Search results for " Descriptors"

showing 10 items of 49 documents

An evaluation of recent local image descriptors for real-world applications of image matching

2019

This paper discusses and compares the best and most recent local descriptors, evaluating them on increasingly complex image matching tasks, encompassing planar and non-planar scenarios under severe viewpoint changes. This evaluation, aimed at assessing descriptor suitability for real-world applications, leverages the concept of approximated overlap error as a means to naturally extend to non-planar scenes the standard metric used for planar scenes. According to the evaluation results, most descriptors exhibit a gradual performance degradation in the transition from planar to non-planar scenes. The best descriptors are those capable of capturing well not only the local image context, but als…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - InformaticaImage matchingComputer sciencebusiness.industryVisual descriptorsComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognition02 engineering and technology03 medical and health sciences0302 clinical medicineLocal Image Descriptors; Image MatchingRobustness (computer science)Computer Science::Computer Vision and Pattern RecognitionComputer Science::Multimedia030221 ophthalmology & optometry0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessImage matching Data-driven approach Descriptors Evaluation results Local descriptors Local image descriptors Performance degradation Real-worldScene structure Computer vision
researchProduct

Is There Anything New to Say About SIFT Matching?

2020

SIFT is a classical hand-crafted, histogram-based descriptor that has deeply influenced research on image matching for more than a decade. In this paper, a critical review of the aspects that affect SIFT matching performance is carried out, and novel descriptor design strategies are introduced and individually evaluated. These encompass quantization, binarization and hierarchical cascade filtering as means to reduce data storage and increase matching efficiency, with no significant loss of accuracy. An original contextual matching strategy based on a symmetrical variant of the usual nearest-neighbor ratio is discussed as well, that can increase the discriminative power of any descriptor. Th…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryComputer scienceImage matchingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformPattern recognition02 engineering and technologySIFT sGLOH2 Quantization Binary descriptors Symmetric matching Hierarchical cascade filtering Deep descriptors Keypoint patch orientation Approximated overlap errorDiscriminative modelArtificial IntelligenceHistogramComputer data storage0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligenceSIFTsGLOH2quantizationbinary descriptorssymmetric matchinghierarchical cascade filteringdeep descriptorskeypoint patch orientationapproximated overlap errorbusinessQuantization (image processing)SoftwareInternational Journal of Computer Vision
researchProduct

Guest editorial: Local image descriptors in computer vision

2020

...This Special Issue includes seven original research papers that cover diverse and significant aspects of local image descriptor research. In particular, the order in which papers appear reflects the main phase they address, in an ideal computational pipeline starting with the localisation of salient points in an image and ending with the incorporation of spatial and temporal features in descriptor construction....

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticalocal descriptorscomputer vision
researchProduct

Global Archaelogical Mosaicing for Underwater Scenes

2006

This contribution regards the mosaicing of seabed landscapes, in order to represent higher resolution photos of whole sites with wrecks in a fast and safe fashion. A stereo vision system has been arranged by adding two cameras to the payload aboard a Remotely Operated Vehicle. A number of problems arise due to poor luminosity, cloudy water, water distortion and presence of artifacts. A robust algorithm has been defined to reduce the radial distortion of the camera lenses and to enhance the results.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticamosaicing feature detectors feature descriptors
researchProduct

3D objects descriptors methods: Overview and trends

2017

International audience; Object recognition or object's category recognition under varying conditions is one of the most astonishing capabilities of human visual system. The scientists in computer vision have been trying for decades to reproduce this ability by implementing algorithms and providing computers with appropriate tools. Hence, several intelligent systems have been proposed. To act in this field, numerous approaches have been proposed. In this paper we present an overview of the current trend in 3D objects recognition and describe some representative state of the art methods, highlighting their limits and complexity.

Sketch recognitionComputer science3D single-object recognition[INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR]02 engineering and technology[INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG]Field (computer science)object recognitionhuman visual systemcomputer vision[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingHuman–computer interactionobject category recognition0202 electrical engineering electronic engineering information engineeringskeletonComputer vision3D objects descriptors methodsVisualization3D objects recognitionintelligent systemsNon-Controlled Indexingbusiness.industryCognitive neuroscience of visual object recognitionIntelligent decision support system[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Shape020207 software engineeringComputational modelingObject (computer science)Keypoints3D objects[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]VisualizationRecognition[INFO.INFO-CG] Computer Science [cs]/Computational Geometry [cs.CG]Human visual system modelSolid modelingThree-dimensional displays020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

Local Entropy Characterization of Correlated Random Microstructures

1996

A rigorous connection is established between the local porosity entropy introduced by Boger et al. (Physica A 187, 55 (1992)) and the configurational entropy of Andraud et al. (Physica A 207, 208 (1994)). These entropies were introduced as morphological descriptors derived from local volume fluctuations in arbitrary correlated microstructures occuring in porous media, composites or other heterogeneous systems. It is found that the entropy lengths at which the entropies assume an extremum become identical for high enough resolution of the underlying configurations. Several examples of porous and heterogeneous media are given which demonstrate the usefulness and importance of this morphologic…

Statistics and ProbabilityCondensed Matter - Materials ScienceMaterials scienceConfiguration entropyMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesStatistical physicsMorphological descriptorsCondensed Matter PhysicsPorosityPorous mediumMicrostructure
researchProduct

DRUDIT: Web-based DRUgs DIscovery Tools to design small molecules as modulators of biological targets

2019

Abstract Motivation New in silico tools to predict biological affinities for input structures are presented. The tools are implemented in the DRUDIT (DRUgs DIscovery Tools) web service. The DRUDIT biological finder module is based on molecular descriptors that are calculated by the MOLDESTO (MOLecular DEScriptors TOol) software module developed by the same authors, which is able to calculate more than one thousand molecular descriptors. At this stage, DRUDIT includes 250 biological targets, but new external targets can be added. This feature extends the application scope of DRUDIT to several fields. Moreover, two more functions are implemented: the multi- and on/off-target tasks. These tool…

Statistics and ProbabilityService (systems architecture)PolypharmacologyComputer scienceIn silicoMachine learningcomputer.software_genre01 natural sciencesBiochemistrybiological target finderdrug discoveryMolecular descriptors03 medical and health sciencesMolecular descriptorSettore BIO/10 - BiochimicaWeb applicationComputer SimulationPolypharmacologyMolecular Biology030304 developmental biologySettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniInternet0303 health sciencesbusiness.industrySmall moleculeSettore CHIM/08 - Chimica Farmaceutica0104 chemical sciencesComputer Science Applications010404 medicinal & biomolecular chemistryComputational MathematicsComputational Theory and MathematicsBiological targetThe InternetArtificial intelligencebusinesscomputerSoftware
researchProduct

Comparison of leaf surface roughness analysis methods by sensitivity to noise analysis

2015

International audience; Surface roughness is of great interest in agricultural spraying because it is used to characterise leaf surface wettability to predict the behaviour of droplets on a leaf surface. In recent years, the use of texture analysis to estimate surface roughness has emerged. In this paper we propose to estimate leaf surface roughness by using an optimisation of the Generalized Fourier Descriptors method. This approach is then compared with two other standard methods in the literature, one based on grey level intensity variation and the other on wavelet decomposition. Since roughness has many definitions and each method is calculated differently, we propose a new approach to …

Surface (mathematics)Materials science[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingGaussianSoil ScienceWavelet decompositionSurface finishLeaf roughnessNoise analysissymbols.namesakeOptics[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingSurface roughnessSensitivity (control systems)Generalized Fourier DescriptorsSensitivity indicatorbusiness.industryOptical roughnessNoiseControl and Systems EngineeringsymbolsWettingBiological systembusinessAgronomy and Crop ScienceIntensity (heat transfer)Food Science
researchProduct

Ripensare il curricolo a partire dai learning outcomes. Un’indagine esplorativa nel CdS-L19 dell’Università di Catania per sostenere processi di camb…

2021

Il presente contributo descrive l’indagine esplorativa avviata a seguito dell’analisi dei dati emersi dalla sperimentazione TECO-D/ Pedagogia alla quale ha partecipato il CdS L-19 dell’Università di Catania. I risultati della somministrazione dei test agli studenti hanno indotto le Autrici a operare una riflessione sul contributo che le discipline del curricolo della L-19 forniscono al raggiungimento dei contenuti core definiti dalla sperimentazione. Grazie a uno strumento di rilevazione appositamente creato, è stato chiesto a tutti i docenti del CdS di operare una riflessione sul contributo che l ’ i n s e g n a m e n t o p r o f e s s a t o o f f r e a l raggiungimento degli obiettivi for…

Teco-D learning outcomes university teaching dublin descriptors
researchProduct

Qualità della didattica universitaria e sviluppo della capacità decisionale. Il modello ADVP per garantire i passaggi da L-19 a LM-85bis.

2020

Il presente contributo intende offrire una riflessione sulle competenze attese individuate attraverso la formulazione dei descrittori di Dublino dei CdS in Scienze dell’Educazione (L-19) e Scienze della Formazione Primaria (LM-85bis) istituiti presso l’Ateneo di Palermo e nello stesso tempo proporre un modello per lo sviluppo della maturità professional e necessaria a garantire scelte consapevoli, mature e responsabili. L’analisi condotta ci ha permesso, in una seconda fase di individuare gli obiettivi formativi finali scelti seguendo il modello proposto dalle Linee Guida dell ’Anvur, e di scegliere il modello dell’Activaction du Developpement Vocationnel et Personnel quale strumento per lo…

This paper offers a reflection on the expected competencies identified through the formulation of the Dublin descriptors of the CdS in Education Sciences (L-19) and Primary Education Sciences (LM-85bis) established at the University of Palermo and in the same time to propose a model for the development of professional maturity necessary to ensure informed mature and responsible choices. The analysis carried out allowed us in a second phase to identify the final training objectives chosen following the model proposed by the ANVUR Guidelines and to select the model of the Activaction du Developpement Vocationnel et Personnel for developing decision-making capacity that allows a conscious and responsible passage of students from course L-19 to course LM-85bis safeguarding the specific professional skills that young people wishing to dedicate themselves to teaching in primary and kindergarten must acquire.Settore M-PED/03 - Didattica E Pedagogia Speciale
researchProduct