Search results for "Transform"

showing 10 items of 3975 documents

Exploiting Visual Saliency Algorithms for Object-Based Attention: A New Color and Scale-Based Approach

2017

Visual Saliency aims to detect the most important regions of an image from a perceptual point of view. More in detail, the goal of Visual Saliency is to build a Saliency Map revealing the salient subset of a given image by analyzing bottom-up and top-down factors of Visual Attention. In this paper we proposed a new method for Saliency detection based on colour and scale analysis, extending our previous work based on SIFT spatial density inspection. We conducted several experiments to study the relationships between saliency methods and the object attention processes and we collected experimental data by tracking the eye movements of thirty viewers in the first three seconds of observation o…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniComputer sciencebusiness.industrymedia_common.quotation_subject05 social sciencesComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEye movementExperimental dataScale-invariant feature transformVisual saliency Object-based attention SIFT Fixation maps Dataset Eye trackingPattern recognition02 engineering and technology050105 experimental psychologySalientPerceptionFixation (visual)0202 electrical engineering electronic engineering information engineeringEye tracking020201 artificial intelligence & image processing0501 psychology and cognitive sciencesComputer visionArtificial intelligencebusinessObject-based attentionmedia_common
researchProduct

A New Class of Searchable and Provably Highly Compressible String Transformations

2019

The Burrows-Wheeler Transform is a string transformation that plays a fundamental role for the design of self-indexing compressed data structures. Over the years, researchers have successfully extended this transformation outside the domains of strings. However, efforts to find non-trivial alternatives of the original, now 25 years old, Burrows-Wheeler string transformation have met limited success. In this paper we bring new lymph to this area by introducing a whole new family of transformations that have all the "myriad virtues" of the BWT: they can be computed and inverted in linear time, they produce provably highly compressible strings, and they support linear time pattern search direc…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniFOS: Computer and information sciences050101 languages & linguisticsBurrows-wheeler transformation; Combinatorics on words; Data indexing and compression000 Computer science knowledge general worksSettore INF/01 - InformaticaCombinatorics on words05 social sciences02 engineering and technologyData_CODINGANDINFORMATIONTHEORYComputer ScienceBurrows-wheeler transformationComputer Science - Data Structures and Algorithms0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processing0501 psychology and cognitive sciencesData Structures and Algorithms (cs.DS)Data indexing and compressionCombinatorics on word
researchProduct

Multi-modal Medical Image Registration by Local Affine Transformations

2018

Image registration is the process of finding the geometric transformation that, applied to the floating image, gives the registered image with the highest similarity to the reference image. Registering a pair of images involves the definition of a similarity function in terms of the parameters of the geometric transformation that allows the registration. This paper proposes to register a pair of images by iteratively maximizing the empirical mutual information through coordinate gradient descent. Hence, the registered image is obtained by applying a sequence of local affine transformations. Rather than adopting a uniformly spaced grid to select image blocks to locally register, as done by s…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniModalbusiness.industryComputer scienceImage Registration Mutual Information Medical ImagesImage registrationComputer visionArtificial intelligenceAffine transformationbusiness
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

Effective and Efficient Interpolation for Mutual Information based Multimodality Elastic Image Registration

2009

Mutual information (MI) is a popular similarity metric for multimodality image registration purpose. However, it is negatively influenced by artifacts due to interpolation effects. As a result, registration algorithms performance could be affected. In this paper a novel interpolation scheme is presented. It is both effective and efficient. Effective because it limits the presence of local maxima in the mutual information curve, efficient because it is simple to compute being based on simple and optimized distance measures. The method is validated and compared against other techniques both from performance and time complexity persepectives. Differently from other reference works, which perfo…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSimilarity (geometry)business.industryImage registrationMutual informationinterpolation mutual information elastic registration non-linear optimizationDistance measuresHistogramMetric (mathematics)Computer visionArtificial intelligencebusinessAlgorithmRigid transformationMathematicsInterpolation
researchProduct

An Evolution of the Non-Parameter Harris Affine Corner Detector: A Distributed Approach

2009

A parallel version of a new automatic Harris-based corner detector is presented. A scheduler to dynamically and homogeneously distribute high computational workload on heterogeneous parallel architectures such as Grid systems has been implemented to speedup the whole procedure. Experimental results show the robustness of the underlying scheduler, which can be easily exploited in various automatic image analysis systems.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSpeedupSettore INF/01 - InformaticaComputer scienceDetectorFeature extractionYarnParallel computingEdge detectionGrid AlgorithmCorner DetectorScheduling (computing)Robustness (computer science)Adaptive Schedulingvisual_artvisual_art.visual_art_mediumAffine transformationClient-server ParadigmComputer Science::Operating Systems2009 International Conference on Parallel and Distributed Computing, Applications and Technologies
researchProduct

Fuzzy Smoothed Composition of Local Mapping Transformations for Non-rigid Image Registration

2009

This paper presents a novel method for medical image regis- tration. The global transformation is obtained by composing affine trans- formations, which are recovered locally from given landmarks. Transfor- mations of adjacent regions are smoothed to avoid blocking artifacts, so that a unique continuous and differentiable global function is obtained. Such composition is operated using a technique derived from fuzzy C- means clustering. The method was successfully tested on several datasets; results, both qualitative and quantitative, are shown. Comparisons with other methods are reported. Final considerations on the efficiency of the technique are explained.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionibusiness.industryImage registrationPattern recognitionComposition (combinatorics)Blocking (statistics)Fuzzy logicfree form deformation image registration fuzzy clustering function interpolation.Global transformationComputer visionDifferentiable functionArtificial intelligenceAffine transformationbusinessCluster analysisMathematics
researchProduct

Fake News Spreaders Detection: Sometimes Attention Is Not All You Need

2022

Guided by a corpus linguistics approach, in this article we present a comparative evaluation of State-of-the-Art (SotA) models, with a special focus on Transformers, to address the task of Fake News Spreaders (i.e., users that share Fake News) detection. First, we explore the reference multilingual dataset for the considered task, exploiting corpus linguistics techniques, such as chi-square test, keywords and Word Sketch. Second, we perform experiments on several models for Natural Language Processing. Third, we perform a comparative evaluation using the most recent Transformer-based models (RoBERTa, DistilBERT, BERT, XLNet, ELECTRA, Longformer) and other deep and non-deep SotA models (CNN,…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionitext classificationcorpus linguisticSettore ING-INF/03 - Telecomunicazionifake newTwitterauthor profilingconvolutional neural networkdeep learningNatural Language Processing (NLP)user classificationfake news; misinformation; Natural Language Processing (NLP); transformers; Twitter; convolutional neural networks; text classification; deep learning; machine learning; user classification; author profiling; corpus linguistics; linguistic analysismachine learningtransformermisinformationlinguistic analysisInformation Systems
researchProduct

ARC FAULT DETECTION EQUIPMENT AND METHOD USING LOW FREQUENCY HARMONIC CURRENT ANALYSIS

2012

An arc fault detection circuit includes a current sensing circuit coupled to a line conductor carrying a current. The current sensing circuit operates to sense current and output data indicative of the sensed current. A processing circuit implements a frequency transform algorithm to transform the output data to frequency data in a low frequency range and with a high spectral resolution where a minimum short time observation window is concerned. The processing circuit identifies an arc fault condition on the line conductor by identifying differences in said frequency data between at least two subsequent observation windows and identifying characteristics which exceed thresholds.

Settore ING-INF/07 - Misure Elettriche E Elettronichearc faults detection home protection photovoltaic systems electrical safety series arcs arc fault circuit interrupter (AFCI) harmonic analysis chirp-z transform (CZT)
researchProduct

Introduction: Shakespearean Subversions.

2014

Settore L-LIN/10 - Letteratura IngleseShakespeare Italian Culture Appropriation Transformation Opposition
researchProduct