Search

Abstract Background Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) — a locally adaptive image filter — allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering. Methods Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ( $$[^{18}\text {F}]$$ [ 18 F ] FDG, $$[^{18}\text {F}]$$ [ 18 F ] L-DOPA, $$[^{68}\text {Ga}]$$ [ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the “optimal” filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs. Results The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal $$\text {SUV}_\text {max}$$ SUV max values of the unfiltered images with a low mean ± SD difference of $$\delta \text {SUV}_\text {max}^{\text {CNN},\text {STD}}$$ δ SUV max CNN , STD = (−3.9 ± 5.2)% and $$\delta \text {SUV}_\text {max}^{\text {BF},\text {STD}}$$ δ SUV max BF , STD = (−4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar $$\text {SUV}_\text {max}$$ SUV max values in the vast majority of cases with an overall average difference of $$\delta \text {SUV}_\text {max}^{\text {CNN},\text {BF}}$$ δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with $$\delta \text {Noise}^{\text {CNN},\text {BF}}$$ δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed. Conclusions Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning.

Background: Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) — a locally adaptive image filter — allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering. Methods: Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ( [ 18 F ] FDG, [ 18 F ] L-DOPA, [ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the "optimal" filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs. Results: The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUV max values of the unfiltered images with a low mean ± SD difference of δ SUV max CNN , STD = (−3.9 ± 5.2)% and δ SUV max BF , STD = (−4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUV max values in the vast majority of cases with an overall average difference of δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed. Conclusions: Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning. [ABSTRACT FROM AUTHOR]

The need for efficient video coding technology is more important than ever in the current scenario where video applications are increasing worldwide, and Internet of Things (IoT) devices are becoming widespread. In this context, it is necessary to carefully review the recently completed MPEG-5 Essential Video Coding (EVC) standard because the EVC Baseline profile is customized to meet the specific requirements needed to process IoT video data in terms of low complexity. Nevertheless, the EVC Baseline profile has a notable disadvantage. Since it is a codec composed only of simple tools developed over 20 years, it tends to represent numerous coding artifacts. In particular, the presence of blocking artifacts at the block boundary is regarded as a critical issue that must be addressed. To address this, this paper proposes a post-filter using a block partitioning information-based Convolutional Neural Network (CNN). The proposed method in the experimental results objectively shows an approximately 0.57 dB for All-Intra (AI) and 0.37 dB for Low-Delay (LD) improvements in each configuration by the proposed method when compared to the pre-post-filter video, and the enhanced PSNR results in an overall bitrate reduction of 11.62% for AI and 10.91% for LD in the Luma and Chroma components, respectively. Due to the huge improvement in the PSNR, the proposed method significantly improved the visual quality subjectively, particularly in blocking artifacts at the coding block boundary. [ABSTRACT FROM AUTHOR]

Acquired images are often noisy. Since the amount of such images increases, they should be compressed where lossy compression is often applied for several reasons. Such compression is associated with the phenomena of specific image filtering due to lossy compression and the possible existence of an optimal operation point (OOP). However, such filtering is not perfect, and residual noise can be quite intensive even if an image is compressed at the so-called optimal operation point. Then, additional post-filtering can be applied. Thus, the basic subject of this paper is the post-processing of noisy images compressed in a lossy manner. The main goal of this paper is to consider the possible application of a block-matching 3-dimensional (BM3D) filter to images corrupted by additive white Gaussian noise compressed by a better portable graphics (BPG) coder with a compression ratio smaller than that for the optimal operation point and in OOP neighborhood. The tasks of this paper are to analyze the efficiency of compressed image post-processing depending on noise intensity, image complexity, coder compression parameter Q, and filter threshold parameter β according to different quality metrics and to provide practical recommendations on setting the filter and coder parameters. The main result is that the post-processing efficiency decreases when the coder compression parameter increases and becomes negligible for a coder compression parameter slightly larger than its value for OOP. The post-processing efficiency is larger for simpler structure images and larger noise intensity. Compressed image quality due to post-processing improves according to the standard criterion peak signal-to-noise ratio and visual quality metrics. For larger coder compression parameters, the optimal threshold shifts toward smaller values. In conclusion, we demonstrate the efficiency of post-processing and show that the BM3D filter outperforms the standard discrete cosine-based (DCT) filter. We also provide recommendations for filter parameter setting. We also outline possible research directions for the future.

Acquired images are often noisy. Since the amount of such images increases, they should be compressed where lossy compression is often applied for several reasons. Such compression is associated with the phenomena of specific image filtering due to lossy compression and the possible existence of an optimal operation point (OOP). However, such filtering is not perfect, and residual noise can be quite intensive even if an image is compressed at the so-called optimal operation point. Then, additional post-filtering can be applied. Thus, the basic subject of this paper is the post-processing of noisy images compressed in a lossy manner. The main goal of this paper is to consider the possible application of a block-matching 3-dimensional (BM3D) filter to images corrupted by additive white Gaussian noise compressed by a better portable graphics (BPG) coder with a compression ratio smaller than that for the optimal operation point and in OOP neighborhood. The tasks of this paper are to analyze the efficiency of compressed image post-processing depending on noise intensity, image complexity, coder compression parameter Q, and filter threshold parameter β according to different quality metrics and to provide practical recommendations on setting the filter and coder parameters. The main result is that the postprocessing efficiency decreases when the coder compression parameter increases and becomes negligible for a coder compression parameter slightly larger than its value for OOP. The post-processing efficiency is larger for simpler structure images and larger noise intensity. Compressed image quality due to post-processing improves according to the standard criterion peak signal-to-noise ratio and visual quality metrics. For larger coder compression parameters, the optimal threshold shifts toward smaller values. In conclusion, we demonstrate the efficiency of post-processing and show that the BM3D filter outperforms the standard discrete cosine-based (DCT) filter. We also provide recommendations for filter parameter setting. We also outline possible research directions for the future. [ABSTRACT FROM AUTHOR]

The need for efficient video coding technology is more important than ever in the current scenario where video applications are increasing worldwide, and Internet of Things (IoT) devices are becoming widespread. In this context, it is necessary to carefully review the recently completed MPEG-5 Essential Video Coding (EVC) standard because the EVC Baseline profile is customized to meet the specific requirements needed to process IoT video data in terms of low complexity. Nevertheless, the EVC Baseline profile has a notable disadvantage. Since it is a codec composed only of simple tools developed over 20 years, it tends to represent numerous coding artifacts. In particular, the presence of blocking artifacts at the block boundary is regarded as a critical issue that must be addressed. To address this, this paper proposes a post-filter using a block partitioning information-based Convolutional Neural Network (CNN). The proposed method in the experimental results objectively shows an approximately 0.57 dB for All-Intra (AI) and 0.37 dB for Low-Delay (LD) improvements in each configuration by the proposed method when compared to the pre-post-filter video, and the enhanced PSNR results in an overall bitrate reduction of 11.62% for AI and 10.91% for LD in the Luma and Chroma components, respectively. Due to the huge improvement in the PSNR, the proposed method significantly improved the visual quality subjectively, particularly in blocking artifacts at the coding block boundary.

The accuracy of positron emission tomography (PET) imaging is hampered by the partial volume effect (PVE), which causes image blurring and sampling. The PVE produces spillover phenomena, making PET analysis difficult. Generally, the PVE values vary based on reconstruction methods and filtering. Thus, selection of the proper reconstruction and filtering method can ensure accurate and high-quality PET images. This study compared the values of factors (recovery coefficient (RC), uniformity, and spillover ratio (SOR)) associated with different reconstruction and post-filtering methods using a mouse image quality phantom (NEMA NU 4), and we present an effective approach for microPET images. The PET images were obtained using a microPET scanner (Inveon, Siemens Medical Solutions, Malvern, PA, USA). PET data were reconstructed and/or post-filtered. For tumors smaller than 3 mm, iterative reconstruction methods provided better image quality. For tumor sizes bigger than 3 mm, reconstruction methods without post-filtering showed better results. [ABSTRACT FROM AUTHOR]

The paper proposes a novel post-filtering method based on convolutional neural networks (CNNs) for quality enhancement of RGB/grayscale images and video sequences. The lossy images are encoded using common image codecs, such as JPEG and JPEG2000. The video sequences are encoded using previous and ongoing video coding standards, high-efficiency video coding (HEVC) and versatile video coding (VVC), respectively. A novel deep neural network architecture is proposed to estimate fine refinement details for full-, half-, and quarter-patch resolutions. The proposed architecture is built using a set of efficient processing blocks designed based on the following concepts: (i) the multi-head attention mechanism for refining the feature maps, (ii) the weight sharing concept for reducing the network complexity, and (iii) novel block designs of layer structures for multiresolution feature fusion. The proposed method provides substantial performance improvements compared with both common image codecs and video coding standards. Experimental results on high-resolution images and standard video sequences show that the proposed post-filtering method provides average BD-rate savings of 31.44% over JPEG and 54.61% over HEVC (x265) for RGB images, Y-BD-rate savings of 26.21% over JPEG and 15.28% over VVC (VTM) for grayscale images, and 15.47% over HEVC and 14.66% over VVC for video sequences.

In order to simplify the complexity and reduce the cost of the microphone array, this paper proposes a dual-microphone based sound localization and speech enhancement algorithm. Based on the time delay estimation of the signal received by the dual microphones, this paper combines energy difference estimation and controllable beam response power to realize the 3D coordinate calculation of the acoustic source and dual-microphone sound localization. Based on the azimuth angle of the acoustic source and the analysis of the independent quantity of the speech signal, the separation of the speaker signal of the acoustic source is realized. On this basis, post-wiener filtering is used to amplify and suppress the voice signal of the speaker, which can help to achieve speech enhancement. Experimental results show that the dual-microphone sound localization algorithm proposed in this paper can accurately identify the sound location, and the speech enhancement algorithm is more robust and adaptable than the original algorithm.

Abstract Background Positron emission tomography (PET) imaging has a wide applicability in oncology, cardiology and neurology. However, a major drawback when imaging very active regions such as the bladder is the spill-in effect, leading to inaccurate quantification and obscured visualisation of nearby lesions. Therefore, this study aims at investigating and correcting for the spill-in effect from high-activity regions to the surroundings as a function of activity in the hot region, lesion size and location, system resolution and application of post-filtering using a recently proposed background correction technique. This study involves analytical simulations for the digital XCAT2 phantom and validation acquiring NEMA phantom and patient data with the GE Signa PET/MR scanner. Reconstructions were done using the ordered subset expectation maximisation (OSEM) algorithm. Dedicated point-spread function (OSEM+PSF) and a recently proposed background correction (OSEM+PSF+BC) were incorporated into the reconstruction for spill-in correction. The standardised uptake values (SUV) were compared for all reconstruction algorithms. Results The simulation study revealed that lesions within 15–20 mm from the hot region were predominantly affected by the spill-in effect, leading to an increased bias and impaired lesion visualisation within the region. For OSEM, lesion SUVmax converged to the true value at low bladder activity, but as activity increased, there was an overestimation as much as 19% for proximal lesions (distance around 15–20 mm from the bladder edge) and 2–4% for distant lesions (distance larger than 20 mm from the bladder edge). As bladder SUV increases, the % SUV change for proximal lesions is about 31% and 6% for SUVmax and SUVmean, respectively, showing that the spill-in effect is more evident for the SUVmax than the SUVmean. Also, the application of post-filtering resulted in up to 65% increment in the spill-in effect around the bladder edges. For proximal lesions, PSF has no major improvement over OSEM because of the spill-in effect, coupled with the blurring effect by post-filtering. Within two voxels around the bladder, the spill-in effect in OSEM is 42% (32%), while for OSEM+PSF, it is 31% (19%), with (and without) post-filtering, respectively. But with OSEM+PSF+BC, the spill-in contribution from the bladder was relatively low (below 5%, either with or without post-filtering). These results were further validated using the NEMA phantom and patient data for which OSEM+PSF+BC showed about 70–80% spill-in reduction around the bladder edges and increased contrast-to-noise ratio up to 36% compared to OSEM and OSEM+PSF reconstructions without post-filtering. Conclusion The spill-in effect is dependent on the activity in the hot region, lesion size and location, as well as post-filtering; and this is more evident in SUVmax than SUVmean. However, the recently proposed background correction method facilitates stability in quantification and enhances the contrast in lesions with low uptake.

Dense image matching (DIM) is a critical technique when computing accurate 3D geometric information for many photogrammetric applications. Most DIM methods adopt first‐order regularisation priors for efficient matching, which often introduce stepped biases (also called fronto‐parallel biases) into the matching results. To remove these biases and compute more accurate matching results, this paper proposes a novel post‐filtering method by adjusting the surface orientation of each pixel in the matching process. The core algorithm formulates the post‐filtering as the optimisation of a global energy function with second‐order regularisation priors. A compromise solution of the energy function is computed by breaking the optimisation into a collection of sub‐optimisations of each pixel in a local adaptive window. The proposed method was compared with several state‐of‐the‐art post‐filtering methods on indoor, aerial and satellite datasets. The comparisons demonstrate that the proposed method obtains the highest post‐filtering accuracies on all datasets. [ABSTRACT FROM AUTHOR]

The accuracy of positron emission tomography (PET) imaging is hampered by the partial volume effect (PVE), which causes image blurring and sampling. The PVE produces spillover phenomena, making PET analysis difficult. Generally, the PVE values vary based on reconstruction methods and filtering. Thus, selection of the proper reconstruction and filtering method can ensure accurate and high-quality PET images. This study compared the values of factors (recovery coefficient (RC), uniformity, and spillover ratio (SOR)) associated with different reconstruction and post-filtering methods using a mouse image quality phantom (NEMA NU 4), and we present an effective approach for microPET images. The PET images were obtained using a microPET scanner (Inveon, Siemens Medical Solutions, Malvern, PA, USA). PET data were reconstructed and/or post-filtered. For tumors smaller than 3 mm, iterative reconstruction methods provided better image quality. For tumor sizes bigger than 3 mm, reconstruction methods without post-filtering showed better results.

Abstract Wiener post-filtering is a method for sound source enhancement that is known to be practically effective in various acoustic environments. To calculate an Wiener post-filter, the power spectral density (PSD) of the target source as well as that of noise needs to be estimated. Although a previous method known as PSD-estimation-in-beamspace was invented for estimating the PSD of sound sources using multiple beamformers, heuristic design of the beamformers may degrade the accuracy in source PSD estimation. To avoid selecting such beamformers, this study proposes an analytical beamformer design method using subtractive PSD estimation model, i.e. the target source PSD is described by subtraction of the PSD of noise-dominant signals from the PSD of a target source-dominant signal. The study reveals that beamformers suitable for PSD estimation can be analytically designed when a PSD mixing matrix consisting of the beamformer's directivity gains is circulant and its inverse becomes an M-matrix to make the PSD estimation model subtractive. The results of numerical simulations and practical experiments prove that the performance of the sound source enhancement will be improved when beamformers designed with the proposed method are utilized even in practical acoustic environments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Context-aware recommender systems leverage the value of recommendations by exploiting context information that affects user preferences and situations, with the goal of recommending items that are really relevant to changing user needs. Despite the importance of context-awareness in the recommender systems realm, researchers and practitioners lack guides that help them understand the state of the art and how to exploit context information to smarten up recommender systems. This paper presents the results of a comprehensive systematic literature review we conducted to survey context-aware recommenders and their mechanisms to exploit context information. The main contribution of this paper is a framework that characterizes context-aware recommendation processes in terms of: i) the recommendation techniques used at every stage of the process, ii) the techniques used to incorporate context, and iii) the stages of the process where context is integrated into the system. This systematic literature review provides a clear understanding about the integration of context into recommender systems, including context types more frequently used in the different application domains and validation mechanisms—explained in terms of the used datasets, properties, metrics, and evaluation protocols. The paper concludes with a set of research opportunities in this field. [ABSTRACT FROM AUTHOR]

Several researchers have contemplated deep learning-based post-filters to increase the quality of statistical parametric speech synthesis, which perform a mapping of the synthetic speech to the natural speech, considering the different parameters separately and trying to reduce the gap between them. The Long Short-term Memory (LSTM) Neural Networks have been applied successfully in this purpose, but there are still many aspects to improve in the results and in the process itself. In this paper, we introduce a new pre-training approach for the LSTM, with the objective of enhancing the quality of the synthesized speech, particularly in the spectrum, in a more efficient manner. Our approach begins with an auto-associative training of one LSTM network, which is used as an initialization for the post-filters. We show the advantages of this initialization for the enhancing of the Mel-Frequency Cepstral parameters of synthetic speech. Results show that the initialization succeeds in achieving better results in enhancing the statistical parametric speech spectrum in most cases when compared to the common random initialization approach of the networks.

In this paper we propose a novel fast algorithm for calculating the transfer function of the Zelinski post-filter in a microphone array. The proposed algorithm requires less memory and fewer arithmetical multiplications. We demonstrate that for the 'classical' algorithm computational complexity increases quadratically as a function of the number of microphones in the array. In contrast, the computational complexity of the proposed algorithm increases linearly. This provides a considerable acceleration in the calculation of the post-filter transfer function in real-time systems. [ABSTRACT FROM AUTHOR]

Accurately predicting protein-protein interaction sites (PPIs) is currently a hot topic because it has been demonstrated to be very useful for understanding disease mechanisms and designing drugs. Machine-learning-based computational approaches have been broadly utilized and demonstrated to be useful for PPI prediction. However, directly applying traditional machine learning algorithms, which often assume that samples in different classes are balanced, often leads to poor performance because of the severe class imbalance that exists in the PPI prediction problem. In this study, we propose a novel method for improving PPI prediction performance by relieving the severity of class imbalance using a data-cleaning procedure and reducing predicted false positives with a post-filtering procedure: First, a machine-learning-based data-cleaning procedure is applied to remove those marginal targets, which may potentially have a negative effect on training a model with a clear classification boundary, from the majority samples to relieve the severity of class imbalance in the original training dataset; then, a prediction model is trained on the cleaned dataset; finally, an effective post-filtering procedure is further used to reduce potential false positive predictions. Stringent cross-validation and independent validation tests on benchmark datasets demonstrated the efficacy of the proposed method, which exhibits highly competitive performance compared with existing state-of-the-art sequence-based PPIs predictors and should supplement existing PPI prediction methods. [ABSTRACT FROM AUTHOR]

Anti-aliasing is a well-established technique in computer graphics that reduces the blocky or stair-wise appearance of pixels. This paper provides a comprehensive overview of the anti-aliasing techniques used in computer graphics, which can be classified into two categories: post-filtering based anti-aliasing and pre-filtering based anti-aliasing. We discuss post-filtering based anti-aliasing algorithms through classifying them into hardware anti-aliasing techniques and post-process techniques for deferred rendering. Comparisons are made among different methods to illustrate the strengths and weaknesses of every category. We also review the utilization of anti-aliasing techniques from the first category in different graphic processing units, i.e., different NVIDIA and AMD series. This review provides a guide that should allow researchers to position their work in this important research area, and new research problems are identified. [ABSTRACT FROM AUTHOR]

Highlights: [•] Lombard effect is modeled in post-filtering to improve speech intelligibility. [•] The proposed method works with narrowband telephone speech with minimal delay. [•] The proposed method improves intelligibility in difficult noise conditions. [ABSTRACT FROM AUTHOR]

Although the area of context-aware recommender systems (CARS) has made a significant progress over the last several years, the problem of comparing various contextual pre-filtering, post-filtering and contextual modeling methods remained fairly unexplored. In this paper, we address this problem and compare several contextual pre-filtering, post-filtering and contextual modeling methods in terms of the accuracy and diversity of their recommendations to determine which methods outperform the others and under which circumstances. To this end, we consider three major factors affecting performance of CARS methods, such as the type of the recommendation task, context granularity and the type of the recommendation data. We show that none of the considered CARS methods uniformly dominates the others across all of these factors and other experimental settings; but that a certain group of contextual modeling methods constitutes a reliable 'best bet' when choosing a sound CARS approach since they provide a good balance of accuracy and diversity of contextual recommendations. [ABSTRACT FROM AUTHOR]

In this work, we present novel Bayesian algorithms for acoustic echo cancellation and residual echo suppression in the presence of a memoryless loudspeaker nonlinearity. The system nonlinearity is modeled using a basis-generic nonlinear expansion. This allows us to express the microphone observation in the DFT domain in terms of the nonlinear-expansion coefficients and the acoustic echo path. We augment the observation model with first-order Markov models for the echo-path vector and the nonlinear-expansion coefficients to arrive at a composite state-space model. The echo path vector and each nonlinear-expansion coefficient are designated as the unknown random variables in our Bayesian model. The posterior estimators for the random variables and the learning rules for the a priori unknown model parameters are then derived via the maximization of the variational lower bound on the log likelihood. We further show that a Bayesian post-filter for residual echo suppression can be derived by optimizing a minimum-mean-square error (MMSE) cost function subject to marginalization with respect to the posteriors estimated in the echo cancellation stage. The effectiveness of the approach is supported by simulation results and an analysis using instrumental performance measures. [ABSTRACT FROM AUTHOR]

This paper shows the importance of the optimal smoothing scheme in Microphone Array Post-Filtering (MAPF) under a combined Deterministic-Stochastic Hybrid Model (DSHM). We reveal that some of the well-known MAPF algorithms may cause serious speech distortion without using the optimal smoothing scheme, which is resulted from oversmoothing the raw periodogram over time. Using a minimum conditional mean square error criterion, we derive the optimal smoothing factor under the DSHM, where the Deterministic-to-Stochastic-Ratio (DSR) and the stationarity determine the value of the optimal smoothing factor. The optimal smoothing scheme is applied to the Transient-Beam-to-Reference-Ratio (TBRR)-based MAPF algorithm and experimental results show its better performance in terms of both the Log-Spectral Distance (LSD) and the Perceptual Evaluation of Speech Quality (PESQ). [ABSTRACT FROM AUTHOR]

The problem of residual evaluation for fault detection in nonlinear systems is addressed in this article. Using the factorisation approach, a post-filter is designed and a threshold is computed to achieve an optimal trade-off between fault detectability and the number of false alarms. Furthermore, it is shown that the proposed post-filter also guarantees H-/H∞ multi-objective optimisation of the residual signal. The effectiveness of the proposed method is demonstrated by fault detection of the three-tank benchmark system. [ABSTRACT FROM AUTHOR]

A modification is proposed for the second order incomplete Cholesky decomposition (IC2). It makes possible to design a preconditioning procedure for the conjugate gradient method (CGM) with a controllable fill-in in the preconditioner. The modified algorithm is used to develop a load-balancing parallel preconditioning for CGM as applied to linear systems with symmetric positive definite matrices. Numerical results obtained using a multiprocessor computer system are presented. [ABSTRACT FROM AUTHOR]

The paper proposes a novel post-filtering method based on convolutional neural networks (CNNs) for quality enhancement of RGB/grayscale images and video sequences. The lossy images are encoded using common image codecs, such as JPEG and JPEG2000. The video sequences are encoded using previous and ongoing video coding standards, high-efficiency video coding (HEVC) and versatile video coding (VVC), respectively. A novel deep neural network architecture is proposed to estimate fine refinement details for full-, half-, and quarter-patch resolutions. The proposed architecture is built using a set of efficient processing blocks designed based on the following concepts: (i) the multi-head attention mechanism for refining the feature maps, (ii) the weight sharing concept for reducing the network complexity, and (iii) novel block designs of layer structures for multiresolution feature fusion. The proposed method provides substantial performance improvements compared with both common image codecs and video coding standards. Experimental results on high-resolution images and standard video sequences show that the proposed post-filtering method provides average BD-rate savings of 31.44 % over JPEG and 54.61 % over HEVC (x265) for RGB images, Y-BD-rate savings of 26.21 % over JPEG and 15.28 % over VVC (VTM) for grayscale images, and 15.47 % over HEVC and 14.66 % over VVC for video sequences. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a new method of depth-image-based rendering (DIBR) for free-viewpoint TV (FTV). In the conventional method, we estimated the depth of an object on the virtual image plane, which is called view-dependent depth estimation, and the virtual view images are rendered using the view-dependent depth map. In this method, virtual viewpoint images are rendered with 3D warping instead of estimating the view-dependent depth, since depth estimation is usually costly and it is desirable to eliminate it from the rendering process. However, 3D warping causes some problems that do not occur in the method with view-dependent depth estimation; for example, the appearance of holes on the rendered image, and the occurrence of depth discontinuity on the surface of the object at virtual image plane. Depth discontinuity causes artifacts on the rendered image. In this paper, these problems are solved by projecting depth map to the virtual image plane and performing post-filtering on the projected depth map. In the experiments, high-quality arbitrary viewpoint images were obtained by rendering images from relatively small number of cameras. [Copyright &y& Elsevier]

Automatic semantic concept detection in video is important for effective content-based video retrieval and mining and has gained great attention recently. In this paper, we propose a general post-filtering framework to enhance robustness and accuracy of semantic concept detection using association and temporal analysis for concept knowledge discovery. Co-occurrence of several semantic concepts could imply the presence of other concepts. We use association mining techniques to discover such inter-concept association relationships from annotations. With discovered concept association rules, we propose a strategy to combine associated concept classifiers to improve detection accuracy. In addition, because video is often visually smooth and semantically coherent, detection results from temporally adjacent shots could be used for the detection of the current shot. We propose temporal filter designs for inter-shot temporal dependency mining to further improve detection accuracy. Experiments on the TRECVID 2005 dataset show our post-filtering framework is both efficient and effective in improving the accuracy of semantic concept detection in video. Furthermore, it is easy to integrate our framework with existing classifiers to boost their performance. [ABSTRACT FROM PUBLISHER]

We propose a simple yet effective deblocking method for JPEG compressed image through postfiltering in shifted windows (PSW) of image blocks. The MSE is compared between the original image block and the image blocks in shifted windows, so as to decide whether these altered blocks are used in the smoothing procedure. Our research indicates that there exists strong correlation between the optimal mean squared error threshold and the image quality factor Q, which is selected in the encoding end and can be computed from the quantization table embedded in the JPEG file. Also we use the standard deviation of each original block to adjust the threshold locally so as to avoid the over-smoothing of image details. With various image and bit-rate conditions, the processed image exhibits both great visual effect improvement and significant peak signal-to-noise ratio gain with fairly low computational complexity. Extensive experiments and comparison with other deblocking methods are conducted to justify the effectiveness of the proposed PSW method in both objective and subjective measures. [ABSTRACT FROM AUTHOR]

Post-filtering is an effective tool for improvement of encoded image and video quality at low bit- rates. Some consumer electronics devices such as mobile phones apply excessive compression to meet limited bandwidth requirements. Thus, some annoying visual artifacts occur in the decoded image/video. This paper presents a deblocking method based on fuzzy logic to alleviate one of the most common visual art artifacts (i.e. blocking) encountered in heavily compressed images. The proposed approach takes intensity difference and variance of pixels at the block boundaries into account in a fuzzy manner to decide amount of blocking effect. Once the proposed approach decides the type of the blockiness, a simple interpolation according to the strength is carried out. Experimental results show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a novel noise reduction system, using a hybrid noise estimation technique and post-filtering, to suppress both localized noises and non-localized noise simultaneously in arbitrary noise environments. To estimate localized noises, we present a hybrid noise estimation technique which combines a multi-channel estimation approach we previously proposed and a soft-decision single-channel estimation approach. Final estimation accuracy for localized noises is significantly improved by incorporating a robust and accurate speech absence probability (RA-SAP) estimator, which considers the strong correlation of SAPs between adjacent frequency bins and consecutive frames and makes full use of the high estimation accuracy of the multi-channel approach. The estimated spectra of localized noises are reduced from those of noisy observations by spectral subtraction. Non-localized noise is further reduced by a multi-channel post-filter which is based on the optimally modified log-spectral amplitude (OM-LSA) estimator. With the assumption of a diffuse noise field, we propose an estimator for the a priori SAP based on the coherence characteristic of the noise field at spectral subtraction output, high coherence at low frequencies and low coherence at high frequencies, improving the spectral enhancement of the desired speech signal. Experimental results demonstrates the effectiveness and superiorities of the proposed noise estimation/reduction methods in terms of objective and subjective measures in various noise conditions. [Copyright &y& Elsevier]

A speech reinforcement system is presented to improve communication between the front and the rear passengers in large motor vehicles. This type of communication can be difficult due to a number of factors, including distance between speakers, noise and lack of visual contact. The system described makes use of a set of microphones to pick up the speech of each passenger, then it amplifies these signals and plays them back to the cabin through the car audio loudspeaker system. The two main problems are noise amplification and electro-acoustic coupling between loudspeakers and microphones. To overcome these problems the system uses a set of acoustic echo cancellers, echo suppression filters and noise reduction stages. In this paper, the stability of a speech reinforcement system is studied. We propose a solution based on echo cancellers and residual echo suppression filters. The spectral estimation method for the power spectral density of the residual echo existing after the echo canceller is presented along with the derivation of the optimal residual echo suppression filter. Some results about the performance of the proposed system are also provided. [ABSTRACT FROM AUTHOR]

In this paper, we present a method to reduce blocking and ringing artifacts in low bit-rate block-based video coding. For each block, its DC value and DC values of the surrounding eight neighbor blocks are exploited to predict low frequency AC coefficients, which allow to infer spatial characteristics of a block before quantization stage in the encoding system. These predicted AC coefficients are used to classify each block into either of two categories, low-activity or high-activity block. In the following post-processing stage, two kinds of low pass filters are adaptively applied according to the classified result on each block. It allows for strong low pass filtering in low-activity regions where the blocking artifacts are most noticeable, whereas it allows for weak low pass filtering in high-activity regions to reduce ringing noise as well as blocking artifacts without introducing undesired blur. In the former case, the blocking artifacts are reduced by one-dimensional (1-D) horizontal and vertical low pass filters. In the latter case, both deblocking and deringing are considered by using either 3-tap or 2-tap filter, which make the architecture simple.TMN8 decoder for H.263+ is used to test the proposed method. The experimental results are evaluated in both subjective and objective manner, and show that the proposed algorithm is efficient and effective in reducing ringing artifacts as well as blocking artifacts in the low bit-rate block-based video coding. [Copyright &y& Elsevier]

A far-reaching expansion of advanced information technology enables ease and seamless communications over online social networks, which have been a de facto premium correspondents in the current cyber world. The ever-growing social network data has gained attention in recent years and can be handy for industrial revolution 4.0. With the integration of social networks with the Internet of Things being noticed in different industries to enhance human involvement and increase their productivity, security in such networks is increasingly alarming. Vulnerabilities can be characterized in the form of privacy invasion, leading to hazardous contents, which can be detrimental to social media actors and in turn impact the processes of the overall Social Network-Integrated Industrial Internet of Things (SN-IIoT) ecosystem. Despite this prevalence, the current platforms do not have any significant level of functionality to capture, process, and reveal unhealthy content among the social media actors. To address those challenges by detecting hazardous contents and create a stable social internet environment within IIoT, a statistical learning-enabled trustworthy analytic tool for human behaviors has been developed in this paper. More specifically, this paper proposes a machine learning (ML)-enabled scheme SPY-BOT, which incorporates a hybrid data extraction algorithm to perform post-filtering that arbitrates the users' behavior polarity. The scheme creates class labels based on the featured keywords from the decision user and classifies suspicious contacts through the aid of ML. The results suggest the potential of the proposed approach to classify the users' behavior in SN-IIoT. [ABSTRACT FROM AUTHOR]