errors than the conventional broadband DOA estimation method, especially in demanding scenarios with low SNR and limited snapshots. Moreover, the proposed approach also relaxes the unambiguous array element-spacing restrictions, i.e., it has extended the frequency range of wideband signals where direction finding without angle ambiguity is achievable.

Edge-Aware Convolution Neural Network Based Salient Object Detection

Abstract: Salient object detection has received great amount of attention in recent years. In this letter, we propose a novel salient object detection algorithm, which combines the global contextual information along with the low-level edge features. First, we train an edge detection stream based on the state-of-the-art holistically-nested edge detection (HED) model and extract hierarchical boundary information from each VGG block. Then, the edge contours are served as the complementary edge-aware information and integrated with the saliency detection stream to depict continuous boundary for salient objects. Finally, we combine pyramid pooling modules with auxiliary side output supervision to form the multi-scale pyramid-based supervision module, providing multi-scale global contextual information for the saliency detection network. Compared with the previous methods, the proposed network contains more explicit edge-aware features and exploit the multi-scale global information more effectively. Experiments demonstrate the effectiveness of the proposed method, which achieves the state-of-the-art performance on five popular benchmarks.

Velocity-Based Signal Features for the Assessment of Parkinsonian Handwriting

Abstract: This letter investigates different velocity-based signal processing techniques to the aim of Parkinson's disease classification through handwriting. It is showed that combining new velocity-based features with classic features improves state-of-the-art performance on the PaHaW dataset.

The Multi-Lane Capsule Network

Abstract: We introduce multi-lane capsule networks (MLCN), which are a separable and resource efficient organization of capsule networks (CapsNet) that allows parallel processing while achieving high accuracy at reduced cost. A MLCN is composed of a number of (distinct) parallel lanes , each contributing to a dimension of the result, trained using the routing-by-agreement organization of CapsNet. Our results indicate similar accuracy with a much-reduced cost in number of parameters for the Fashion-MNIST and Cifar10 datasets. They also indicate that the MLCN outperforms the original CapsNet when using a proposed novel configuration for the lanes. MLCN also has faster training and inference times, being more than two-fold faster than the original CapsNet in a same accelerator.