Statistical Image Model Research Articles

SOFTWARE IMPLEMENTATION OF ALGORITHMS FOR SELECTING THE OUTLINES OF OBJECTS IMAGES IN INTELLECTUAL VIDEO SURVEILLANCE SYSTEMS

The rapid advancement in digital image acquisition and transmission technologies poses challenges in processing vast volumes of video information streams. Images serve as crucial sources of decision-making information across a wide range of tasks. Key objectives addressed by intelligent video surveillance systems include object identification, trajectory determination, object speed measurement, and real-time detection of critical events for securing premises. Among the primary operations in intelligent video surveillance systems is the extraction of object contours from images, as contours contain essential information for object recognition based on their shape. This approach excludes internal image points, significantly reducing the amount of processed information and enabling real-time image analysis. Contour analysis encompasses methods for selecting, describing, and processing image contours to describe, store, compare, and search for objects based on their external contours. This methodology effectively addresses fundamental challenges in pattern recognition, such as transferring, rotating, and scaling object images. The paper discusses prominent contour analysis methods and presents software implementations of algorithms for extracting object outlines in intelligent video surveillance systems. A promising future direction involves synthesizing algorithms that extract object contours using a two-scale statistical image model.

The Relationship between Land Use Changes in the Increase of Runoff in the Gorgan River Watershed Using Satellite Image Data and Statistical Models

The Relationship between Land Use Changes in the Increase of Runoff in the Gorgan River Watershed Using Satellite Image Data and Statistical Models

A Fast, Robust Method for Quantitative Assessment of Collagen Fibril Architecture from Transmission Electron Micrographs.

Collagen is the most abundant protein in mammals; it exhibits a hierarchical organization and provides structural support to a wide range of soft tissues, including blood vessels. The architecture of collagen fibrils dictates vascular stiffness and strength, and changes therein can contribute to disease progression. While transmission electron microscopy (TEM) is routinely used to examine collagen fibrils under normal and pathological conditions, computational tools that enable fast and minimally subjective quantitative assessment remain lacking. In the present study, we describe a novel semi-automated image processing and statistical modeling pipeline for segmenting individual collagen fibrils from TEM images and quantifying key metrics of interest, including fibril cross-sectional area and aspect ratio. For validation, we show first-of-their-kind illustrative results for adventitial collagen in the thoracic aorta from three different mouse models.

BayeSeg: Bayesian modeling for medical image segmentation with interpretable generalizability.

Due to the cross-domain distribution shift aroused from diverse medical imaging systems, many deep learning segmentation methods fail to perform well on unseen data, which limits their real-world applicability. Recent works have shown the benefits of extracting domain-invariant representations on domain generalization. However, the interpretability of domain-invariant features remains a great challenge. To address this problem, we propose an interpretable Bayesian framework (BayeSeg) through Bayesian modeling of image and label statistics to enhance model generalizability for medical image segmentation. Specifically, we first decompose an image into a spatial-correlated variable and a spatial-variant variable, assigning hierarchical Bayesian priors to explicitly force them to model the domain-stable shape and domain-specific appearance information respectively. Then, we model the segmentation as a locally smooth variable only related to the shape. Finally, we develop a variational Bayesian framework to infer the posterior distributions of these explainable variables. The framework is implemented with neural networks, and thus is referred to as deep Bayesian segmentation. Quantitative and qualitative experimental results on prostate segmentation and cardiac segmentation tasks have shown the effectiveness of our proposed method. Moreover, we investigated the interpretability of BayeSeg by explaining the posteriors and analyzed certain factors that affect the generalization ability through further ablation studies. Our code is released via https://zmiclab.github.io/projects.html.

Technical note: MAMBA-Multi-pAradigM voxel-Based Analysis: A computational cookbot.

Voxel-Based (VB) analysis embraces a multifaceted ensemble of sophisticated techniques, lying at the boundary between image processing and statistical modeling, that allow for a frequentist inference of pathophysiological properties anchored to an anatomical reference. VB methods has been widely adopted in neuroimaging studies and, more recently, they are gaining momentum in radiation oncology research. However, the price for the power of VB analysis is the complexity of the underlying mathematics and algorithms. In this paper, we present the Multi-pAradigM voxel-Based Analysis (MAMBA) toolbox, which is intended for a flexible application of VB analysis in a wide variety of scenarios in medical imaging and radiation oncology. The MAMBA toolbox is implemented in Matlab. It provides open-source functions to compute VB statistical models of the input data, according to a great variety of regression schemes, and to derive VB maps of the observed significance level, performing a non-parametric permutation inference. The toolbox allows for including VB and global outcomes, as well as an arbitrary amount of VB and global Explanatory Variables (EVs). In addition, the Matlab Parallel Computing Toolbox is exploited to take advantage of the perfect parallelizability of most workloads. The use of MAMBA was demonstrated by means of several realistic examples on a synthetic dataset mimicking a radiation oncology scenario. MAMBA is an open-source toolbox, freely available for academic and non-commercial purposes. It is designed to make state-of-the-art VB analysis accessible to research scientists without the programming resources needed to build from scratch their own software solutions. At the same time, the source code is handed out for more experienced users to complement their own tools, also customizing user-defined models. MAMBA guarantees high generality and flexibility in the design of the statistical models, significantly expanding on the features of available free tools for VB analysis. The presented toolbox aims at increasing the reach of VB studies as well as the sharing of research results.

Bayesian Image Super-Resolution With Deep Modeling of Image Statistics.

Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity priors. Concretely, first we consider an ideal image as the sum of a smoothness component and a sparsity residual, and model real image degradation including blurring, downscaling, and noise corruption. Then, we develop a variational Bayesian approach to infer their posteriors. Finally, we implement the variational approach for single image super-resolution (SISR) using deep neural networks, and propose an unsupervised training strategy. The experiments on three image restoration tasks, i.e., ideal SISR, realistic SISR, and real-world SISR, demonstrate that our method has superior model generalizability against varying noise levels and degradation kernels and is effective in unsupervised SISR. The code and resulting models are released via https://zmiclab.github.io/projects.html.

Image Desaturation for SDO/AIA Using Mixed Convolution Network

The Atmospheric Imaging Assembly (AIA) onboard the Solar Dynamics Observatory (SDO) provides full-disk solar images with high temporal cadence and spatial resolution over seven extreme ultraviolet (EUV) wave bands. However, as violent solar flares happen, images captured in EUV wave bands may have saturation in active regions, resulting in signal loss. In this paper, we propose a deep learning model to restore the lost signal in saturated regions by referring to both unsaturated/normal regions within a solar image and statistical probability model of massive normal solar images. The proposed model, namely mixed convolution network (MCNet), is established over conditional generative adversarial network (GAN) and the combination of partial convolution (PC) and validness migratable convolution (VMC). These two convolutions were originally proposed for image inpainting. In addition, they are implemented only on unsaturated/valid pixels, followed by certain compensation to compensate the deviation of PC/VMC relative to normal convolution. Experimental results demonstrate that the proposed MCNet achieves favorable desaturated results for solar images and outperforms the state-of-the-art methods both quantitatively and qualitatively.

Robust Rayleigh Regression Method for SAR Image Processing in Presence of Outliers

The presence of outliers (anomalous values) in synthetic aperture radar (SAR) data and the misspecification in statistical image models may result in inaccurate inferences. To avoid such issues, the Rayleigh regression model based on a robust estimation process is proposed as a more realistic approach to model this type of data. This article aims at obtaining Rayleigh regression model parameter estimators robust to the presence of outliers. The proposed approach considered the weighted maximum likelihood method and was submitted to numerical experiments using simulated and measured SAR images. Monte Carlo simulations were employed for the numerical assessment of the proposed robust estimator performance in finite signal lengths, their sensitivity to outliers, and the breakdown point. For instance, the nonrobust estimators show a relative bias value 65-fold larger than the results provided by the robust approach in corrupted signals. In terms of sensitivity analysis and break down point, the robust scheme resulted in a reduction of about 96% and 10%, respectively, in the mean absolute value of both measures, in compassion to the nonrobust estimators. Moreover, two SAR datasets were used to compare the ground type and anomaly detection results of the proposed robust scheme with competing methods in the literature.

A Hierarchical Gamma Mixture Model Toward Hidden Markov Random Field for High-Resolution SAR Image Segmentation

Accurately modeling the distributions of spectral intensities is an effective way to obtain accurate segmentation results. Existing mixture models mostly fail to establish accurate statistical models of high-resolution SAR images due to the complex statistical features of their spectral intensities. We propose a hierarchical gamma mixture model (HGaMM)-based high-resolution SAR images segmentation algorithm. In the proposed algorithm, a statistical model for SAR images is built using HGaMM, which can model heavy-tailed, asymmetric, multimodal, or flat distributions with its hierarchical structure. The algorithm allows for the effective utilization of spectral intensity information required for image segmentation. The HGaMM consists of several components that serve as the first layer, and several elements under each component serve as the second layer. The component weight is constructed using posterior probabilities of local pixels aimed at reducing noise effects. The segmentation model can then be established by the Bayesian theorem. A new expectation maximization/adding or deleting Markov chain Monte Carlo (EM/ADMCMC) is incorporated to implement parameter estimation and determine the optimum number of components. Several experiments were implemented on simulated and real high-resolution SAR images to evaluate the applicability and efficiency of the proposed approach. The experimental results show that the proposed HGaMM algorithm outperforms traditional algorithms and can obtain accurate results.

A low light natural image statistical model for joint contrast enhancement and denoising

We study the problem of joint low light image contrast enhancement and denoising using a statistical approach. The low light natural image in the band pass domain is modeled by statistically relating a Gaussian scale mixture model for the pristine image, to the low light image, through a detail loss coefficient and Gaussian noise. The detail loss coefficient is statistically described using a posterior distribution with respect to its estimate based on a prior contrast enhancement algorithm. We then design our low light enhancement and denoising (LLEAD) method by computing the minimum mean squared error estimate of the pristine image band pass coefficients. We create the Indian Institute of Science low light image dataset of well-lit and low light image pairs to learn the model parameters and evaluate our enhancement method. We show through extensive experiments on multiple datasets that our method helps better enhance the contrast while simultaneously controlling the noise when compared to other state of the art joint contrast enhancement and denoising methods.

Ridgelet-Nets With Speckle Reduction Regularization for SAR Image Scene Classification

With powerful feature representations, convolutional neural networks (CNNs) have produced tremendous achievements in image classification tasks and, typically, entail millions of labeled samples to train massive parameters. However, the sample labeling of synthetic aperture radar (SAR) images is extremely difficult, especially pixelwise labels, and has, sometimes, required field trips to accomplish labeling. Moreover, the inherent speckle noise may weaken the ability of networks to extract effective features from SAR images. In this article, we address these issues by labeling a few patchwise samples and propose Ridgelet-Nets with speckle reduction regularization for SAR image scene classification by combining deep learning with multiscale geometric analysis and statistical modeling of SAR images. First, we design Ridgelet-Nets with convolutional kernels constructed by ridgelet filters to reduce the training parameters and learn more discriminative features. Then, we embed speckle reduction regularization in the Ridgelet-Nets to restrain the influence of speckle noise and smooth the classification maps, in which the prior information of SAR image statistical modeling is introduced. Finally, we propose an adaptive SAR image scene classification framework based on an extended hierarchical visual semantic model, considering the differences in the structures and spatial relationships of different regions in the SAR images, particularly large-scale and complex scenes. Experimental results on real SAR images demonstrate that the proposed framework can achieve preferable classification performance using very limited labeled samples.

Framework for Machine Learning of CT and PET Radiomics to Predict Local Failure after Radiotherapy in Locally Advanced Head and Neck Cancers.

Context:Cancer Radiomics is an emerging field in medical imaging and refers to the process of converting routine radiological images that are typically qualitatively interpreted to quantifiable descriptions of the tumor phenotypes and when combined with statistical analytics can improve the accuracy of clinical outcome prediction models. However, to understand the radiomic features and their correlation to molecular changes in the tumor, first, there is a need for the development of robust image analysis methods, software tools and statistical prediction models which is often limited in low- and middle-income countries (LMIC).Aims:The aim is to build a framework for machine learning of radiomic features of planning computed tomography (CT) and positron emission tomography (PET) using open source radiomics and data analytics platforms to make it widely accessible to clinical groups. The framework is tested in a small cohort to predict local disease failure following radiation treatment for head-and-neck cancer (HNC). The predictors were also compared with the existing Aerts HNC radiomics signature.Settings and Design:Retrospective analysis of patients with locally advanced HNC between 2017 and 2018 and 31 patients with both pre- and post-radiation CT and evaluation PET were selected.Subjects and Methods:Tumor volumes were delineated on baseline PET using the semi-automatic adaptive-threshold algorithm and propagated to CT; PyRadiomics features (total of 110 under shape/intensity/texture classes) were extracted. Two feature-selection methods were tested for model stability. Models were built based on least absolute shrinkage and selection operator-logistic and Ridge regression of the top pretreatment radiomic features and compared to Aerts' HNC-signature. Average model performance across all internal validation test folds was summarized by the area under the receiver operator curve (ROC).Results:Both feature selection methods selected CT features MCC (GLCM), SumEntropy (GLCM) and Sphericity (Shape) that could predict the binary failure status in the cross-validated group and achieved an AUC >0.7. However, models using Aerts' signature features (Energy, Compactness, GLRLM-GrayLevelNonUniformity and GrayLevelNonUniformity-HLH wavelet) could not achieve a clear separation between outcomes (AUC = 0.51–0.54).Conclusions:Radiomics pipeline included open-source workflows which makes it adoptable in LMIC countries. Additional independent validation of data is crucial for the implementation of radiomic models for clinical risk stratification.

Synthetic Aperture Radar Image Statistical Modeling: Part Two-Spatial Correlation Models and Simulation

Following on the first part of our review of synthetic aperture radar (SAR) image statistical modeling [1], which concerns single-pixel statistical models, this article extends our discussion to spatial correlation analysis, focusing on SAR spatial correlation models and SAR clutter simulation methods. Two types of spatial correlation models, the product model and the coherent scatterer model, are summarized: the first considers correlation characteristics from the image itself while the second analyzes spatial correlation stemming from the underlying scatterer and the physical imaging process. In addition, we review four spatially correlated clutter simulation methods based on two classical distributions ( K and G 0): a product model-based method, an inverse transform method (ITM)-based approach, a coherent scatterer model-based technique, and the generalized Gaussian coherent scatterer ( GGCS ) approach. We discuss the advantages and disadvantages of these models and methods and provide references for further research into the statistical modeling of SAR images.

Synthetic Aperture Radar Image Statistical Modeling: Part One-Single-Pixel Statistical Models

With the rapid development of spaceborne synthetic aperture radar (SAR) technology and the acquisition of a large volume of SAR images, SAR image interpretation has become an urgent and difficult research topic. SAR image statistical modeling is one of the theoretical foundations for SAR image interpretation. It is of great value for the in-depth analysis of SAR images. This article reviews the major developments of SAR image statistical modeling since its beginning, including more than 20 statistical distributions of eight statistical models, and gives their derivations and expressions, which can be used as a basic reference for the statistical modeling of SAR images (see Notations and Definitions).

Automatic detection of venous air embolism using transesophageal echocardiography in patients undergoing neurological surgery in the semi-sitting position: a pilot study

Neurological surgery in the semi-sitting position is linked with a pronounced incidence of venous air embolism (VAE) which can be fatal and therefore requires continuous monitoring. Transesophageal echocardiography (TEE) provides a high sensitivity for the intraoperative detection of VAE; however, continuous monitoring with TEE requires constant vigilance by the anaesthesiologist, which cannot be ensured during the entire surgical procedure. We implemented a fully automatic VAE detection system for TEE based on a statistical model of the TEE images. In the sequence of images, the cyclic heart activity is regarded as a quasi-periodic process, and air bubbles are detected as statistical outliers. The VAE detection system was evaluated by means of receiver operating characteristic (ROC) curves using a data set consisting of 155.14 h of intraoperatively recorded TEE video and a manual classification of periods with visible VAE. Our automatic detection system accomplished an area under the curve (AUC) of 0.945 if all frames with visible VAE were considered as detection target, and an AUC of 0.990 if frames with the least severe optical grade of VAE were excluded from the analysis. Offline-review of the recorded TEE videos showed that short embolic events (≤ 2 min) may be overseen when monitoring TEE video manually. Automatic detection of VAE is feasible and could provide significant support to anaesthesiologists in clinical practice. Our proposed algorithm might possibly even offer a higher sensitivity compared to manual detection. The specificity, however, requires improvement to be acceptable for practical application. Trial Registration: German Clinical Trials Register (DRKS00011607).

Elliptic shape prior for object 2D-3D pose estimation using circular feature

Many objects in real world have circular feature. It is a difficult task to obtain the 2D-3D pose estimation using circular feature in challenging scenarios. This paper proposes a method to incorporate elliptic shape prior for object pose estimation using a level set method. The relationship between the projection of the circular feature of a 3D object and the signed distance function corresponding to it is analyzed to yield a 2D elliptic shape prior. The method employs the combination of the grayscale histogram, the intensities of edge, and the smoothness distribution as main image feature descriptors that define the image statistical measure model. The elliptic shape prior combined with the image statistical measure energy model drives the elliptic shape contour to the projection of the circular feature of the 3D object with the current pose into the image plane. These works effectively reduce the impacts of the challenging scenarios on the pose estimate results. In addition, the method utilizes particle filters that take into account the motion dynamics of the object among scene frames, and this work provides the robust method for object 2D-3D pose estimation using circular feature in a challenging environment. Various numerical experiments are illustrated to show the performance and advantages of the proposed method.

An Unsupervised Iris Based Biometric System with Inherent Feature Thresholding

This paper provides a general indication of the existing approaches rely on basic factor (i.e. extraction of iris information, affine transform, and distance matrix) as input. An essential factor in effective design of IRIS based biometric approach is the accuracy with which the model can estimate a region of interest (i.e. IRIS) within constraints and unforeseen issues, which can be very problematical but need of the hour. We introduced a new IRIS based biometric system that incorporates various factors that takes complete information of eye for developing the feature set (digest) while affine transforms are not incorporated while the three sets distance measure is incepted to enhance accuracy. The algorithm-based size of template, functionality of distance measure and/or scope, methods and/or function of application through well-defined scientific and statistical principles. Unfortunately, the accuracy of the existing approaches is limited despite the large scale of experience with several improvements based on digital image processing and statistical models. Henceforth, we incorporated several texture analysis algorithms with computing techniques along with several parametric enhancement constraints to ensure the feasibility, effectiveness and efficiency of the proposed framework in comparison with the existing methods.

Sparse Domain Gaussianization for Multi-Variate Statistical Modeling of Retinal OCT Images

In this paper, a multivariate statistical model that is suitable for describing Optical Coherence Tomography (OCT) images is introduced. The proposed model is comprised of a multivariate Gaussianization function in sparse domain. Such an approach has two advantages, i.e. 1) finding a function that can effectively transform the input - which is often not Gaussian - into normally distributed samples enables the reliable application of methods that assume Gaussianity, 2) although multivariate Gaussianization in spatial domain is a complicated task and rarely results in closed-form analytical model, by transferring data to sparse domain, our approach facilitates multivariate statistical modeling of OCT images. To this end, a proper multivariate probability density function (pdf) which considers all three properties of OCT images in sparse domains (i.e. compression, clustering, and persistence properties) is designed and the proposed sparse domain Gaussianization framework is established. Using this multivariate model, we show that the OCT images often follow a 2-component multivariate Laplace mixture model in the sparse domain. To evaluate the performance of the proposed model, it is employed for OCT image denoising in a Bayesian framework. Visual and numerical comparison with previous prominent methods reveals that our method improves the overall contrast of the image, preserves edges, suppresses background noise to a desirable amount, but is less capable of maintaining tissue texture. As a result, this method is suitable for applications where edge preservation is crucial, and a clean noiseless image is desired.

Group-Based Sparse Representation Based on lp -Norm Minimization for Image Inpainting

As a powerful statistical image modeling technique, sparse representation has been successfully applied in various image restoration applications. Most traditional methods depend on ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm optimization and patch-based sparse representation models. However, these methods have two limits: high computational complexity and the lack of the relationship among patches. To solve the above problems, we choose the group-based sparse representation models to simplify the computing process and realize the nonlocal self-similarity of images by designing the adaptive dictionary. Meanwhile, we utilize Ipnorm minimization to solve nonconvex optimization problems based on the weighted Schatten p-norm minimization, which can make the optimization model more flexible. Experimental results on image inpainting show that the proposed method has a better performance than many current state-of-the-art schemes, which are based on the pixel, patch, and group respectively, in both peak signal-to-noise ratio and visual perception.

A Sensing and Tracking Algorithm for Multiple Frequency Line Components in Underwater Acoustic Signals.

Reliable and efficient sensing and tracking of multiple weak or time-varying frequency line components in underwater acoustic signals is the topic of this paper. We propose a method for automatic detection and tracking of multiple frequency lines in lofargram based on hidden Markov model (HMM). Instead of being directly subjected to frequency line tracking, the whole lofargram is first segmented into several sub-lofargrams. Then, the sub-lofargrams suspected to contain frequency lines are screened. In these sub-lofargrams, the HMM-based method is used for detection of multiple frequency lines. Using image stitching and statistical model method, the frequency lines with overlapping parts detected by different sub-lofargrams are merged to obtain the final detection results. The method can effectively detect multiple time-varying frequency lines of underwater acoustic signals while ensuring the performance under the condition of low signal-to-noise ratio (SNR). It can be concluded that the proposed algorithm can provide better multiple frequency lines sensing ability while greatly reducing the amount of calculations and providing potential techniques for feature sensing and tracking processing of unattended equipment such as sonar buoys and submerged buoys.