Search results for "vector"

showing 10 items of 2660 documents

Geometry control of the junction between two fractal curves

2012

International audience; The general objective of our work is to create a geometric modeller based on iterative processes. With this objective in mind, we have to provide tools that work with fractal objects in the same manner as with objects of classical topology. In this article we focus on the constructing of an intermediate curve between two other curves defined by different iterative construction processes. A similar problem often arises with subdivision surfaces, when the goal is to connect two surfaces with different subdivision masks. We start by dealing with curves, willing to later generalise our approach to surfaces. We formalise the problem with the Boundary Controlled Iterated F…

business.industry010102 general mathematics[INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR]Boundary (topology)Geometry[ INFO.INFO-GR ] Computer Science [cs]/Graphics [cs.GR]02 engineering and technology01 natural sciencesComputer Graphics and Computer-Aided DesignIndustrial and Manufacturing Engineering[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]Computer Science ApplicationsConnection (mathematics)FractalIterated function system0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSubdivision surface0101 mathematicsbusinessEigenvalues and eigenvectorsDifferential (mathematics)MathematicsSubdivisionComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Image difference detection under varying illumination based on vector space and correlations

2012

Abstract We propose two methods to detect differences in images independently of local changes of intensity. The methods are based on calculating geometrical operators when images are considered as vectors. Operators can be expressed in terms of correlations for the possibility of optical implementations. The methods are invariant to changes of the form af ( x , y ) +  b , where a and b are arbitrary unknown parameters that may vary over the image f ( x , y ). Computer simulations show that the method works well when the illumination model is satisfied. Results from real images taken with a web camera show the robustness of the method.

business.industry02 engineering and technologyReal image01 natural sciencesAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic Materials010309 opticsOpticsRobustness (computer science)0103 physical sciencesOptical correlator0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingElectrical and Electronic EngineeringInvariant (mathematics)businessAlgorithmMathematicsVector spaceOptik
researchProduct

Classification of persimmon fruit origin by near infrared spectrometry and least squares-support vector machines

2014

Abstract The main objective of this work has been the authentication by Fourier transform near infrared (FT-NIR) spectrometry of the origin of persimmon fruits cultivated in different regions of Spain. In order to achieve this goal, 166 persimmon samples from 7 different regions of Spain were analyzed by FT-NIR spectrometry. By splitting the spectral data in training and independent test sets, a classification model was built using least squares support vector machines chemometric technique. Orthogonal signal correction and principal component analysis were performed prior to conduct the classification strategy. The verified model was applied for the prediction of the origin of 50 samples f…

business.industryAnalytical chemistryPattern recognitionNear-Infrared SpectrometryMass spectrometryLeast squaresChemometricsSupport vector machinesymbols.namesakeFourier transformTest setPrincipal component analysissymbolsArtificial intelligencebusinessFood ScienceMathematicsJournal of Food Engineering
researchProduct

Alternative method for binary shape alignment of non-symmetrical shapes based on minimal enclosing box

2012

Proposed is a novel method based on the minimal enclosing box (MEB) to determine the canonical orientation associated with a three-dimensional binary shape. It is suggested that, when the shape has no clear distinctive features and two or more of the eigenvalues are similar, this method is more suitable than the commonly used method based on principal component analysis (PCA). An experiment is performed with shapes of human livers by measuring the degree on which a prototypical image (atlas) matches to a new shape after alignment by PCA, minimal area projection (MAP), and MEB showing that in this case MEB outperforms the usual PCA-based alignment method and also the MAP method.

business.industryAtlas (topology)Binary numberPattern recognitionComputer Science::Computational GeometryTopologyComputational geometryImage (mathematics)Minimum bounding boxPrincipal component analysisArtificial intelligenceElectrical and Electronic EngineeringbusinessProjection (set theory)Eigenvalues and eigenvectorsMathematicsElectronics Letters
researchProduct

Visible-NIR reflectance spectroscopy and manifold learning methods applied to the detection of fungal infections on citrus fruit

2015

Abstract The development of systems for automatically detecting decay in citrus fruit during quality control is still a challenge for the citrus industry. The feasibility of reflectance spectroscopy in the visible and near infrared (NIR) regions was evaluated for the automatic detection of the early symptoms of decay caused by Penicillium digitatum fungus in citrus fruit. Reflectance spectra of sound and decaying surface parts of mandarins cv. ‘Clemenvilla’ were acquired in two different spectral regions, from 650 nm to 1050 nm (visible–NIR) and from 1000 nm to 1700 nm (NIR), pointing to significant differences in spectra between sound and decaying skin for both spectral ranges. Three diffe…

business.industryChemistryDimensionality reductionFeature vectorNear-infrared spectroscopyNonlinear dimensionality reductionLinear discriminant analysisSammon mappingOpticsPrincipal component analysisbusinessSpectroscopyBiological systemFood Science
researchProduct

Modeling user preferences in content-based image retrieval: A novel attempt to bridge the semantic gap

2015

This paper is concerned with content-based image retrieval from a stochastic point of view. The semantic gap problem is addressed in two ways. First, a dimensional reduction is applied using the (pre-calculated) distances among images. The dimension of the reduced vector is the number of preferences that we allow the user to choose from, in this case, three levels. Second, the conditional probability distribution of the random user preference, given this reduced feature vector, is modeled using a proportional odds model. A new model is fitted at each iteration. The score used to rank the image database is based on the estimated probability function of the random preference. Additionally, so…

business.industryCognitive NeuroscienceFeature vectorDimensionality reductionPattern recognitionProbability density functionConditional probability distributionContent-based image retrievalcomputer.software_genreComputer Science ApplicationsWeightingArtificial IntelligenceArtificial intelligenceData miningbusinessImage retrievalcomputerSemantic gapMathematicsNeurocomputing
researchProduct

Fuzzy sigmoid kernel for support vector classifiers

2004

This Letter proposes the use of the fuzzy sigmoid function presented in (IEEE Trans. Neural Networks 14(6) (2003) 1576) as non-positive semi-definite kernel in the support vector machines framework. The fuzzy sigmoid kernel allows lower computational cost, and higher rate of positive eigenvalues of the kernel matrix, which alleviates current limitations of the sigmoid kernel.

business.industryCognitive NeurosciencePattern recognitionSigmoid functionFuzzy logicComputer Science ApplicationsSupport vector machineKernel methodArtificial IntelligencePolynomial kernelKernel embedding of distributionsRadial basis function kernelLeast squares support vector machineArtificial intelligencebusinessMathematicsNeurocomputing
researchProduct

WiHAR : From Wi-Fi Channel State Information to Unobtrusive Human Activity Recognition

2020

A robust and unobtrusive human activity recognition system is essential to a multitude of applications, such as health care, active assisted living, robotics, sports, and tele-immersion. Existing well-performing activity recognition methods are either vision- or wearable sensor-based. However, they are not fully passive. In this paper, we develop WiHAR—an unobtrusive Wi-Fi-based activity recognition system. WiHAR uses the Wi-Fi network interface card to capture the channel state information (CSI) data. These CSI data are effectively processed, and then amplitude and phase information is used to obtain the spectrogram. In the subsequent step, the time-variant mean Doppler shift (MDS) caused …

business.industryComputer science05 social sciencesDecision treeWearable computer050801 communication & media studies020206 networking & telecommunicationsComputingMilieux_LEGALASPECTSOFCOMPUTING02 engineering and technologyLinear discriminant analysisActivity recognitionSupport vector machine0508 media and communicationsChannel state information0202 electrical engineering electronic engineering information engineeringSpectrogramComputer visionArtificial intelligencebusinessVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550
researchProduct

Text Classification Using Novel “Anti-Bayesian” Techniques

2015

This paper presents a non-traditional “Anti-Bayesian” solution for the traditional Text Classification (TC) problem. Historically, all the recorded TC schemes work using the fundamental paradigm that once the statistical features are inferred from the syntactic/semantic indicators, the classifiers themselves are the well-established statistical ones. In this paper, we shall demonstrate that by virtue of the skewed distributions of the features, one could advantageously work with information latent in certain “non-central” quantiles (i.e., those distant from the mean) of the distributions. We, indeed, demonstrate that such classifiers exist and are attainable, and show that the design and im…

business.industryComputer scienceBayesian probabilityPattern recognitioncomputer.software_genreComputingMethodologies_PATTERNRECOGNITIONData miningArtificial intelligencebusinesscomputerClassifier (UML)Linear numberVector spaceQuantile
researchProduct

Head Pose Estimation for Sign Language Video

2013

We address the problem of estimating three head pose angles in sign language video using the Pointing04 data set as training data. The proposed model employs facial landmark points and Support Vector Regression learned from the training set to identify yaw and pitch angles independently. A simple geometric approach is used for the roll angle. As a novel development, we propose to use the detected skin tone areas within the face bounding box as additional features for head pose estimation. The accuracy level of the estimators we obtain compares favorably with published results on the same data, but the smaller number of pose angles in our setup may explain some of the observed advantage.

business.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSign language3D pose estimationMotion captureData setSupport vector machineMinimum bounding boxFace (geometry)Computer visionArtificial intelligencebusinessPose
researchProduct