Search results for "Segmentation"

showing 10 items of 674 documents

Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR

2021

In medical image segmentation, several studies have used Bayesian neural networks to segment and quantify the uncertainty of the images. These studies show that there might be an increased epistemic uncertainty in areas where there are semantically and visually challenging pixels. The uncertain areas of the image can be of a great interest as they can possibly indicate the regions of incorrect segmentation. To leverage the uncertainty information, we propose a segmentation model that incorporates the uncertainty into its learning process. Firstly, we generate the uncertainty estimate (sample variance) using Monte-Carlo dropout during training. Then we incorporate it into the loss function t…

PixelCalibration (statistics)business.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognitionImage segmentationLeverage (statistics)SegmentationSample varianceArtificial intelligenceUncertainty quantificationbusinessDropout (neural networks)
researchProduct

A class-separability-based method for multi/hyperspectral image color visualization

2010

In this paper, a new color visualization technique for multi- and hyperspectral images is proposed. This method is based on a maximization of the perceptual distance between the scene endmembers as well as natural constancy of the resulting images. The stretched CMF principle is used to transform reflectance into values in the CIE L*a*b* colorspace combined with an a priori known segmentation map for separability enhancement between classes. Boundaries are set in the a*b* subspace to balance the natural palette of colors in order to ease interpretation by a human expert. Convincing results on two different images are shown.

PixelComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPalette (computing)Hyperspectral imagingImage segmentationColor spaceVisualizationSegmentationComputer visionArtificial intelligencebusinessSubspace topology2010 IEEE International Conference on Image Processing
researchProduct

A Clustering Approach to texture Classification

1988

In the paper a clustering technique to segment an image in to “homogeneous” regions is studied. The homogeneity of each region is evaluated by means of a “proximity function” computed between the pixels. The main result of such approach is that no-histogramming is required in order to perform segmentation. Possibilistic and probabilistic approaches are, also, combined to evaluate the significativity of the computed regions.

PixelComputer sciencebusiness.industryFeature vectorHomogeneity (statistics)Correlation clusteringComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONProbabilistic logicPattern recognitionImage textureComputer Science::Computer Vision and Pattern RecognitionSegmentationArtificial intelligenceCluster analysisbusiness
researchProduct

A Comparative Study on Feature Selection for Retinal Vessel Segmentation Using FABC

2009

This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.

PixelSettore INF/01 - InformaticaComputer sciencebusiness.industryFeature vectorRetinal images vessel segmentation AdaBoost classifier feature selection.ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognitionFeature selectionFeature (computer vision)SegmentationComputer visionArtificial intelligenceHeuristicsbusinessFeature detection (computer vision)
researchProduct

Image Colorization Method Using Texture Descriptors and ISLIC Segmentation

2017

We present a new colorization method to assign color to a grayscale image based on a reference color image using texture descriptors and Improved Simple Linear Iterative Clustering (ISLIC). Firstly, the pixels of images are classified using Support Vector Machine (SVM) according to texture descriptors, mean luminance, entropy, homogeneity, correlation, and local binary pattern (LBP) features. Then, the grayscale image and the color image are segmented into superpixels, which are obtained by ISLIC to produce more uniform and regularly shaped superpixels than those obtained by SLIC, and the classified images are further post-processed combined with superpixles for removing erroneous classific…

Pixelbusiness.industryColor imageLocal binary patternsComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationPattern recognitionImage segmentationGrayscaleImage textureComputer Science::Computer Vision and Pattern RecognitionArtificial intelligencebusinessCluster analysisComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Variational multiframe restoration of images degraded by noisy (stochastic) blur kernels

2013

This article introduces and explores a class of degradation models in which an image is blurred by a noisy (stochastic) point spread function (PSF). The aim is to restore a sharper and cleaner image from the degraded one. Due to the highly ill-posed nature of the problem, we propose to recover the image given a sequence of several observed degraded images or multiframes. Thus we adopt the idea of the multiframe approach introduced for image super-resolution, which reduces distortions appearing in the degraded images. Moreover, we formulate variational minimization problems with the robust (local or nonlocal) L^1 edge-preserving regularizing energy functionals, unlike prior works dealing wit…

Point spread functionSequenceMathematical optimizationApplied MathematicsComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION010103 numerical & computational mathematics02 engineering and technology01 natural sciencesImage (mathematics)Computational MathematicsComputer Science::Computer Vision and Pattern Recognition0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSegmentationMinification0101 mathematicsAlgorithmEnergy (signal processing)Image restorationDegradation (telecommunications)MathematicsJournal of Computational and Applied Mathematics
researchProduct

Combining Real-Time Segmentation and Classification of Rehabilitation Exercises with LSTM Networks and Pointwise Boosting

2020

Autonomous biofeedback tools in support of rehabilitation patients are commonly built as multi-tier pipelines, where a segmentation algorithm is first responsible for isolating motion primitives, and then classification can be performed on each primitive. In this paper, we present a novel segmentation technique that integrates on-the-fly qualitative classification of physical movements in the process. We adopt Long Short-Term Memory (LSTM) networks to model the temporal patterns of a streaming multivariate time series, obtained by sampling acceleration and angular velocity of the limb in motion, and then we aggregate the pointwise predictions of each isolated movement using different boosti…

PointwiseMultivariate statisticsBoosting (machine learning)Rehabilitationbusiness.industryComputer sciencemedicine.medical_treatmentmedicineSegmentationPattern recognitionGeneral MedicineArtificial intelligencebusinessProceedings of the AAAI Conference on Artificial Intelligence
researchProduct

Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography.

2019

Abstract In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then…

Positron emission tomographyComputer scienceInitializationMedicine (miscellaneous)Context (language use)Imaging phantomActive contour algorithm03 medical and health sciences0302 clinical medicineRegion of interestArtificial IntelligenceNeoplasmsmedicineHumansSegmentation030304 developmental biologyRetrospective Studies0303 health sciencesActive contour modelDiscriminant analysimedicine.diagnostic_testbusiness.industryDiscriminant AnalysisPattern recognitionLinear discriminant analysisPositron emission tomographyBiological target volume segmentationPositron-Emission TomographyArtificial intelligencebusiness030217 neurology & neurosurgeryAlgorithmsArtificial intelligence in medicine
researchProduct

A probabilistic framework for automatic prostate segmentation with a statistical model of shape and appearance

2011

International audience; Prostate volume estimation from segmented prostate contours in Trans Rectal Ultrasound (TRUS) images aids in diagnosis and treatment of prostate diseases, including prostate cancer. However, accurate, computationally efficient and automatic segmentation of the prostate in TRUS images is a challenging task owing to low Signal-To-Noise-Ratio (SNR), speckle noise, micro-calcifications and heterogeneous intensity distribution inside the prostate region. In this paper, we propose a probabilistic framework for propagation of a parametric model derived from Principal Component Analysis (PCA) of prior shape and posterior probability values to achieve the prostate segmentatio…

Posterior probability030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicineExpectation–maximization algorithm[ INFO.INFO-TI ] Computer Science [cs]/Image ProcessingActive Appearance Model.Computer visionMathematicsbusiness.industryBayes ClassificationProbabilistic logicStatistical modelSpeckle noisePattern recognitionImage segmentationProstate SegmentationExpectationMaximizationActive appearance modelActive Appearance Model[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV][INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Parametric modelArtificial intelligencebusiness030217 neurology & neurosurgery
researchProduct

Preoperative Planning for Guidewires Employing Shape-Regularized Segmentation and Optimized Trajectories

2019

Upcoming robotic interventions for endovascular procedures can significantly reduce the high radiation exposure currently endured by surgeons. Robotically driven guidewires replace manual insertion and leave the surgeon the task of planning optimal trajectories based on segmentation of associated risk structures. However, such a pipeline brings new challenges. While Deep learning based segmentation such as U-Net can achieve outstanding Dice scores, it fails to provide suitable results for trajectory planning in annotation scarce environments. We propose a preoperative pipeline featuring a shape regularized U-Net that extracts coherent anatomies from pixelwise predictions. It uses Rapidly-ex…

Preoperative planningComputer sciencebusiness.industryDeep learningPipeline (computing)DiceMachine learningcomputer.software_genreTask (project management)Convex optimizationSegmentationArtificial intelligenceMotion planningbusinesscomputer
researchProduct