Computer-Aided Detection of COVID-19 from CT Images Based on Gaussian Mixture Model and Kernel Support Vector Machines Classifier.

There is a huge diversity of definitions of visually image segments, ranging from simple uniformly colored segments, textured segments, through symmetric patterns, and up to complex semantically meaningful objects. This diversity has led to a wide range of different approaches for image segmentation. In this paper we present a single unified framework for addressing this problem --- Segmentation by Composition. We define a good image segment as one which can be easily composed using its own pieces, but is difficult to compose using pieces from other parts of the image. This non-parametric approach captures a large diversity of segment types, yet requires no pre-definition or modelling of segment types, nor prior training. Based on this definition, we develop a segment extraction algorithm --- i.e., given a single point-of-interest, provide the best image segment containing that point. This induces a figure-ground image segmentation, which applies to a range of different segmentation tasks: single image segmentation, simultaneous co-segmentation of several images, and class-based segmentations.

This study presents two support vector machine (SVM) based models for forecasting hourly precipitation during tropical cyclone (typhoon) events. The two SVM-based models are the traditional Gaussian kernel SVMs (GSVMs) and the advanced wavelet kernel SVMs (WSVMs). A comparison between the fifth-generation Pennsylvania State University–National Center for Atmospheric Research (PSU–NCAR) Mesoscale Model (MM5) and statistical models, including SVM-based models and linear regressions (regression), was made in terms of performance of rainfall prediction at the Shihmen Reservoir watershed in Taiwan. Data from 73 typhoons affecting the Shihmen Reservoir watershed were included in the analysis. This study designed six attribute combinations with different lag times for the forecast target. The modified RMSE, bias, and estimated threat score (ETS) results were employed to assess the predicted outcomes. Results show that better attribute combinations for typhoon climatologic characteristics and typhoon precipitation predictions occurred at 0-h lag time with modified RMSE values of 0.288, 0.257, and 0.296 in GSVM, WSVM, and the regression, respectively. Moreover, WSVM having average bias and ETS values close to 1.0 gave better predictions than did the GSVM and regression models. In addition, Typhoons Zeb (1998) and Nari (2001) were selected for comparison between the MM5 model output and the developed statistical models. Results showed that the MM5 tended to overestimate the peak and cumulative rainfall amounts while the statistical models were inclined to yield underestimations.

Magnetic resonance images are relevant sources of information for detecting and diagnosing a large number of illnesses and abnormalities. Segmentation of digital images helps to classify the pixels in the different regions according to their intensity level. Segmentation of digital images implemented on magnetic resonance images can help experts to improve the performance of evaluations and make a correct differential diagnosis to indicate the appropriate treatment. This chapter proposes the use of MFO, SCA and SFO algorithms to search for 2, 3, 4, 5, 8, 16 and 32 threshold values using minimum cross entropy function to segment prostatic magnetic resonance images, and implementing statistical metrics like PSNR, SSIM, and FSIM to measure the quality of a segmented image, quantified and establish the proper comparison frame, so visual comparison is not enough. The approach is tested on a set of benchmark images to demonstrate that the segmentation of digital images can improve the detection of prostatic abnormalities or illnesses.KeywordsMoth-Flame Optimization Algorithm (MFO)Sine Cosine Optimization Algorithm (SCA)Sunflower Optimization Algorithm (SFO)Metaheuristic algorithmsOptimizationThresholding segmentationMagnetic resonance prostatic images

In crop disease image segmentation, traditional convolutional neural networks have the problem of low image accuracy. For this reason, this paper proposes a segmentation method that combines conditional random fields with segnet networks. First, input the training set in the data set into the segnet network for training, and obtain the initial segmentation result and the network with updated parameters; secondly, the image segmented by the segnet network is sent to the conditional random field in the form of pixels and classification vectors corresponding to the pixels At the same time, construct an energy function to represent the relative relationship between pixels, and then keep training; in order to get the conditional random field in the training set, you need to adjust and optimize the image segmented by the segnet network to get it; then in the verification set, the segnet network and the weight parameters of the conditional random field model are further adjusted and optimized to obtain the final conditional random field and segnet network; finally, the final conditional random field and segnet network are applied to the crop disease image segmentation. The test results show that compared with the Otsu threshold and Grabcut segmentation methods, the segmentation accuracy P, recall rate R, and comprehensive evaluation index F of this method are all the maximum, and the average processing time of a single image is 0.86 s; compared with pspnet and deeplab methods, Under the premise that the segmentation accuracy P, the recall rate R, and the comprehensive evaluation index F are basically unchanged, the average processing time of a single image is significantly reduced. The results show that the best comprehensive effect can be achieved by segmenting crop disease images in complex environments using the method in this paper.

Text segmentation in digital images is requisite for many image analysis and interpretation tasks. In this article, we have proposed an effective binarization method towards text segmentation in digital images. This method produces a number of connected components consisting of text as well as non-text. Next, it is required to identify the possible text components from the obtained connected components. Further, to distinguish between text and non-text components, a set of features are identified. Then, during training, we consider the two feature files namely text and non-text prepared by us. Here, K-Nearest Neighbour (K-NN) classifier is considered for the present two class classification problem. The experiments are based on ICDAR 2011 Born Digital Dataset. We have accomplished in binarization and as well as segmenting between text and non-text.

Comparison of hypospadias phenotype pixel segmentation to GMS score

This paper compares performances between Gaussian Mixture Model (GMM) classifier and polynomial classifier for text-independent speaker identification. The MFCC feature set has been used for this comparison. Experimental evaluation was conducted on the POLYCOST database with 130 speakers. The importance of the prior in the polynomial classifier has been discussed in detail. Results reveal that, the identification accuracy of the polynomial classifier strongly depends on the choice of prior. For proper prior selection the polynomial classifier can perform better than the GMM classifier.KeywordsSpeaker identificationGMM classifierPolynomial classifier

Ecological models require a large variety of variables in order to describe the biotic and abiotic conditions that define wildlife habitats and biotope distribution. Instead of providing this information using regular grids or categorical maps, geographic object-based image analysis allows to describe the land cover based on meaningful spatial regions which are closer to the natural habitats than regular grids and more flexible to the specific needs of models than categorical data. In the frame of the Lifewatch/Wallonia-Brussels project, we use GEOBIA to create a geographic object database closely related to the ecological concept of ecotope. Through an iterative process with ecological modellers, this database has been designed in order to define its key characteristics : it had to provide a quantitative description of the land cover within topographically relevant spatial regions and it integrates contextual information from different scales. The proof of concept of this new type of geographic database was done over the Wallon region in Belgium. This study area covers approximately 16800 square kilometers with a very fragmented landscape. A dataset including aerial photographs at 0.25 cm resolution and LIDAR at 0.8 pts/m has been provided by theWalloon region for the study. The data were resampled at 2m resolution for the purpose of the analysis. The data processing workflow includes three steps : pixel-based image classification, image segmentation and object-based integration. Pixel-based image classification consists in a supervised classification with the spectral values from the aerial photographs (NIR/Red/green/blue), the Digital Height Model extracted from the LIDAR and the intensity of the first LIDAR return. This yielded a classification into broadleaved trees, needleleaved trees, grass, bare soil, crop, pavement, building, water and shadows with more than 80% overal accuracy. The image segmentation approach is the main novelty of this research. In order to fit with the biotopes, image segments indeed had to take the type of slope into account. This was achieved by computing pseudo-hillshades for North-South andWest-East orientation and including those two files together with the spectral information from the aerial photographs. The result of this analysis is a set of topographically relevant ecotope delineation. The last step applied contextual decision rules to consistently aggregate the land cover information at the ecotope level and add more information from ancillary datasets.

Nowadays, the video coding standards for object based video coding and the tools for multimedia content description are available. Hence, we have powerful tools that can be used for content-based video coding, description, indexing and organization. In the past, it was difficult to extract higher level semantics, such as video objects, automatically. In this paper, we present a novel approach to moving object region detection. For this purpose, we developed a framework which applies bidirectional global motion estimation and compensation in order to identify potential foreground object regions. After spatial image segmentation, the results are assigned to image segments, and further diffused over the image region. This enables robust object region detection also in cases, where the investigated object does not move completely all the time. Finally, each image segment can be classified as being either situated in the foreground or in the background. Subsequent region merging delivers foreground object masks which can be used in order to define the region-of-attention for content based video coding, but also for contour based object classification.

Image segmentation is the process of partitioning a digital image into a set of homogeneous regions (according to some homogeneity criterion) to facilitate a subsequent higher-level analysis. In this context, the present paper proposes an unsupervised and graph-based method of image segmentation, which is driven by an application goal, namely, the generation of image segments associated with a user-defined and application-specific goal. A graph, together with a random grid of source elements, is defined on top of the input image. From each source satisfying a goal-driven predicate, called seed, a propagation algorithm assigns a cost to each pixel on the basis of similarity and topological connectivity, measuring the degree of association with the reference seed. Then, the set of most significant regions is automatically extracted and used to estimate a statistical model for each region. Finally, the segmentation problem is expressed in a Bayesian framework in terms of probabilistic Markov random field (MRF) graphical modeling. An ad hoc energy function is defined based on parametric models, a seed-specific spatial feature, a background-specific potential, and local-contextual information. This energy function is minimized through graph cuts and, more specifically, the alpha-beta swap algorithm, yielding the final goal-driven segmentation based on the maximum a posteriori (MAP) decision rule. The proposed method does not require deep a priori knowledge (e.g., labelled datasets), as it only requires the choice of a goal-driven predicate and a suited parametric model for the data. In the experimental validation with both magnetic resonance (MR) and synthetic aperture radar (SAR) images, the method demonstrates robustness, versatility, and applicability to different domains, thus allowing for further analyses guided by the generated products.

Recently it has been shown that min-cut algorithms can provide perceptually salient image segments when they are given appropriate proposals for source and sink regions. Here we explore the use of random walks and associated spectral embedding techniques for the automatic generation of suitable proposal regions. To do this, we first derive a mathematical connection between spectral embedding and anisotropic image smoothing kernels. We then use properties of the spectral embedding and the associated smoothing kernels to select multiple pairs of source and sink regions for min-cut. This typically provides an over-segmentation, and therefore region merging is used to form the final image segmentation. We demonstrate this process on several sample images.

Developing a treatment strategy that effectively prolongs the lives of people with brain tumors requires an accurate diagnosis of the condition. Therefore, improving the preoperative classification of meningiomas is a priority. Machine learning (ML) has made great strides thanks to the development of convolutional neural networks (CNNs) and computer-aided tumor detection systems. The deep convolutional layers automatically extract important and dependable information from the input space, in contrast to more traditional neural network layers. One recent and promising advancement in this field is ML. Still, there is a dearth of studies being carried out in this area. Therefore, starting with the analysis of magnetic resonance images, we have suggested in this research work a tried-and-tested and methodical strategy for real-time meningioma diagnosis by image segmentation using a very deep transfer learning CNN model or DNN model (VGG-16) with CUDA. Since the VGGNet CNN model has a greater level of accuracy than other deep CNN models like AlexNet, GoogleNet, etc., we have chosen to employ it. The VGG network that we have constructed with very small convolutional filters consists of 13 convolutional layers and 3 fully connected layers. Our VGGNet model takes in an sMRI FLAIR image input. The VGG's convolutional layers leverage a minimal receptive field, i.e., 3 × 3, the smallest possible size that still captures up/down and left/right. Moreover, there are also 1 × 1 convolution filters acting as a linear transformation of the input. This is followed by a ReLU unit. The convolution stride is fixed at 1 pixel to keep the spatial resolution preserved after convolution. All the hidden layers in our VGG network also use ReLU. A dataset consisting of 264 3D FLAIR sMRI image segments from three different classes (meningioma, tuberculoma, and normal) was employed. The number of epochs in the Sequential Model was set to 10. The Keras layers that we used were Dense, Dropout, Flatten, Batch Normalization, and ReLU. According to the simulation findings, our suggested model successfully classified all of the data in the dataset used, with a 99.0% overall accuracy. The performance metrics of the implemented model and confusion matrix for tumor classification indicate the model's high accuracy in brain tumor classification. The good outcomes demonstrate the possibility of our suggested method as a useful diagnostic tool, promoting better understanding, a prognostic tool for clinical outcomes, and an efficient brain tumor treatment planning tool. It was demonstrated that several performance metrics we computed using the confusion matrix of the previously used model were very good. Consequently, we think that the approach we have suggested is an important way to identify brain tumors.

In recent years, digital watermarking techniques have been proposed to protect the copyright of multimedia data. Different watermarking schemes have been suggested for images. This paper proposes a watermarking algorithm based on image segmentation and Discrete Cosine Transform (DCT). The image is first segmented using Expectation Maximization (EM) algorithm. For each segment, the image segment is subdivided into pixels blocks of size 8 times 8 (64 pixels), and zigzag reordered. The DCT of the block is then computed. Then, a pseudorandom sequence of real numbers is embedded in the DCT domain of each image segment. Different experiments are conducted to show the performance of the scheme under different types of attacks. The results show that our proposed watermark scheme is robust to common signal distortions, including geometric manipulations.

In this paper, we focus on the quantitative comparison of two-dimensional gel images in order to indicate the possible changes of the proteome in separate samples. The comparison of two or more separate gel images cannot be straightforward because it is hard to ensure the same experimental conditions for each experiment. The aim of our investigation was to increase the precision of quantitative validation of changes in proteome of analyzed biological tissue. Our work was divided into two parts: analysis of uncertainties during quantification of gel images prepared with different staining intensities, images with saturated protein spots and to propose an image processing technique to minimize these uncertainties. We proposed a SOM based clustering of watershed transformation based image segmentation result and separate comparison of protein spot intensities in each group. The experimental investigation showed, that the effective SOM size is 3×3 and background subtraction based on pixel intensities on image segment contour give less uncertainty comparing to alternative techniques.

Novelty detection in wildlife scenes through semantic context modelling