Search results for " Vision"

showing 10 items of 2709 documents

Deep Learning Architectures for Diagnosis of Diabetic Retinopathy

2023

For many years, convolutional neural networks dominated the field of computer vision, not least in the medical field, where problems such as image segmentation were addressed by such networks as the U-Net. The arrival of self-attention-based networks to the field of computer vision through ViTs seems to have changed the trend of using standard convolutions. Throughout this work, we apply different architectures such as U-Net, ViTs and ConvMixer, to compare their performance on a medical semantic segmentation problem. All the models have been trained from scratch on the DRIVE dataset and evaluated on their private counterparts to assess which of the models performed better in the segmentatio…

Fluid Flow and Transfer Processessegmentation; medical image; ConvMixer; U-Net; vision transformerProcess Chemistry and TechnologyGeneral EngineeringEnginyeriaFísicaGeneral Materials ScienceEnginyeria biomèdicaInstrumentationComputer Science Applications
researchProduct

Unmanned Aerial Vehicle (UAV) operated spectral camera system for forest and agriculture applications

2011

VTT Technical Research Centre of Finland has developed a Fabry-Perot Interferometer (FPI) based hyperspectral imager compatible with the light weight UAV platforms. The concept of the hyperspectral imager has been published in the SPIE Proc. 7474 and 7668. In forest and agriculture applications the recording of multispectral images at a few wavelength bands is in most cases adequate. The possibility to calculate a digital elevation model of the forest area and crop fields provides means to estimate the biomass and perform forest inventory. The full UAS multispectral imaging system will consist of a high resolution false color imager and a FPI based hyperspectral imager which can be used at …

Forest inventoryPixelbusiness.industryMultispectral imageImaging spectrometerHyperspectral imagingField of viewFalse colorGeographyAstronomical interferometerComputer visionArtificial intelligencebusinessRemote sensing
researchProduct

New shape from Shading methods

1993

Shape from Shading is perhaps the most difficult topic to deal with in Artificial Vision: several researchers have faced it using different approaches. The most part of these methods are based on the Horn algorithm so they require very heavy regularity assumptions about the perceived objects' shape and are computationally expensive.

Form factor (design)Constructive solid geometryPhotometric stereoComputer scienceFrench hornbusiness.industryArtificial visionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer visionArtificial intelligenceShadingbusiness
researchProduct

A passive stabilization solution for camera embedded onboard small planes

2014

Embedded camera is becoming democratized in personal uses like sport. Thus the need for a stabilized video leads to a development of dedicated stabilized systems. However, in professional uses like video protection, stabilization solutions are not yet common. Moreover such a system needs to fit application specific requirements in term of size, weight, amplitude and frequency response.

Frequency responseAmplitude responsebusiness.industryComputer scienceTerm (time)VibrationAmplitudeVibration measurementElectronic engineeringApplication specificComputer visionArtificial intelligencebusinessSimulation2014 IEEE/AIAA 33rd Digital Avionics Systems Conference (DASC)
researchProduct

A simple joint estimation-detection technique for OFDM systems

2005

In this work a simple approach for the joint estimation-detection in a frequency selective severe fading environment of OFDM signals adopting PSK constellations is presented. A linear predictor of suitable order is adopted for the channel estimation in the frequency domain. The predictor coefficients are estimated on the basis of a sample estimation of the autocorrelation of the channel frequency response, aided by a preliminary differential decoding, in a blockwise manner. The detection technique proposed here is based on a simple tree search where a small number of best survivor paths are maintained at each step. Despite the simplicity of above detection approach, the simulation results s…

Frequency responseOrthogonal frequency division multiplexingComputer scienceOrthogonal frequency-division multiplexingChannel estimationLinear predictionData_CODINGANDINFORMATIONTHEORYControl and Systems Engineeringpilot symbolsFrequency domainSignal ProcessingElectronic engineeringFadingComputer Vision and Pattern RecognitionElectrical and Electronic EngineeringAlgorithmSoftwareDecoding methodsMultipath propagationComputer Science::Information TheoryCommunication channelPhase-shift keying
researchProduct

Subjective image fidelity metric based on bit allocation of the human visual system in the DCT domain

1997

Until now, subjective image distortion measures have partially used diverse empirical facts concerning human perception: non-linear perception of luminance, masking of the impairments by a highly textured surround, linear filtering by the threshold contrast frequency response of the visual system, and non-linear post-filtering amplitude corrections in the frequency domain. In this work, we develop a frequency and contrast dependent metric in the DCT domain using a fully non-linear and suprathreshold contrast perception model: the Information Allocation Function (IAF) of the visual system. It is derived from experimental data about frequency and contrast incremental thresholds and it is cons…

Frequency responsegenetic structuresImage qualitybusiness.industrymedia_common.quotation_subjectDistortionFrequency domainSignal ProcessingMetric (mathematics)Human visual system modelContrast (vision)Computer visionComputer Vision and Pattern RecognitionArtificial intelligencebusinessData compressionmedia_commonMathematics
researchProduct

Friction stir consolidation of aluminum machining chips

2017

Friction stir consolidation (FSC) is a solid-phase manufacturing process that consolidates metal powder, chips, or scraps into solid blocks via severe plastic deformation and solid state welding. It has the potential to be a more economical and “green” process to recycle metal waste. In this study, solid discs were made from AA6061 aluminum alloy machining chips by FSC. The progression of the process was revealed by analyzing the motion of the tool, consolidating force, power history, and macro/microstructure of discs produced from a series of partial consolidation experiments. A bowl-shaped recrystallized zone in the vertical cross-sections of the disc products was observed and conside…

Frictions stir consolidation0209 industrial biotechnologyMaterials sciencebusiness.product_category02 engineering and technologyWeldingIndustrial and Manufacturing Engineeringlaw.invention020901 industrial engineering & automationMachininglawRecyclingSettore ING-IND/16 - Tecnologie E Sistemi Di LavorazioneFEMDesign of experimentConsolidation (soil)Mechanical EngineeringMetallurgyRotational speedComputer Science Applications1707 Computer Vision and Pattern Recognition021001 nanoscience & nanotechnologyComputer Science ApplicationsCompressive strengthControl and Systems EngineeringMetal powderDie (manufacturing)Severe plastic deformation0210 nano-technologybusinessSoftware
researchProduct

Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning

2014

Mango fruit are sensitive and can easily develop brown spots after suffering mechanical stress during postharvest handling, transport and marketing. The manual inspection of this fruit used today cannot detect the damage in very early stages of maturity and to date no automatic tool capable of such detection has been developed, since current systems based on machine vision only detect very visible damage. The application of hyperspectral imaging to the postharvest quality inspection of fruit is relatively recent and research is still underway to find a method of estimating internal properties or detecting invisible damage. This work describes a new system to evaluate mechanically induced da…

Fruit qualityEngineeringHyperspectral imagingPixelbusiness.industryMachine visionMultispectral imageSoil ScienceEarly detectionHyperspectral imagingMango fruitsControl and Systems EngineeringNon-destructive inspectionNondestructive testingFeature selectionClassification methodsComputer visionComputer visionArtificial intelligencebusinessMango fruitAgronomy and Crop ScienceFood Science
researchProduct

Case-studies on average-case analysis for an elementary course on algorithms

1999

Average-case algorithm analysis is usually viewed as a tough subject by students in the first courses in computer science. Traditionally, these topics are fully developed in advanced courses with a clear mathematical orientation. The work presented here is not an alternative to this, rather, it presents the analysis of algorithms (and average-case in particular) adapted to the mathematical background of students in an elementary course on algorithms or programming by using two selected case-studies.

Fully developedComputer scienceOrientation (computer vision)Algorithm theoryComputingMilieux_COMPUTERSANDEDUCATIONSubject (documents)Algorithm designElectrical and Electronic EngineeringAlgorithmEducationAnalysis of algorithmsCourse (navigation)Case analysisIEEE Transactions on Education
researchProduct

Textureless macula swelling detection with multiple retinal fundus images

2011

Retinal fundus images acquired with nonmydriatic digital fundus cameras are versatile tools for the diagnosis of various retinal diseases. Because of the ease of use of newer camera models and their relatively low cost, these cameras can be employed by operators with limited training for telemedicine or point-of-care (PoC) applications. We propose a novel technique that uses uncalibrated multiple-view fundus images to analyze the swelling of the macula. This innovation enables the detection and quantitative measurement of swollen areas by remote ophthalmologists. This capability is not available with a single image and prone to error with stereo fundus cameras. We also present automatic alg…

Fundus OculiPoint-of-Care SystemsComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONBiomedical EngineeringOptical flowImage registrationIterative reconstructionFundus (eye)Ophthalmoscopy510 MathematicsImage Processing Computer-AssistedmedicineHumansPreprocessorMacula LuteaComputer visionMacular edema000 Computer science knowledge & systemsRetinamedicine.diagnostic_testbusiness.industrymedicine.diseaseTelemedicineOphthalmoscopymedicine.anatomical_structureArtificial intelligencebusinessAlgorithms
researchProduct