Search results for "Graphics"

showing 10 items of 1223 documents

An Alternative to Medial Axis for the 3D Reconstruction of Unorganized Set of Points Using Implicit Surfaces

2006

Rebuilding three-dimensional objects represented by a set of points is a classical problem in computer graphics. Multiple applications like medical imaging or industrial techniques require finding shape from scattered data. Therefore, the reconstruction of a set of points that represents a shape has been widely studied, depending on data source and reconstruction's objectives. This purpose of this paper is to provide an automatic reconstruction from an unorganized cloud describing an unknown shape in order to provide a solution that will allow to compute the object's volume and to deform it with constant volume. The main idea in this paper consists in filling the object's interior with an e…

Computer sciencebusiness.industryEquipotential surface3D reconstructionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMetaballsObject (computer science)Computer graphicsSet (abstract data type)Medial axisComputer visionArtificial intelligencebusinessConstant (mathematics)ComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Real-Time Human Pose Estimation from Body-Scanned Point Clouds

2015

International audience; This paper presents a novel approach to estimate the human pose from a body-scanned point cloud. To do so, a predefined skeleton model is first initialized according to both the skeleton base point and its torso limb obtained by Principal Component Analysis (PCA). Then, the body parts are iteratively clustered and the skeleton limb fitting is performed, based on Expectation Maximization (EM). The human pose is given by the location of each skeletal node in the fitted skeleton model. Experimental results show the ability of the method to estimate the human pose from multiple point cloud video sequences representing the external surface of a scanned human body; being r…

Computer sciencebusiness.industryHuman pose estimationPoint cloudComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]TorsoMissing data3D pose estimation[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]medicine.anatomical_structure[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Expectation–maximization algorithmPrincipal component analysismedicineComputer visionPoint (geometry)Artificial intelligencebusinessskeleton modelPoseComputingMethodologies_COMPUTERGRAPHICSpoint cloud
researchProduct

Three-dimensional Fuzzy Kernel Regression framework for registration of medical volume data

2013

Abstract In this work a general framework for non-rigid 3D medical image registration is presented. It relies on two pattern recognition techniques: kernel regression and fuzzy c-means clustering. The paper provides theoretic explanation, details the framework, and illustrates its application to implement three registration algorithms for CT/MR volumes as well as single 2D slices. The first two algorithms are landmark-based approaches, while the third one is an area-based technique. The last approach is based on iterative hierarchical volume subdivision, and maximization of mutual information. Moreover, a high performance Nvidia CUDA based implementation of the algorithm is presented. The f…

Computer sciencebusiness.industryImage registrationMutual informationMachine learningcomputer.software_genreFuzzy logicCUDANon-rigid registration Fuzzy regression Mutual information Interpolation GPU computingArtificial IntelligenceSignal ProcessingPattern recognition (psychology)Kernel regressionComputer Vision and Pattern RecognitionArtificial intelligenceData miningGeneral-purpose computing on graphics processing unitsCluster analysisbusinesscomputerSoftwareInterpolationPattern Recognition
researchProduct

New key based on tilted lenses for optical encryption

2016

A novel concept based on tilted spherical lenses for optical encryption using Lohmann’s type I systems is presented. The tilt angle of the spherical lenses is used as an encrypted key and the decryption performance is studied both qualitatively (visual image degradation) and quantitatively (mean squared error analysis) by numerical simulations. The paper presents a general mathematical framework in virtue of the dioptric power matrix formalism and oblique central refraction used in the optometry field. Computer simulations show that image information cannot be retrieved after a few degrees of tilt on both spherical lenses in the encryption system. In addition, a preliminary experiment is pr…

Computer sciencebusiness.industryMaterials Science (miscellaneous)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEncryption01 natural sciencesGeneralLiterature_MISCELLANEOUSIndustrial and Manufacturing EngineeringOptical encryption010309 optics03 medical and health sciences0302 clinical medicineOpticsComputer Science::Multimedia0103 physical sciences030221 ophthalmology & optometryHybrid cryptosystemBusiness and International ManagementbusinessComputingMethodologies_COMPUTERGRAPHICSComputer Science::Cryptography and SecurityApplied Optics
researchProduct

Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency

2018

In this work, we propose a convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes without having access to the reference. The proposed CNN architecture is fed by small patches selected carefully according to their level of saliency. To do so, the visual saliency of the 3D mesh is computed, then we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Afterward, the obtained views are split to obtain 2D small patches that pass through a saliency filter to select the most relevant patches. Experiments are conducted on two MVQ assessment databases, and the results show that the trained CNN achieves good rates in terms of corre…

Computer sciencebusiness.industryQuality assessmentDistortion (optics)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION020207 software engineeringPattern recognition02 engineering and technologyFilter (signal processing)Convolutional neural networkVisualizationSalience (neuroscience)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSaliency mapArtificial intelligencebusinessComputingMethodologies_COMPUTERGRAPHICSVisual saliency2018 25th IEEE International Conference on Image Processing (ICIP)
researchProduct

SVG rendering for internet imaging

2006

The SVG (scalable vector graphics) standard allows representing complex graphical scenes by a collection of graphic vectorial-based primitives, offering several advantages with respect to classical raster images such as: scalability, resolution independence, etc. In this paper we present a full comparison between some advanced raster to SVG algorithms: SWaterG, SVGenie, SVGWave and some commercial tools. SWaterG works by a watershed decomposition coupled with some ad-hoc heuristics, SVGenie and SVGWave use a polygonalization based respectively on data dependent and wavelet triangulation. The results obtained by SWaterG, SVGenie and SVGWave are satisfactory both in terms of perceptual measur…

Computer sciencebusiness.industrySVG triangulation Watershed waveletComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScalable Vector GraphicsWavelet transformcomputer.file_formatResolution independenceRendering (computer graphics)Computer graphics (images)ScalabilityComputer visionArtificial intelligenceRaster graphicsbusinesscomputer3D computer graphicsComputingMethodologies_COMPUTERGRAPHICSData compression
researchProduct

Stereoscopic 3D visualization of particle fields reconstructed from digital inline holograms

2010

Abstract Holography is a powerful tool as it codes information, e.g. on 3D positions in a particle field in a single 2D hologram. In digital holography, the holograms are recorded on a digital image sensor. It is a particular challenge to visualize a digital hologram's depth information, such that it can be understood intuitively while retaining the advantages of a numerical reconstruction. In this contribution it is suggested and demonstrated how a numerically constructed volume can be used to calculate stereoscopic views, which even in the case of non-diffuse illumination allow for an intuitive visualization of particles’ positions in 3D space.

Computer sciencebusiness.industryVolume (computing)HolographyStereoscopyAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic MaterialsVisualizationlaw.inventionDigital imageOpticsStereopsislawComputer graphics (images)Electrical and Electronic EngineeringImage sensorbusinessDigital holographyOptik
researchProduct

Adding Synthetic Detail to Natural Terrain Using a Wavelet Approach

2002

Terrain representation is a basic topic in the field of interactive graphics. The amount of data required for good quality terrain representation offers an important challenge to developers of such systems. For users of these applications the accuracy of geographical data is less important than their natural visual appearance. This makes it possible to mantain a limited geographical data base for the system and to extend it generating synthetic data.In this paper we combine fractal and wavelet theories to provide extra data which keeps the natural essence of actual information available. The new levels of detail(LOD) for the terrain are obtained applying an inverse Wavelet Transform (WT) to…

Computer sciencebusiness.industryWavelet transformImage processingTerraincomputer.software_genreFractal dimensionField (computer science)Set (abstract data type)Computer graphicsWaveletFractalComputer visionData miningArtificial intelligenceRepresentation (mathematics)businesscomputer
researchProduct

Guest Editorial Three-Dimensional Displays and Visualization

2010

THREE-DIMENSIONAL (3D) imaging and display is a natural concept for humans as it is a common vision attribute of our binocular vision, perception, and brain processing. However, until recently, our experiences have been mainly limited to the technologically inferior two-dimensional (2D) as evidenced from widespread use of 2D photography, cinema, and liquid crystal or LED-display for television, computer displays, etc.

Computer sciencebusiness.industrymedia_common.quotation_subjectPhotographyCondensed Matter PhysicsElectronic Optical and Magnetic MaterialsVisualizationMovie theaterComputer graphics (images)PerceptionNatural (music)Electrical and Electronic EngineeringbusinessBinocular visionmedia_commonJournal of Display Technology
researchProduct

Systems thinking and its contribution to understanding future designer thinking

2017

Design is changing in a radical way. The object of design is transforming from tangible objects into services and furthermore, into systems. Increasingly, new insights arise from the interfaces between diverse disciplines – such as art, science and technology – which through various discourses and paradigms have been specialized and driven apart. This discussion paper pinpoints the so-called systems thinkers, hybrid-people, whose methods and habits of work are constituted by the reconciliation of different disciplines. The article aims to bring more understanding to the kind of thinking that is needed in the complex and dynamic environment in which we create and use design today. This discu…

Computer sciencefuture designmedia_common.quotation_subjectmonialaisuusArts and Humanities (miscellaneous)Multidisciplinary approachHuman–computer interactionluovuusSystems thinkingsysteemiajattelucreativitymedia_common060201 languages & linguisticsta113systems thinking06 humanities and the artsCreativityComputer Graphics and Computer-Aided DesignObject (philosophy)0602 languages and literatureSystems engineeringSystematic processdesigner thinkingmultidisciplinaryCritical systems thinkingEuropean Academy of Design Conference
researchProduct