Search results for "sGLOH"

showing 5 items of 5 documents

Rethinking the sGLOH Descriptor

2018

sGLOH (shifting GLOH) is a histogram-based keypoint descriptor that can be associated to multiple quantized rotations of the keypoint patch without any recomputation. This property can be exploited to define the best distance between two descriptor vectors, thus avoiding computing the dominant orientation. In addition, sGLOH can reject incongruous correspondences by adding a global constraint on the rotations either as an a priori knowledge or based on the data. This paper thoroughly reconsiders sGLOH and improves it in terms of robustness, speed and descriptor dimension. The revised sGLOH embeds more quantized rotations, thus yielding more correct matches. A novel fast matching scheme is a…

Cascade matching0209 industrial biotechnologyHistogram binarizationRFDComputer scienceGLOHComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyCNN descriptorLIOP020901 industrial engineering & automationMROGHArtificial IntelligenceRobustness (computer science)Keypoint matchingSIFTHistogram0202 electrical engineering electronic engineering information engineeringSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryApplied MathematicsCognitive neuroscience of visual object recognitionPattern recognitionRotation invariant descriptorsGLOHMIOPComputational Theory and MathematicsKeypoint matching SIFT sGLOH RFDs LIOP MIOP MROGH CNN descriptors rotation invariant descriptors histogram binarization cascade matchingPrincipal component analysis020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftware
researchProduct

RootsGLOH2: embedding RootSIFT 'square rooting' in sGLOH2

2020

This study introduces an extension of the shifting gradient local orientation histogram doubled (sGLOH2) local image descriptor inspired by RootSIFT ‘square rooting’ as a way to indirectly alter the matching distance used to compare the descriptor vectors. The extended descriptor, named RootsGLOH2, achieved the best results in terms of matching accuracy and robustness among the latest state-of-the-art non-deep descriptors in recent evaluation contests dealing with both planar and non-planar scenes. RootsGLOH2 also achieves a matching accuracy very close to that obtained by the best deep descriptors to date. Beside confirming that ‘square rooting’ has beneficial effects on sGLOH2 as it happe…

FEATURE EXTRACTIONLOCAL FEATUREComputer scienceFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformFEATURE MATCHING02 engineering and technologyRobustness (computer science)Euclidean geometryComputer Science::Multimedia0202 electrical engineering electronic engineering information engineeringBeneficial effectsSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryImage matching020206 networking & telecommunicationsPattern recognitionCOMPUTER VISIONImage Matching Local Image Descriptors RootSIFT sGLOH2Computer Science::Computer Vision and Pattern RecognitionEmbedding020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareSquare rootingIMAGE MATCHING
researchProduct

Extending the sGLOH descriptor

2015

This paper proposes an extension of the sGLOH keypoint descriptor [3] which improves its robustness and discriminability. The sGLOH descriptor can handle discrete rotations by a cyclic shift of its elements thanks to its circular structure, but its performance can decrease when the keypoint relative rotation is in between two sGLOH discrete rotations. The proposed extension couples together two sGLOH descriptors for the same patch with different rotations in order to cope with this issue and it can be also applied straightly to the sCOr and sGOr matching strategies of sGLOH. Experimental results show a consistent improvement of the descriptor discriminability, while different setups can be …

Keypoint descriptorMatching (graph theory)Settore INF/01 - InformaticaComputer scienceGLOHStructure (category theory)Scale-invariant feature transformSGLOHExtension (predicate logic)Keypoint descriptor image matching rotation invarianceRunning timeTask (project management)Robustness (computer science)SIFTMatchingAlgorithm
researchProduct

Improving SIFT-based descriptors stability to rotations

2010

Image descriptors are widely adopted structures to match image features. SIFT-based descriptors are collections of gradient orientation histograms computed on different feature regions, commonly divided by using a regular Cartesian grid or a log-polar grid. In order to achieve rotation invariance, feature patches have to be generally rotated in the direction of the dominant gradient orientation. In this paper we present a modification of the GLOH descriptor, a SIFT-based descriptor based on a log-polar grid, which avoids to rotate the feature patch before computing the descriptor since predefined discrete orientations can be easily derived by shifting the descriptor vector. The proposed des…

PixelSettore INF/01 - Informaticabusiness.industryOrientation (computer vision)GLOHInformationSystems_INFORMATIONSTORAGEANDRETRIEVALFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformPattern recognitionComputingMethodologies_PATTERNRECOGNITIONdescriptors SIFT sGLOH sGLOH+ computer vision.Robustness (computer science)Feature (computer vision)Computer Science::Computer Vision and Pattern RecognitionHistogramComputer Science::MultimediaComputer visionArtificial intelligencebusinessMathematics
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