Search results for " Segmentation"

showing 10 items of 462 documents

Neocomian to early Aptian syn-rift evolution of the normal to oblique-rifted North Gabon Margin (Interior and N'Komi Basins).

2009

18 pages; International audience; The North Gabon coastal rift basins consist of a set of 130–150 long-segment asymmetrically tilted half grabens (Interior Basin) and 000–020 short-segment en échelon half grabens (N'Komi Basin) separated by 040–060 major transverse faults. Tectono-sedimentary analysis of field and subsurface data reveals the control exerted by extensional tectonism over continental sedimentation. During Berriasian to early Barremian times, uniform uniaxial 040–060 extension was responsible for the stretching of the brittle upper crust over a 100-km wide domain. During late Barremian–early Aptian times, the main locus of extension stepped westward resulting in severe end-rif…

010504 meteorology & atmospheric sciencesAptianStratigraphy[SDE.MCG]Environmental Sciences/Global ChangesEarly CretaceousEnd-rift erosionStructural basin010502 geochemistry & geophysicsOceanography[ SDU.STU.ST ] Sciences of the Universe [physics]/Earth Sciences/Stratigraphy01 natural sciencesPaleontologyEchelon formationGabon0105 earth and related environmental sciences[SDU.STU.TE]Sciences of the Universe [physics]/Earth Sciences/TectonicsRift segmentationRiftOblique riftingGeologyCrust[ SDU.STU.TE ] Sciences of the Universe [physics]/Earth Sciences/TectonicsCretaceousGrabenTectonics[ SDE.MCG ] Environmental Sciences/Global ChangesGeophysics[SDU.STU.ST]Sciences of the Universe [physics]/Earth Sciences/StratigraphyEconomic GeologyPrecambrian heritageNormal riftingGeology
researchProduct

Optimized Class-Separability in Hyperspectral Images

2016

International audience; Image visualization techniques are mostly based on three bands as RGB color composite channels for human eye to characterize the scene. This, however, is not effective in case of hyper-spectral images (HSI) because they contain dozens of informative spectral bands. To eliminate redundancy of spectral information among these bands, dimensionality reduction (DR) is applied while at the same trying to retain maximum information. In this paper, we propose a new method of information-preserved hyper-spectral satellite image visualization that is based on fusion of unsupervised band selection techniques and color matching function (CMF) stretching. The results show consist…

010504 meteorology & atmospheric sciencesBand SelectionComputer science0211 other engineering and technologiesComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[SDU.STU]Sciences of the Universe [physics]/Earth Sciences02 engineering and technology[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing01 natural sciencesTransformation[SPI]Engineering Sciences [physics][ SPI.NRJ ] Engineering Sciences [physics]/Electric powerDisplay[ SPI ] Engineering Sciences [physics]Computer visionclass separabilityFusion021101 geological & geomatics engineering0105 earth and related environmental sciencesColor imagebusiness.industry[SPI.NRJ]Engineering Sciences [physics]/Electric powerHyperspectral imagingPattern recognition[ SDU.STU ] Sciences of the Universe [physics]/Earth SciencesImage segmentationSpectral bandsDimensionality reductionVisualization[SPI.TRON]Engineering Sciences [physics]/Electronics[ SPI.TRON ] Engineering Sciences [physics]/ElectronicsImaging spectroscopyFull spectral imagingRGB color modelArtificial intelligencehyper-spectral image visualizationbusiness[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
researchProduct

Quality Factors Influencing Consumer Demand for Small Fruit by Focus Group and Sensory Test

2017

ABSTRACTThe market of berries is a niche of high value in Italy. Small fruit’s healthy properties are well known in the international market, but little is known about the reason for a low commercialization rate of fresh small fruit in Italy. The objective of this study was to assess consumer preferences in Italy for selected berry species. Moreover, the study aims to identify the relevant attributes of berries that affect the demand for this produce according to consumers and to compare these attributes. We assessed relevant attributes affecting the demand for fresh berries for different consumers’ profiles and compared berries’ attributes rankings. The results reveal high concordance betw…

0106 biological sciences0301 basic medicineConsumer segmentation; focus group; niche market; sensory quality; Spearman coefficient; Food Science; Business and International Management; MarketingConsumer segmentationmedia_common.quotation_subjectBerryAffect (psychology)01 natural sciencesCommercialization03 medical and health sciencesniche marketWillingness to paySettore AGR/01 - Economia Ed Estimo RuraleEconomicsQuality (business)Spearman coefficientBusiness and International ManagementMarketingmedia_commonMarketing030109 nutrition & dieteticsFocus groupValue (economics)focus groupNiche marketsensory quality010606 plant biology & botanyFood ScienceJournal of Food Products Marketing
researchProduct

A segmentation algorithm for noisy images

2005

International audience; This paper presents a segmentation algorithm for gray-level images and addresses issues related to its performance on noisy images. It formulates an image segmentation problem as a partition of a weighted image neighborhood hypergraph. To overcome the computational difficulty of directly solving this problem, a multilevel hypergraph partitioning has been used. To evaluate the algorithm, we have studied how noise affects the performance of the algorithm. The alpha-stable noise is considered and its effects on the algorithm are studied. Key words : graph, hypergraph, neighborhood hypergraph, multilevel hypergraph partitioning, image segmentation and noise removal.

020203 distributed computingHypergraphMathematics::Combinatorics[ INFO ] Computer Science [cs]Computer sciencebusiness.industrySegmentation-based object categorizationComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationImage processing02 engineering and technologyImage segmentation[INFO] Computer Science [cs]020202 computer hardware & architectureComputer Science::Computer Vision and Pattern Recognition0202 electrical engineering electronic engineering information engineeringGraph (abstract data type)SegmentationComputer vision[INFO]Computer Science [cs]Artificial intelligencebusinessAlgorithmMathematicsofComputing_DISCRETEMATHEMATICS
researchProduct

“Natural wine” consumers and interest in label information: An analysis of willingness to pay in a new Italian wine market segment

2019

Abstract Increasing public attention to issues of health and environmental sustainability has contributed to a growing consumer demand for “natural” food and drinks. As has been observed, this trend has also affected the wine market, leading to the spread of so-called “natural wine”. According to the literature, consumers who are aware of the social and environmental impact of their consumption choices pay more attention to the information displayed on the label as a tool to reduce the risk associated with their purchase. This study seeks to identify which consumers are willing to pay for natural wine and to understand what information on the label influences their choice. This study is one…

020209 energyStrategy and ManagementBack label02 engineering and technologyMillennialIndustrial and Manufacturing EngineeringMarket segmentationWillingness to paySettore AGR/01 - Economia Ed Estimo Rurale0202 electrical engineering electronic engineering information engineeringProduction (economics)Natural (music)Environmental impact assessmentFront labelMarketingHealth concern0505 lawGeneral Environmental ScienceConsumption (economics)WineRenewable Energy Sustainability and the Environment05 social sciencesSustainabilitySustainability050501 criminologyBusinessOrdered logistic regression model
researchProduct

K-nearest neighbor driving active contours to delineate biological tumor volumes

2019

Abstract An algorithm for tumor delineation in positron emission tomography (PET) is presented. Segmentation is achieved by a local active contour algorithm, integrated and optimized with the k-nearest neighbor (KNN) classification method, which takes advantage of the stratified k-fold cross-validation strategy. The proposed approach is evaluated considering the delineation of cancers located in different body districts (i.e. brain, head and neck, and lung), and considering different PET radioactive tracers. Data are pre-processed in order to be expressed in terms of standardized uptake value, the most widely used PET quantification index. The algorithm uses an initial, operator selected re…

0209 industrial biotechnologyK-nearest neighborComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFDG and MET PET imagingStandardized uptake value02 engineering and technologyImaging phantomk-nearest neighbors algorithmActive contour algorithm020901 industrial engineering & automationArtificial IntelligenceRegion of interest0202 electrical engineering electronic engineering information engineeringSegmentationElectrical and Electronic EngineeringActive contour modelbusiness.industryProcess (computing)Pattern recognitionCancer segmentationBiological target volumeControl and Systems Engineering020201 artificial intelligence & image processingArtificial intelligencebusinessEnergy (signal processing)Engineering Applications of Artificial Intelligence
researchProduct

A Fast Multiresolution Approach Useful for Retinal Image Segmentation

2018

Retinal diseases such as retinopathy of prematurity (ROP), diabetic and hypertensive retinopathy present several deformities of fundus oculi which can be analyzed both during screening and monitoring such as the increase of tortuosity, lesions of tissues, exudates and hemorrhages. In particular, one of the first morphological changes of vessel structures is the increase of tortuosity. The aim of this work is the enhancement and the detection of the principal characteristics in retinal image by exploiting a non-supervised and automated methodology. With respect to the well-known image analysis through Gabor or Gaussian filters, our approach uses a filter bank that resembles the “à trous” wav…

0301 basic medicine03 medical and health sciences030104 developmental biologySettore INF/01 - Informaticabusiness.industryComputer scienceRetinal image segmentationComputer visionArtificial intelligencebusinessElliptical Gaussian filters Directional Map Retinal Vessel Fundus OculiProceedings of the 7th International Conference on Pattern Recognition Applications and Methods
researchProduct

Automatic detection of hemangiomas using unsupervised segmentation of regions of interest

2016

In this paper we compare the performances of three automatic methods of identifying hemangioma regions in images: 1) unsupervised segmentation using the Otsu method, 2) Fuzzy C-means clustering (FCM) and 3) an improved region growing algorithm based on FCM (RG-FCM). For each image, the starting point of the algorithms is a rectangular region of interest (ROI) containing the hemangioma. For computing the performances of each method, the ROIs had been manually labeled in 2 classes: pixels of hemangioma and pixels of non-hemangioma. The computed scores are given separately for each image, as well as global performances across all ROIs for both classes. The best classification of non-hemangioma…

0301 basic medicineComputer scienceScale-space segmentation02 engineering and technologyOtsu's methodHemangioma03 medical and health sciencessymbols.namesakeMinimum spanning tree-based segmentationRegion of interestHistogram0202 electrical engineering electronic engineering information engineeringmedicineComputer visionSegmentation-based object categorizationbusiness.industryPattern recognitionImage segmentationmedicine.diseaseStatistical classification030104 developmental biologyRegion growingsymbols020201 artificial intelligence & image processingArtificial intelligencebusiness2016 International Conference on Communications (COMM)
researchProduct

Analysis of normal human retinal vascular network architecture using multifractal geometry

2017

AIM To apply the multifractal analysis method as a quantitative approach to a comprehensive description of the microvascular network architecture of the normal human retina. METHODS Fifty volunteers were enrolled in this study in the Ophthalmological Clinic of Cluj-Napoca, Romania, between January 2012 and January 2014. A set of 100 segmented and skeletonised human retinal images, corresponding to normal states of the retina were studied. An automatic unsupervised method for retinal vessel segmentation was applied before multifractal analysis. The multifractal analysis of digital retinal images was made with computer algorithms, applying the standard box-counting method. Statistical analyse…

0301 basic medicineEarly detectionGeometryFundus (eye)03 medical and health scienceschemistry.chemical_compoundretinal vessel segmentationlcsh:OphthalmologyClinical ResearchMedicineSegmentationRetinal microvasculaturebusiness.industryRetinalMultifractal systemGeneralized dimensionsMultifractalRetinal vesselOphthalmology030104 developmental biologyMicrovascular NetworkRetinal image analysisStandard box-counting methodchemistryVascular networklcsh:RE1-994business
researchProduct

Study of Consumer Preferences in Regard to the Blonde Orange Cv. Washington Navel “Arancia Di Ribera PDO”

2016

Consumers’ attitude and preferences in regard to food ingre- dients, country of origin, social corporate responsibility toward the environment, and work conditions have changed over the last 10 years. Consumers are getting more educated and there- fore more sensitive around cultivation practices in agriculture and food processing, which increases concerns in regard to production practices in agriculture. Several studies have been conducted on consumers’ preferences about quality food, but not with regard to blonde oranges cv. Washington Navel culti- vated in southern Italy. This quality fruit is a niche product that achieved the Protected Designation of Origin (PDO) certifica- tion for high…

0301 basic medicineMarketing030109 nutrition & dieteticsbusiness.industryCertificationOrange (colour)PurchasingCountry of originCluster Analysis Consumer Preferences Preferences segmentation Purchase behaviour Quality fresh food03 medical and health sciencesGeographyAgricultureSettore AGR/01 - Economia Ed Estimo RuraleFood processingCorporate social responsibilityBusiness and International ManagementMarketingFood qualitybusinessFood Science
researchProduct