Isotropic Filter Research Articles

Predicting the wash behaviour of filter cakes with inhomogeneous cake geometry on a macroscopic scale

Displacement washing of isotropic filter cakes with inhomogeneous cake geometry is investigated theoretically. Fluid flow is described by Darcy’s law, while the advection–dispersion equation is used to describe solute transport within the cake. An additional mass transfer term is taken into account to describe mass transfer from non-permeated to permeated domains of the filter cake. The equations are solved numerically in three spatial dimensions. Model predictions are compared to experimental data from preceding publications of the authors and show good agreement. An explorative case study demonstrates the negative impact of typical inhomogeneous cake geometries on displacement washing.

Local geometry-perceptive mesh convolution with multi-ring receptive field

Learning 3D mesh representation is necessary for many computer vision and graphic tasks. Recently, some works have studied convolution methods for directly processing input meshes. However, these methods are usually weak in extracting local geometry information because of the disadvantages such as isotropic filter, neglect of mesh topology, and a small convolution field. In this paper, we introduce a local geometry-perceptive mesh convolution, which pays attention to mesh irregular structures for efficiently capturing geometry features in a multi-ring receptive field. Specifically, we define each template node’s dynamic neighbor-attention weights used in multiple attention aggregation operations for obtaining local mesh change information of different vertices in the multi-ring field. After each aggregation, a shared anisotropic filter maps the catenation of each new vertex and its neighbors for extracting geometry features of the current ring. Then, complete local geometry features of each vertex in its large local field are obtained by summing the mapped results of each aggregation. Moreover, the position features of each vertex are added to its local geometry features to get the final representation vector of the vertex. We demonstrate the proposed mesh convolution method’s strong ability in modeling 3D mesh shapes.

Robust Mesh Representation Learning via Efficient Local Structure-Aware Anisotropic Convolution.

Mesh is a type of data structure commonly used for 3-D shapes. Representation learning for 3-D meshes is essential in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insights from CNN for 3-D shapes. However, 3-D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3-D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this article, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each template's node according to its neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in the random synthesizer-a new Transformer model for natural language processing (NLP). Since the learnable weighting matrices require large amounts of parameters for high-resolution 3-D shapes, we introduce a matrix factorization technique to notably reduce the parameter size, denoted as LSA-small. Furthermore, a residual connection with a linear transformation is introduced to improve the performance of our LSA-Conv. Comprehensive experiments demonstrate that our model produces significant improvement in 3-D shape reconstruction compared to state-of-the-art methods.

Fast Grayscale Morphology for Circular Window

AbstractMorphological operations are among the most popular classic image filters. The filter assumes the maximum or minimum value within a window and is often used for light object thickening and thinning operations, which are important components of various workflows, such as object recognition and stylization. Circular windows are preferred over rectangular windows for obtaining isotropic filter results. However, the existing efficient algorithms focus on rectangular or binary input images. Efficient morphological operations with circular windows for grayscale images remain challenging. In this study, we present a fast grayscale morphology heuristic computation algorithm that decomposes circular windows using the convex hull of circles. We significantly accelerate traditional methods based on Minkowski addition by introducing new decomposition rules specialized for circular windows. As our morphological operation using a convex hull can be computed independently for each pixel, the algorithm is efficient for modern multithreaded hardware.

Novel computer aided diagnostic system using hybrid neural network for early detection of pancreatic cancer

One of the most dangerous tumours in the world, pancreatic cancer (PC), has an unimpressive five-year survival rate of about 5%. An early PC identification is crucial for raising patient survival rates. Diagnosis of PC requires computed tomography (CT), magnetic resonance imaging (MRI) with magnetic resonance cholangiopancreatography (MRCP), or biopsy. The proposed CAD design approach includes image preprocessing, segmentation, feature extraction, and classification phases. Preprocessing is done by using Colour conversion and an isotropic diffusion filter approaches. After that, proposed Fuzzy K-NN Equality algorithm used in segmentation procedures. Deep Learning with feature extraction is used as a classification tool. Tumour cells are classified using the features collected from the pancreatic sample. Train values and testing datasets are part of the image classification criterion. For the purpose of detecting pancreatic cancer, a hybrid Deep Convolutional Neural Network with Deep Belief Network (DCNN_DBN) algorithm is used. According to the experimental findings, the current CAD system offers massive prospects as well as safety in the automated diagnosis of both benign as well as malignant cancers and produces the accuracy of 99.6%. Using this classifier, computing complexity is massively diminished. The suggested technique could be enhanced to detect more pancreatic cancer cell abnormalities.

Anisotropic diffusion filters for flow-dependent variational data assimilation of sea surface temperature

It is well known that the background error covariance matrix in the data assimilation is anisotropic and varied with the flow field, that is, flow-dependent. However, it is generally assumed to be isotropic and static for ease of implementation. Therefore, to enhance the quality of the background error covariance, two easy-to-implement, flow-dependent three-dimensional variational analysis (3DVar) schemes, the advection–diffusion filter (ADF) and the Smagorinsky diffusion filter (SDF), are tentatively proposed. These serve as alternative schemes for the traditional methods that are based on the isotropic assumption. First, a correctness test of the gradient for the ADF is performed to verify the validity of the adjoint code. Then, the response analysis for the 1D advection–diffusion​ equation is investigated to validate the anisotropic characteristic of the ADF with various flow velocities. Second, the two flow-dependent 3DVar schemes are verified via single-observation assimilation experiments. Compared to the existing diffusion filter with a static diffusion coefficient, both new schemes show a flow-dependent capability in the assimilation experiment because they successfully spread the observational information anisotropically. Finally, a retroactive real-time forecast experiment framework based on a 3D baroclinic primitive equation ocean model is used to investigate the effects of the ADF/SDF on the analysis and forecast accuracy of sea surface temperature (SST). While the traditional variational assimilation method with an isotropic diffusion filter generally reduces initial field errors, both the ADF and SDF can further enhance the accuracy of the initial fields in strong current areas. In addition, better forecast skills can be obtained with the two flow-dependent schemes in the East China Sea.

Ability of spatial filters to distinguish between two MUAPs generated from MUs with different locations, sizes and fibers pennation

In this study, we investigated the effects of the motor unit (MU) location and size and the fibres pennation on the ability of anisotropic and almost isotropic spatial filters used to detect surface electromyographic (EMG) signals to make a distinction between motor unit action potentials (MUAPs) generated from two MUs. The study was based on simulated MUAPs. The fibres orientation was performed by varying the fibres pennation angle (FPA).The root mean square error (RMSE) between MUAPs generated from two MUs was used as a criterion to evaluate the ability of the investigated filters to distinguish between two generated MUAPs. The location of a MU was fixed and the second MU moved away from the first MU in the transversal direction for the first case and in the depth direction in the second case to take five different locations in every case.We showed that the capability of the studied filters to more separate two MUAPs strongly depended on MU location, MU size and FPA. This capability of separation was best with large distances between the two MUs and with large sizes of them. Furthermore, the main survey of this work was that the BiTDD filter has the best ability of separation of two MUAPs than the other filters in a given FPA interval. The number of pennation angles in this interval is related to the location and size of the moved MU.

A novel filtering method for geodetically determined ocean surface currents using deep learning

Abstract Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth’s climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, which combines satellite observations of sea level and Earth’s gravity, offers the only means to estimate the dominant geostrophic component of these currents globally. Unfortunately, however, geodetically-determined geostrophic currents suffer from high levels of contamination in the form of geodetic noise. Conventional approaches use isotropic spatial filters to improve the signal-to-noise ratio, though this results in high levels of attenuation. Hence, the use of deep learning to improve the geodetic determination of the ocean currents is investigated. Supervised machine learning typically requires clean targets from which to learn. However, such targets do not exist in this case. Therefore, a training dataset is generated by substituting clean targets with naturally smooth climate model data and generative machine learning networks are employed to replicate geodetic noise, providing noisy input and clean target pairs. Prior knowledge of the geodetic noise is exploited to develop a more realistic training dataset. A convolutional denoising autoencoder (CDAE) is then trained on these pairs. The trained CDAE model is then applied to unseen real geodetic ocean currents. It is demonstrated that our method outperforms conventional isotropic filtering in a case study of four key regions: the Gulf Stream, the Kuroshio Current, the Agulhas Current, and the Brazil-Malvinas Confluence Zone.

Parallel BESO framework for solving high-resolution topology optimisation problems

The bi-directional evolutionary structural optimisation (BESO) has attracted much interest in recent decades. However, the high computational cost of the topology optimisation method hinders its applications in large-scale industrial designs. In this study, a parallel BESO method is developed to solve high-resolution topology optimisation problems. An open-source computing platform, FEniCS, is used to parallelise the finite element analysis (FEA) and optimisation steps. Significant improvements in efficiency have been made to the FEA and the filtering process. An iterative solver, a reanalysis approach and a hard-kill option in BESO have been developed to reduce the computational cost of the FEA. A PDE-based isotropic filter scheme is used to eliminate the time-consuming elemental adjacency search process. The efficiency and effectiveness of the developed method are demonstrated by a series of numerical examples in both 2D and 3D. It is shown that the parallel BESO can efficiently solve problems with more than 100 million tetrahedron elements on a 14-cores CPU server. This work holds great potential for high-resolution design problems in engineering and architecture.

A novel family of edge preserving anisotropic filters

In this article, new anisotropic image filters are introduced and their performances are compared with existing isotropic and anisotropic filters. The developed filters were examined according to their image noise removing performances in terms of standard image quality metrics, as well as the edge preserving properties of the filtered images. Mathematical inferences of anisotropic filters are made based on the minimization of the Polyakov action energy integral. New anisotropic metrics are found by means of Finsler metrics that minimize the corresponding integral. The new metrics perform filtering by updating the image with anisotropic Laplace-Beltrami flow. After filtering, it was observed that the introduced metrics perform well against other anisotropic metrics. It is also observed that the developed New Randers, New Normalized Miron, and New Metric filters preserve edges better than other filters, making it a plausible noise removal tool prior to edge detection in image processing. The source codes of proposed filters are publicly available at https://github.com/HAYDARKILIC.

Expressions for the calculation of isotropic Gaussian filter kernels in the spherical harmonic domain

Expressions for the calculation of isotropic Gaussian filter kernels in the spherical harmonic domain

Examining the Influence of Spatial Smoothing on Spatiotemporal Features of Intrinsic Connectivity Networks at Low ICA Model Order.

Using a relatively high model order of independent component analysis (ICA with 75 ICs) of functional magnetic resonance imaging (fMRI) data, we have reported a clear effect of spatial smoothing Gaussian kernel size on spatiotemporal properties of intrinsic connectivity networks (ICNs). However, many if not the majority of ICA fMRI studies are usually performed at low model order, e.g., 20-IC decomposition, as such low order is generally enough to extract the few networks of interest such as the default-mode network (DMN). The aim of this study is to investigate if we can replicate the spatial smoothing effects on spatiotemporal features of ICNs at low ICA model order. Same resting state fMRI data that we used with 75-IC analysis were used here. Spatial smoothing using an isotropic Gaussian filter kernel with full width at half maximum (FWHM) of 4, 8, and 12 mm was applied during preprocessing. ICNs were identified from 20-IC decomposition and evaluated in terms of three primary features: spatial map intensity, functional network connectivity (FNC), and power spectra. The results identified similar effects of spatial smoothing on spatial map intensities and power spectra at p < 0.01, false discovery rate (FDR) corrected for multiple comparisons. Reduced spatial smoothing kernel size resulted in decreased spatial map intensities as well as a generally decreased low-frequency power (0.01 - 0.10 Hz) but increased high-frequency power (0.15 - 0.25 Hz). FNC, however, did not show a uniform change in correlation values with the size of smoothing kernel. Notably, FNC between DMNs decreased but FNC between central executive and visual networks increased with an increase in smoothing kernel size. These preliminary findings confirm spatial smoothing influences ICN features regardless of model order. The discussion focuses on differences between observed changes at low and high ICA model orders.

Learning Local Neighboring Structure for Robust 3D Shape Representation

Mesh is a powerful data structure for 3D shapes. Representation learning for 3D meshes is important in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insight from CNN for 3D shapes. However, 3D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this paper, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each node according to the local neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in random synthesizer -- a new Transformer model for natural language processing (NLP). Comprehensive experiments demonstrate that our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.

Diffusion-informed spatial smoothing of fMRI data in white matter using spectral graph filters

Brain activation mapping using functional magnetic resonance imaging (fMRI) has been extensively studied in brain gray matter (GM), whereas in large disregarded for probing white matter (WM). This unbalanced treatment has been in part due to controversies in relation to the nature of the blood oxygenation level-dependent (BOLD) contrast in WM and its detectability. However, an accumulating body of studies has provided solid evidence of the functional significance of the BOLD signal in WM and has revealed that it exhibits anisotropic spatio-temporal correlations and structure-specific fluctuations concomitant with those of the cortical BOLD signal. In this work, we present an anisotropic spatial filtering scheme for smoothing fMRI data in WM that accounts for known spatial constraints on the BOLD signal in WM. In particular, the spatial correlation structure of the BOLD signal in WM is highly anisotropic and closely linked to local axonal structure in terms of shape and orientation, suggesting that isotropic Gaussian filters conventionally used for smoothing fMRI data are inadequate for denoising the BOLD signal in WM. The fundamental element in the proposed method is a graph-based description of WM that encodes the underlying anisotropy observed across WM, derived from diffusion-weighted MRI data. Based on this representation, and leveraging graph signal processing principles, we design subject-specific spatial filters that adapt to a subject’s unique WM structure at each position in the WM that they are applied at. We use the proposed filters to spatially smooth fMRI data in WM, as an alternative to the conventional practice of using isotropic Gaussian filters. We test the proposed filtering approach on two sets of simulated phantoms, showcasing its greater sensitivity and specificity for the detection of slender anisotropic activations, compared to that achieved with isotropic Gaussian filters. We also present WM activation mapping results on the Human Connectome Project’s 100-unrelated subject dataset, across seven functional tasks, showing that the proposed method enables the detection of streamline-like activations within axonal bundles.

Study on the Performances of an Approximating Spline Filter Based on the ADRF Function in Surface Roughness Evaluation

Isotropy is an important feature of an area filter in the three-dimensional surface roughness evaluation. First, the transmission characteristic deviation between the approximating spline filter and the Gaussian filter is reduced by cascading approximating. Second, the approximating spline filter is superimposed on the orthogonal direction to obtain an isotropic areal filter. Then, four direct methods for the solving approximating spline matrix are applied. Based on the profile filtering and areal filtering, the computational efficiency and accuracy are compared. The experimental results show that the improved square root method (LDLT decomposition) combines both computational efficiency and filtering precision, and is a good choice for solving the approximating spline matrix. Finally, six kinds of robust approximating spline filters are constructed. Taking the output value of robust Gaussian regression filter (RGRF) as reference, and the honing profile and step surface with deep valley characteristics were used as test surfaces to compare their robustness and iteration time. The experimental results show that the approximating spline filter based on the ADRF function has the shortest iteration times, while its roughness is close to the robust Gaussian regression filter.

Gabor and Maximum Response Filters with Random Forest Classifier for Face Recognition in the Wild

Research on face recognition has been evolving for decades. There are numerous approaches developed with highly desirable outcomes in constrained environments. In contrast, approaches to face recognition in an unconstrained environment where varied facial posing, occlusion, aging, and image quality still pose vast challenges. Thus, face recognition in the unconstrained environment still an unresolved problem. Many current techniques are not performed well when experimented in unconstrained databases. Additionally, most of the real-world application needs a good face recognition performance in the unconstrained environment. This paper presents a comprehensive process aimed to enhance the performance of face recognition in an unconstrained environment. This paper presents a face recognition system in an unconstrained environment. The fusion between Gabor filters and Maximum Response (MR) filters with Random Forest classifier is implemented in the proposed system. Gabor filters are a hybrid of Gabor magnitude filters and Oriented Gabor Phase Congruency (OGPC) filters. Gabor magnitude filters produce the magnitude response while the OGPC filters produce the phase response of Gabor filters. The MR filters contain the edge- and bar-anisotropic filter responses and isotropic filter responses. In the face features selection process, Monte Carlo Uninformative Variable Elimination Partial Least Squares Regression (MC-UVE-PLSR) is used to select the optimal face features in order to minimize the computational costs without compromising the accuracy of face recognition. Random Forests is used in the classification of the generated feature vectors. The algorithm performance is evaluated using two unconstrained facial image databases: Labelled Faces in the Wild (LFW) and Unconstrained Facial Images (UFI). The proposed technique used produces encouraging results in these evaluated databases in which it recorded face recognition rates that are comparable with other state-of-the-art algorithms.

Additional methods for the stable calculation of isotropic Gaussian filter coefficients: The case of a truncated filter kernel

The isotropic Gaussian filter is frequently used as a post-processing method for mitigating errors in Gravity Recovery and Climate Experiment (GRACE) time-variable gravity field solutions. It is known that the recurrent calculation of isotropic Gaussian filter coefficients in the spherical harmonic domain results in numerical instabilities. This issue has been recently resolved by Piretzidis & Sideris (Computers & Geosciences 133:104303) for the case of a global Gaussian filter. In this paper, we extend this work for the case of a regional Gaussian filter (i.e., a Gaussian filter with a truncated kernel). We show that instabilities also occur when the coefficients of a regional Gaussian filter are calculated using a conventional recurrence relation, and we provide methods for their proper treatment. We also briefly present some theoretical preliminaries related to recurrence relations and examine algorithms (i.e., initial value and boundary value algorithms) for their stable evaluation. Our analysis indicates that the initial value algorithms are ineffective for the calculation of regional Gaussian filter coefficients, contrary to the global Gaussian filter. The comparison of the boundary value algorithms shows that the Thomas and lower-upper (LU) decomposition algorithms are the most suitable for this case. Their main advantage is their insusceptibility to numerical limitations, such as overflow errors. The Thomas algorithm is also the most efficient in terms of computational speed.

Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification

Up to the present, an enormous number of advanced techniques have been developed to enhance and extract the spatially semantic information in hyperspectral image processing and analysis. However, locally semantic change, such as scene composition, relative position between objects, spectral variability caused by illumination, atmospheric effects, and material mixture, has been less frequently investigated in modeling spatial information. As a consequence, identifying the same materials from spatially different scenes or positions can be difficult. In this paper, we propose a solution to address this issue by locally extracting invariant features from hyperspectral imagery (HSI) in both spatial and frequency domains, using a method called invariant attribute profiles (IAPs). IAPs extract the spatial invariant features by exploiting isotropic filter banks or convolutional kernels on HSI and spatial aggregation techniques (e.g., superpixel segmentation) in the Cartesian coordinate system. Furthermore, they model invariant behaviors (e.g., shift, rotation) by the means of a continuous histogram of oriented gradients constructed in a Fourier polar coordinate. This yields a combinatorial representation of spatial-frequency invariant features with application to HSI classification. Extensive experiments conducted on three promising hyperspectral datasets (Houston2013 and Houston2018) demonstrate the superiority and effectiveness of the proposed IAP method in comparison with several state-of-the-art profile-related techniques. The codes will be available from the website: https://sites.google.com/view/danfeng-hong/data-code.

Diagnosis of Cataract using a Robust Algorithm for Telemedicine Applications

This project proposes and evaluates an algorithm to automatically detect cataract from colored images of adult human subjects. The methods currently available make use of DSLR (Digital Single Lens Reflex) cameras which are very expensive thereby, making the whole process expensive. The main objective of this project is to provide a robust and affordable alternative to the classic treatment method which adopts the above methods. In this project via an algorithm we aim to diagnose the presence of cataract from the true colour images of an eye. The algorithm proposed makes use of OpenCV for cataract screening based on textural features such as uniformity, intensity and standard deviation. These features are first computed and mapped using Data Mining techniques after consultation with an eye expert to define the basic threshold of screening system and later tested on real subjects in an eye clinic. Pre-processing includes conservative smoothing followed by image de-noising. The isotropic Gaussian filter is widely used as a low pass filter for image de-noising.Feature extraction is done after pre-processing to extract all the information for cataract detection from the eye’s pupil region. The extracted parameters were compared with the values obtained from an ophthalmologist to determine the presence of Cataract in the eye of the patient. Finally, a tele-ophthalmology model using our proposed system has been suggested, which confirms the telemedicine application of the proposed system.

Diagnosis of Cataract using a Robust Algorithm for Telemedicine Applications

This project proposes and evaluates an algorithm to automatically detect cataract from colored images of adult human subjects. The methods currently available make use of DSLR (Digital Single Lens Reflex) cameras which are very expensive thereby, making the whole process expensive. The main objective of this project is to provide a robust and affordable alternative to the classic treatment method which adopts the above methods. In this project via an algorithm we aim to diagnose the presence of cataract from the true colour images of an eye. The algorithm proposed makes use of OpenCV for cataract screening based on textural features such as uniformity, intensity and standard deviation. These features are first computed and mapped using Data Mining techniques after consultation with an eye expert to define the basic threshold of screening system and later tested on real subjects in an eye clinic. Pre-processing includes conservative smoothing followed by image de-noising. The isotropic Gaussian filter is widely used as a low pass filter for image de-noising.Feature extraction is done after pre-processing to extract all the information for cataract detection from the eye’s pupil region. The extracted parameters were compared with the values obtained from an ophthalmologist to determine the presence of Cataract in the eye of the patient. Finally, a tele-ophthalmology model using our proposed system has been suggested, which confirms the telemedicine application of the proposed system.