Search results for "Digital image"

showing 8 items of 228 documents

Video-Assisted Navigation for Adjustment of Image-Guidance Accuracy to Slight Brain Shift

2015

Background Information supplied by an image-guidance system can be superimposed on the operating microscope oculars or on a screen, generating augmented reality. Recently, the outline of a patient's head and skull, injected in the oculars of a standard operating microscope, has been used to check the registration accuracy of image guidance. Objective To propose the use of the brain surface relief and superficial vessels for real-time intraoperative visualization and image-guidance accuracy and for intraoperative adjustment for brain shift. Methods A commercially available image-guidance system and a standard operating microscope were used. Segmentation of the brain surface and cortical bloo…

medicine.medical_specialtymedicine.diagnostic_testbusiness.industrymedicine.medical_treatmentMagnetic resonance imagingImaging phantomSurgeryVisualizationDigital imagemedicineSurgerySegmentationComputer visionAugmented realityNeurology (clinical)Artificial intelligencebusinessOperating microscopeCraniotomyOperative Neurosurgery
researchProduct

Micromechanical Modeling of Aortic Pathologies

2021

modellazione meccanicadigital image correlationaneurisma toracico aortico ascendenteAscending Thoracic Aortic Aneurysm Micromechanical Modeling Patient-Specific
researchProduct

Neural Classification of Compost Maturity by Means of the Self-Organising Feature Map Artificial Neural Network and Learning Vector Quantization Algo…

2019

Self-Organising Feature Map (SOFM) neural models and the Learning Vector Quantization (LVQ) algorithm were used to produce a classifier identifying the quality classes of compost, according to the degree of its maturation within a period of time recorded in digital images. Digital images of compost at different stages of maturation were taken in a laboratory. They were used to generate an SOFM neural topological map with centres of concentration of the classified cases. The radial neurons on the map were adequately labelled to represent five suggested quality classes describing the degree of maturation of the composted organic matter. This enabled the creation of a neural separator classify…

non-parametric classificationComputer science020209 energyHealth Toxicology and Mutagenesislcsh:Medicine02 engineering and technology010501 environmental sciencesengineering.material01 natural sciencesArticleDigital imageSoftwareArtificial Intelligence0202 electrical engineering electronic engineering information engineeringLearningTopological map0105 earth and related environmental sciencesLVQ algorithmLearning vector quantizationArtificial neural networkSOFM neural networkCompostbusiness.industryCompostinglcsh:RPublic Health Environmental and Occupational Health<i>LVQ</i> algorithmengineeringNeural Networks ComputerbusinessClassifier (UML)AlgorithmAlgorithmsSoftwareInternational Journal of Environmental Research and Public Health
researchProduct

Image classification based on 2D feature motifs

2013

The classification of raw data often involves the problem of selecting the appropriate set of features to represent the input data. In general, various features can be extracted from the input dataset, but only some of them are actually relevant for the classification process. Since relevant features are often unknown in real-world problems, many candidate features are usually introduced. This degrades both the speed and the predictive accuracy of the classifier due to the presence of redundancy in the candidate feature set. In this paper, we study the capability of a special class of motifs previously introduced in the literature, i.e. 2D irredundant motifs, when they are exploited as feat…

pattern discoveryContextual image classificationProbabilistic latent semantic analysisExploitComputer sciencebusiness.industryScale-invariant feature transformPattern recognitioncomputer.software_genreDigital imageComputingMethodologies_PATTERNRECOGNITIONclassificationimage analysisVisual WordArtificial intelligenceData miningbusinessClassifier (UML)computerImage compression
researchProduct

Automated Railway Signs Detection. Preliminary Results

2019

Abstract Nowadays safety in railways is mostly achieved by automated system technologies such as ERTMS/ETCS. Nevertheless, on local railways (suburban and regional lines) several tasks still depend on the choices and actions of a human crew. With the aim to improve safety in such type of railways, this research proposes a system for the automatic detection and recognition of railway signs by means of the digital image processing technique. First field applications, carried out on the Italian railway network, show that the proposed system is very accurate (the percentage of correctly detected railway signs is about 97%), even at high train speeds.

railway safety050210 logistics & transportation0209 industrial biotechnologyComputer science05 social sciencesGeneral Engineering02 engineering and technologyK4011-4343Transportation and communicationrailway sign detection and recognitionComputer Science Applications020901 industrial engineering & automation0502 economics and businessdigital image processing techniqueRailway safety digital image processing technique railway sign detection and recognitionRailway safetyTransport and Telecommunication Journal
researchProduct

Tekniikoita digitaalisten valokuvien aitouden arvioimiseen

2009

 Ollari, Ilkka Tietojärjestelmätieteen kandidaatintutkielma / Ilkka Ollari Jyväskylä: Jyväskylän yliopisto, 2009, 28 s. Kandidaatintutkielma Digitaalisten valokuvien muokkaamisesta on tullut hyvin helppoa ja yleistä, mikä on osaltaan johtanut valokuvien luotettavuuden heikentymiseen. Tässä tutkielmassa käsittelen kirjallisuuskatsauksen pohjalta erilaisia valokuvien aitouden arvioimiseen tarkoitettuja tekniikoita. Tutkin mm. sitä, kuinka luotettavasti kyseisillä tekniikoilla valokuvien aitous voidaan varmistaa, ja minkälaisia rajoitteita eri tekniikoilla on. Tekniikat voidaan jakaa aktiivisiin ja passiivisiin. Ensin mainitusta ryhmästä käsittelen vesileimoja, jotka ovat merkittävin aktiivist…

vesileimadigital image forensicskuvan muokkausdigitaalisten valokuvien autentikointi
researchProduct

Development and characterisation of polymer composite materials with bio-inspired functions

2018

Promocijas darbs ir izstrādāts disertācijas veidā fizikas nozarē materiālu fizikas apakšnozarē. Pētījums tika veikts LU Materiālu mehānikas institūtā. Darbs saistīts ar aktuālu un jaunu pētījumu virzienu: bioinspirēto funkciju tālāku attīstīšanu slodzi nesošos kompozītos. Tās ir mehānisku triecienu vizuālās indikācijas un polimēru matricas vaskulārās pašdziedināšanas funkcijas. Šīs funkcijas tika nodrošinātas, izveidojot viedus slāņus un iebūvējot tos kompozītā. Pētījumā tika noskaidrotas piemērotās pārbaužu secības, attīstītas kvantitatīvas metodes un mehānisks modelis, lai novērtētu jauno funkciju efektivitāti kompozītos. Ir pierādīta funkciju augstā efektivitāte un spēja uzlabot slodzi n…

visual indicationmicro-tubesmechanical testingPhysicsbruisable compositesself-healingdigital image analysisFizikaPhysics of Materials
researchProduct

Digitaalisten kuvaväärennösten tunnistaminen JPEG-pakkausta hyödyntäen

2010

Digitaalisten valokuvien muokkaamisesta on tullut hyvin helppoa ja yleistä, mikä on nostanut esille huolen valokuvien uskottavuudesta. Ongelman ratkaisuksi on esitetty erilaisia tekniikoita, joilla valokuvien aitoutta voidaan arvioida. Tarkastelen tässä tutkielmassa niin sanottuja passiivisia tekniikoita, jotka eivät edellytä kuvasta minkäänlaista ennakkotietoa, kuten vesileimaa. Vertailen viittä tällaista tekniikkaa laatimani neljä kohtaa käsittävän kriteeristön pohjalta. Vertailtavia ominaisuuksia ovat tarkkuus, tunnistetut muokkaustyypit, rajoitukset sekä vakaus vastatoimia vastaan. Vertailu osoittaa, että eräs merkittävimmistä tekniikoiden ongelmista on niiden huono toleranssi kuvan häv…

väärennöksettodentaminendigitaalikuvausJPEGdigital image forensicskuvankäsittelykuvat
researchProduct