Search results for "Computer Science::Computer Vision and Pattern Recognition"

showing 10 items of 193 documents

Estimation of fibre orientation from digital images

2001

In this paper, estimation of fibre orientation is studied for fibre systems observable as a blurred greyscale image. The estimation method is based on scaled variograms observed along a set of sampling lines in different directions. The parameters of the orientation distribution are obtained numerically. Simulated data are used to study the statistical properties of the method.

Acoustics and UltrasonicsMaterials Science (miscellaneous)General MathematicsGrayscaleSet (abstract data type)Digital imageimage analysisRadiology Nuclear Medicine and imagingComputer visionInstrumentationMathematicslcsh:R5-920Boolean modelbusiness.industryOrientation (computer vision)lcsh:MathematicsSampling (statistics)Boolean modelObservablesimulationlcsh:QA1-939Distribution (mathematics)fibre orientationdigitizationComputer Science::Computer Vision and Pattern RecognitionSignal ProcessingstereologyComputer Vision and Pattern RecognitionArtificial intelligencebusinesslcsh:Medicine (General)Biotechnology
researchProduct

Unsupervised low-key image segmentation using curve evolution approach

2013

Low-key images widely exist in imaging-based systems such as space telescopes, medical imaging equipment, machine vision systems. Unsupervised low-key image segmentation is an important process for image analysis or digital measurement in these applications. In this paper, a novel active contour model with the probability density function (PDF) of gamma distribution for image segmentation is proposed. The flexible gamma distribution is used to describe both of the heterogeneous foreground and dark background in a low-key image. Besides, an unsupervised curve initialization method is also designed in this paper, which helps to accelerate the convergence speed of curve evolution. The effectiv…

Active contour modelbusiness.industrySegmentation-based object categorizationComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationInitializationPattern recognitionImage segmentationImage textureComputer Science::Computer Vision and Pattern RecognitionCurve fittingGamma distributionComputer visionArtificial intelligencebusinessMathematics2013 IEEE International Conference on Mechatronics (ICM)
researchProduct

A robust aerial image registration method using Gaussian mixture models

2014

Aerial image registration is one of the bases in many aerospace applications, such as aerial reconnaissance and aerial mapping. In this paper, we propose a novel aerial image registration algorithm which is based on Gaussian mixture models. First of all, considering the characters of the aerial images, the work uses a shape feature detector which computes the boundaries of regions with nearly the same gray-value to extract invariant feature. Then, a Gaussian mixture models (GMM) based image registration model is built and solved to estimate the transformation matrix between two aerial images. Furthermore, the proposed method is applied on real aerial images, and the results demonstrate the …

Aerial surveyComputer sciencebusiness.industryFeature detectorCognitive NeuroscienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage registrationComputerApplications_COMPUTERSINOTHERSYSTEMSPattern recognitionComputer Science Applications1707 Computer Vision and Pattern RecognitionMixture modelAerial images; Feature detector; Gaussian mixture models; Image registration; Computer Science Applications1707 Computer Vision and Pattern Recognition; Cognitive Neuroscience; Artificial IntelligenceComputer Science ApplicationsComputer Science::RoboticsComputer Science::Systems and ControlArtificial IntelligenceComputer Science::Computer Vision and Pattern RecognitionAerial imagesComputer visionAerial reconnaissanceArtificial intelligenceGaussian mixture modelsbusinessAerial imageImage registration
researchProduct

Hybrid architecture for shape reconstruction and object recognition

1998

The proposed architecture is aimed to recover 3-D- shape information from gray-level images of a scene; to build a geometric representation of the scene in terms of geometric primitives; and to reason about the scene. The novelty of the architecture is in fact the integration of different approaches: symbolic reasoning techniques typical of knowledge representation in artificial intelligence, algorithmic capabilities typical of artificial vision schemes, and analogue techniques typical of artificial neural networks. Experimental results obtained by means of an implemented version of the proposed architecture acting on real scene images are reported to illustrate the system capabilities.

Artificial neural networkKnowledge representation and reasoningComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognitionImage processingTheoretical Computer ScienceHuman-Computer InteractionArtificial IntelligenceComputer Science::Computer Vision and Pattern RecognitionPattern recognition (psychology)Systems architectureComputer visionGeometric primitiveArtificial intelligenceGraphicsbusinessSoftware
researchProduct

Regularized RBF Networks for Hyperspectral Data Classification

2004

In this paper, we analyze several regularized types of Radial Basis Function (RBF) Networks for crop classification using hyperspectral images. We compare the regularized RBF neural network with Support Vector Machines (SVM) using the RBF kernel, and AdaBoost Regularized (ABR) algorithm using RBF bases, in terms of accuracy and robustness. Several scenarios of increasing input space dimensionality are tested for six images containing six crop classes. Also, regularization, sparseness, and knowledge extraction are paid attention.

Artificial neural networkbusiness.industryComputer scienceMathematicsofComputing_NUMERICALANALYSISComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONHyperspectral imagingPattern recognitionSupport vector machineComputingMethodologies_PATTERNRECOGNITIONComputer Science::Computational Engineering Finance and ScienceRobustness (computer science)Computer Science::Computer Vision and Pattern RecognitionRadial basis function kernelRadial basis functionArtificial intelligenceAdaBoostbusinessCurse of dimensionality
researchProduct

A Neural Architecture for 3D Segmentation

2003

An original neural scheme for segmentation of range data is presented, which is part of a more general 3D vision system for robotic applications. The entire process relies on a neural architecture aimed to perform first order image irradiance analysis, that is local estimation of magnitude and orientation of the image irradiance gradient.

Artificial neural networkbusiness.industryOrientation (computer vision)Computer scienceNoise reductionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONProcess (computing)CurvatureEdge detectionRange (mathematics)Computer Science::Computer Vision and Pattern RecognitionComputer visionSegmentationArtificial intelligencebusiness
researchProduct

LogDet divergence-based metric learning with triplet constraints and its applications.

2014

How to select and weigh features has always been a difficult problem in many image processing and pattern recognition applications. A data-dependent distance measure can address this problem to a certain extent, and therefore an accurate and efficient metric learning becomes necessary. In this paper, we propose a LogDet divergence-based metric learning with triplet constraints (LDMLT) approach, which can learn Mahalanobis distance metric accurately and efficiently. First of all, we demonstrate the good properties of triplet constraints and apply it in LogDet divergence-based metric learning model. Then, to deal with high-dimensional data, we apply a compressed representation method to learn…

AutomatedData InterpretationBiometryFeature extractionhigh dimensional datametric learningPattern RecognitionFacial recognition systemSensitivity and SpecificityMatrix decompositionPattern Recognition Automatedcompressed representationComputer-AssistedArtificial Intelligencecompressed representation; high dimensional data; LogDet divergence; metric learning; triplet constraint; Artificial Intelligence; Biometry; Data Interpretation Statistical; Face; Humans; Image Enhancement; Image Interpretation Computer-Assisted; Pattern Recognition Automated; Photography; Reproducibility of Results; Sensitivity and Specificity; Algorithms; Facial Expression; Software; Medicine (all); Computer Graphics and Computer-Aided DesignImage Interpretation Computer-AssistedPhotographyHumansDivergence (statistics)Image retrievalImage InterpretationMathematicsMahalanobis distancebusiness.industryLogDet divergenceMedicine (all)Reproducibility of ResultsPattern recognitionStatisticalImage EnhancementComputer Graphics and Computer-Aided DesignFacial ExpressionComputingMethodologies_PATTERNRECOGNITIONComputer Science::Computer Vision and Pattern RecognitionData Interpretation StatisticalFaceMetric (mathematics)Pattern recognition (psychology)Artificial intelligencetriplet constraintbusinessSoftwareAlgorithmsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society
researchProduct

Reflectance-based surface saliency

2017

In this paper, we propose an original methodology allowing the computation of the saliency maps for high dimensional RTI data (Reflectance Transformation Imaging). Unlike most of the classical methods, our approach aims at devising an intrinsic visual saliency of the surface, independent of the sensor (image) and the geometry of the scene (light-object-camera). From RTI data, we use the DMD (Discrete Modal Decomposition) technique for the angular reflectance reconstruction, which we extend by a new transformation on the modal basis enabling a rotation-invariant representation of reconstructed reflectances. This orientation-invariance of the resulting reflectance shapes fosters a robust esti…

Basis (linear algebra)Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION020207 software engineering02 engineering and technologyIterative reconstructionVisual appearanceTransformation (function)Salience (neuroscience)Computer Science::Computer Vision and Pattern Recognition0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessPolynomial texture mappingSurface reconstructionComputingMethodologies_COMPUTERGRAPHICS2017 IEEE International Conference on Image Processing (ICIP)
researchProduct

Novel Iris Biometric Watermarking Based on Singular Value Decomposition and Discrete Cosine Transform

2014

Published version of an article in the journal: Mathematical Problems in Engineering. Also available from the publisher at: http://dx.doi.org/10.1155/2014/926170 A novel iris biometric watermarking scheme is proposed focusing on iris recognition instead of the traditional watermark for increasing the security of the digital products. The preprocess of iris image is to be done firstly, which generates the iris biometric template from person's eye images. And then the templates are to be on discrete cosine transform; the value of the discrete cosine is encoded to BCH error control coding. The host image is divided into four areas equally correspondingly. The BCH codes are embedded in the sing…

BiometricsArticle SubjectGeneral MathematicsIris recognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEngineering (all)Robustness (computer science)Computer Science::MultimediaDiscrete cosine transformMathematics (all)Computer visionDigital watermarkingTransform codingMathematicsComputer Science::Cryptography and Securitybusiness.industrylcsh:MathematicsVDP::Technology: 500::Mechanical engineering: 570General EngineeringWatermarkVDP::Technology: 500::Information and communication technology: 550lcsh:QA1-939ComputingMethodologies_PATTERNRECOGNITIONlcsh:TA1-2040Computer Science::Computer Vision and Pattern RecognitionArtificial intelligencebusinesslcsh:Engineering (General). Civil engineering (General)BCH codeMathematics (all); Engineering (all)Mathematical Problems in Engineering
researchProduct

A sensor-data-based denoising framework for hyperspectral images

2015

Many denoising approaches extend image processing to a hyperspectral cube structure, but do not take into account a sensor model nor the format of the recording. We propose a denoising framework for hyperspectral images that uses sensor data to convert an acquisition to a representation facilitating the noise-estimation, namely the photon-corrected image. This photon corrected image format accounts for the most common noise contributions and is spatially proportional to spectral radiance values. The subsequent denoising is based on an extended variational denoising model, which is suited for a Poisson distributed noise. A spatially and spectrally adaptive total variation regularisation term…

Blind deconvolution[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingHyperspectral imagingAnisotropic diffusionComputer scienceNoise reductionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technology01 natural sciences010309 opticsOptics[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing0103 physical sciencesdenoising0202 electrical engineering electronic engineering information engineeringbusiness.industryHyperspectral imagingcomputer.file_formatNon-local meansAtomic and Molecular Physics and OpticsLight intensityFull spectral imagingComputer Science::Computer Vision and Pattern Recognition020201 artificial intelligence & image processingImage file formatsNoise (video)businesscomputer
researchProduct