Dissertations / Theses on the topic 'Image analysis – Software'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Image analysis – Software.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Teo, Ching Leong. "Bistatic radar system analysis and software development." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2003. http://library.nps.navy.mil/uhtbin/hyperion-image/03Dec%5FTeo%5FChing.pdf.
Full textThesis advisor(s): David C. Jenn, D. Curtis Schleher. Includes bibliographical references (p. 95-96). Also available online.
Francis, Nicholas David. "Parallel architectures for image analysis." Thesis, University of Warwick, 1991. http://wrap.warwick.ac.uk/108844/.
Full textThomas, Mathew. "Semi-Automated Dental Cast Analysis Software." Wright State University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=wright1310404863.
Full textSelf, Joel. "On-the-fly dynamic dead variable analysis /." Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd1791.pdf.
Full textMinch, Stacy Lynn. "Validity of Seven Syntactic Analyses Performed by the Computerized Profiling Software." Diss., CLICK HERE for online access, 2009. http://contentdm.lib.byu.edu/ETD/image/etd2956.pdf.
Full textRungta, Neha Shyam. "Guided Testing for Automatic Error Discovery in Concurrent Software." Diss., CLICK HERE for online access, 2009. http://contentdm.lib.byu.edu/ETD/image/etd3175.pdf.
Full textBrown, Christopher A. "Usability analysis of the channel application programming interface." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2003. http://library.nps.navy.mil/uhtbin/hyperion-image/03Jun%5FBrown.pdf.
Full textChen, He. "Microscopic Hyperspectral Image Analysis via Deep Learning." Thesis, Griffith University, 2020. http://hdl.handle.net/10072/396188.
Full textThesis (Masters)
Master of Philosophy (MPhil)
School of Info & Comm Tech
Science, Environment, Engineering and Technology
Full Text
Caffall, Dale Scott. "Conceptual framework approach for system-of-systems software developments." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2003. http://library.nps.navy.mil/uhtbin/hyperion-image/03Mar%5FCaffall.pdf.
Full textThesis advisor(s): James Bret Michael, Man-Tak Shing. Includes bibliographical references (p. 83-84). Also available online.
Rexilius, Jan [Verfasser], and Klaus-Dietz [Akademischer Betreuer] Tönnies. "Software phantoms in medical image analysis / Jan Rexilius. Betreuer: Klaus-Dietz Tönnies." Magdeburg : Universitätsbibliothek, 2015. http://d-nb.info/1072685531/34.
Full textRexilius, Jan [Verfasser], and Klaus [Akademischer Betreuer] Tönnies. "Software phantoms in medical image analysis / Jan Rexilius. Betreuer: Klaus-Dietz Tönnies." Magdeburg : Universitätsbibliothek, 2015. http://nbn-resolving.de/urn:nbn:de:gbv:ma9:1-6064.
Full textKerbyson, Darren James. "A multiple-SIMD architecture for image and tracking analysis." Thesis, University of Warwick, 1992. http://wrap.warwick.ac.uk/80185/.
Full textLai, Ka Chon. "Constructing social networks based on image analysis." Thesis, University of Macau, 2012. http://umaclib3.umac.mo/record=b2586279.
Full textStevenson, Clint Wesley. "A logistic regression analysis of utah colleges exit poll response rates using SAS software /." Diss., CLICK HERE for online access, 2006. http://contentdm.lib.byu.edu/ETD/image/etd1578.pdf.
Full textHockgraver, Valerie Ruth. "Implementation of ImageActionplus software for improved image analysis of solid propellant combustion holograms." Thesis, Monterey, California. Naval Postgraduate School, 1989. http://hdl.handle.net/10945/27089.
Full textMasood, Khalid. "Histological image analysis and gland modelling for biopsy classification." Thesis, University of Warwick, 2010. http://wrap.warwick.ac.uk/3918/.
Full textGiuliani, Giulia. "Analysis and improvement of a software framework for solving mathematical puzzles." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Find full textRaza, Shan-e.-Ahmed. "Multi-variate image analysis for detection of biomedical anomalies." Thesis, University of Warwick, 2014. http://wrap.warwick.ac.uk/61713/.
Full textAmundberg, Joel, and Martin Moberg. "System Agnostic GUI Testing : Analysis of Augmented Image Recognition Testing." Thesis, Blekinge Tekniska Högskola, Institutionen för programvaruteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-21441.
Full textVan, der Westhuizen Lynette. "Concise analysis and testing of a software model of a satellite remote sensing system used for image generation." Thesis, Stellenbosch : Stellenbosch University, 2014. http://hdl.handle.net/10019.1/96029.
Full textENGLISH ABSTRACT: The capability of simulating the output image of earth observation satellite sensors is of great value, as it reduces the dependency on extensive field tests when developing, testing and calibrating satellite sensors. The aim of this study was to develop a software model to simulate the data acquisition process used by passive remote sensing satellites for the purpose of image generation. To design the software model, a comprehensive study was done of a physical real world satellite remote sensing system in order to identify and analyse the different elements of the data acquisition process. The different elements were identified as being the target, the atmosphere, the sensor and satellite, and radiation. These elements and a signature rendering equation are used to model the target-atmosphere-sensor relationship of the data acquisition process. The signature rendering equation is a mathematical model of the different solar and self-emitted thermal radiance paths that contribute to the radiance reaching the sensor. It is proposed that the software model be implemented as an additional space remote sensing application in the Optronics Sensor Simulator (OSSIM) simulation environment. The OSSIM environment provides the infrastructure and key capabilities upon which this specialist work builds. OSSIM includes a staring array sensor model, which was adapted and expanded in this study to operate as a generic satellite sensor. The OSSIM signature rendering equation was found to include all the necessary terms required to model the at-sensor radiance for a satellite sensor with the exception of an adjacency effect term. The equation was expanded in this study to include a term to describe the in-field-of-view adjacency effect due to aerosol scattering. This effect was modelled as a constant value over the sensor field of view. Models were designed to simulate across-track scanning mirrors, the satellite orbit trajectory and basic image processing for geometric discontinuities. Testing of the software model showed that all functions operated correctly within the set operating conditions and that the in-field-of-view adjacency effect can be modelled effectively by a constant value over the sensor field of view. It was concluded that the satellite remote sensing software model designed in this study accurately simulates the key features of the real world system and provides a concise and sound framework on which future functionality can be expanded.
AFRIKAANSE OPSOMMING: Dit is nuttig om ’n sagteware program te besit wat die gegenereerde beelde van ’n satellietsensor vir aarde-waarneming kan naboots. So ’n sagteware program sal die afhanklikheid van breedvoerige veldwerktoetse verminder gedurende die ontwerp, toetsing en kalibrasie fases van die ontwikkeling van ’n satellietsensor. Die doel van hierdie studie was om ’n sagteware model te ontwerp wat die dataverwerwingsproses van ’n passiewe satelliet afstandswaarnemingstelsel kan naboots, met die doel om beelde te genereer. Om die sagteware model te ontwerp het ’n omvattende studie van ’n fisiese regte wêreld satelliet afstandswaarnemingstelsel geverg, om die verskillende elemente van die dataverwerwingsproses te identifiseer en te analiseer. Die verskillende elemente is geïdentifiseer as die teiken, die atmosfeer, die sensor en satelliet, en vloed. Hierdie elemente, tesame met ’n duimdrukvergelyking, is gebruik om die teiken-atmosfeer-sensor verhouding van die dataverwerwingsproses te modelleer. Die duimdrukvergelyking is ’n wiskundige model van die verskillende voortplantingspaaie van gereflekteerde sonvloed en self-stralende termiese vloed wat bydra tot die totale vloed wat die sensor bereik. Dit is voorgestel dat die sagteware model as ’n addisionele ruimte afstandswaarnemingtoepassing in die ‘Optronics sensor Simulator’ (OSSIM) simulasie-omgewing geïmplementeer word. Die OSSIM simulasie-omgewing voorsien die nodige infrastruktuur en belangrike funksies waarop hierdie spesialis werk gebou kan word. OSSIM het ’n starende-skikking sensor model wat in hierdie studie aangepas is en uitgebrei is om as ’n generiese satellietsensor te funksioneer. Die OSSIM duimdrukvergelyking bevat al die nodige radiometriese terme, behalwe ’n nabyheids-verstrooiing term, om die vloed by die satellietsensor te modeleer. Die duimdrukvergelyking is uitgebrei in hierdie studie om ’n term in te sluit wat die verstrooiing van vloed vanaf naby-geleë voorwerpe, as gevolg van aerosol verstrooiing, kan beskryf. Die nabyheids-verstrooiing is gemodeleer as ’n konstante waarde oor die sigveld van die sensor. Modelle is ontwerp om die beweging van oor-baan skandering-spieëls en die satelliet wentelbaan trajek te bereken. ’n Basiese beeldverwerkings model is ook ontwerp om diskontinuïteite in geometriese vorms in die sensor beelde reg te stel. Toetsing van die sagteware model het gewys dat al die funksies korrek gefunksioneer het binne die limiete van die vasgestelde operasionele voorwaardes. Die toets resultate het ook bewys dat die in-sig-veld nabyheids-verstrooiing akkuraat gemodeleer kan word as ’n konstante waarde oor die sensor sigveld. Daar is tot die gevolgtrekking gekom dat die satelliet afstandswaarneming sagteware model wat in hierdie studie ontwerp is al die belangrikste kenmerke van die werklike wêreld stelsel kan simuleer. Die model vorm ’n beknopte en stewige raamwerk waarop toekomstige werk uitgebrei kan word.
Khim, Chamroeun [Verfasser], and Willi [Akademischer Betreuer] Jäger. "3D Image Processing, Analysis, and Software Development of Khmer Inscriptions / Chamroeun Khim ; Betreuer: Willi Jäger." Heidelberg : Universitätsbibliothek Heidelberg, 2016. http://d-nb.info/1180737024/34.
Full textSong, Yu. "Modelling and analysis of plant image data for crop growth monitoring in horticulture." Thesis, University of Warwick, 2008. http://wrap.warwick.ac.uk/2032/.
Full textKnights, MS. "Flexible shape models for image analysis in an automated lobster catch assessment system." Thesis, Honours thesis, University of Tasmania, 2007. https://eprints.utas.edu.au/3013/2/1_front_Knights.pdf.
Full textEckerberg, Klas. "Etta eller nolla? : landskapsarkitekter, yrkeskunnande och informationsteknologi /." Uppsala : Dept. of Landscape Planning Ultuna, Swedish Univ. of Agricultural Sciences, 2004. http://epsilon.slu.se/a463.pdf.
Full textWestlund, Arvid. "Image analysis tool for geometric variations of the jugular veins in ultrasonic sequences : Development and evaluation." Thesis, Uppsala universitet, Avdelningen för visuell information och interaktion, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-348336.
Full textWang, Chunliang. "Computer Assisted Coronary CT Angiography Analysis : Disease-centered Software Development." Licentiate thesis, Linköping University, Linköping University, Radiology, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-17783.
Full textThe substantial advances of coronary CTA have resulted in a boost of use of this new technique in the last several years, which brings a big challenge to radiologists by the increasing number of exams and the large amount of data for each patient. The main goal of this study was to develop a computer tool to facilitate coronary CTA analysis by combining knowledge of medicine and image processing.Firstly, a competing fuzzy connectedness tree algorithm was developed to segment the coronary arteries and extract centerlines for each branch. The new algorithm, which is an extension of the “virtual contrast injection” method, preserves the low density soft tissue around the coronary, which reduces the possibility of introducing false positive stenoses during segmentation.Secondly, this algorithm was implemented in open source software in which multiple visualization techniques were integrated into an intuitive user interface to facilitate user interaction and provide good over¬views of the processing results. Considerable efforts were put on optimizing the computa¬tional speed of the algorithm to meet the clinical requirements.Thirdly, an automatic seeding method, that can automatically remove rib cage and recognize the aortic root, was introduced into the interactive segmentation workflow to further minimize the requirement of user interactivity during post-processing. The automatic procedure is carried out right after the images are received, which saves users time after they open the data. Vessel enhance¬ment and quantitative 2D vessel contour analysis are also included in this new version of the software. In our preliminary experience, visually accurate segmentation results of major branches have been achieved in 74 cases (42 cases reported in paper II and 32 cases in paper III) using our software with limited user interaction. On 128 branches of 32 patients, the average overlap between the centerline created in our software and the manually created reference standard was 96.0%. The average distance between them was 0.38 mm, lower than the mean voxel size. The automatic procedure ran for 3-5 min as a single-thread application in the background. Interactive processing took 3 min in average with the latest version of software. In conclusion, the presented software provides fast and automatic coron¬ary artery segmentation and visualization. The accuracy of the centerline tracking was found to be acceptable when compared to manually created centerlines.
Gonulsen, Aysegul. "Feature Extraction Of Honeybee Forewings And Hindlegs Using Image Processing And Active Contours." Master's thesis, METU, 2004. http://etd.lib.metu.edu.tr/upload/12604738/index.pdf.
Full textsemi-automated honeybee feature extraction system&rdquo
is presented. The aim is to increase the efficiency by decreasing the time spent on handling these measurements and by increasing the accuracy of measured hindleg and forewing features. The problem is studied from the acquisition of the microscope images, to the feature extraction of the honeybee features. In this scope, suitable methods are developed for segmentation of honeybee hindleg and forewing images. Within intermediate steps, blob analysis is utilized, and edges of the forewing and hindlegs are thinned using skeletonization. Templates that represent the forewing and hindleg edges are formed by either Bezier Curves or Polynomial Interpolation. In the feature extraction phase, Active Contour (Snake) algorithm is applied to the images in order to find the critical points using these templates.
Ferreira, Adriane Pedroso Dias. "MetImage: uma metodologia para desenvolvimento de software para o processamento e análise de imagens." Universidade Federal de Santa Maria, 2006. http://repositorio.ufsm.br/handle/1/8243.
Full textO desenvolvimento de software para processamento e análise de imagens é uma tarefa complexa por utilizar métodos matemáticos para resolver os problemas, por necessitar de uma equipe multidisciplinar e por exigir alto grau de qualidade do software desenvolvido. Portanto, fazer uso de uma metodologia que organize e melhore o processo de desenvolvimento desse tipo de software é de vital importância. A existência de uma metodologia é apontada como um dos primeiros passos em direção ao gerenciamento e a melhoria do processo de desenvolvimento de software. Assim, este trabalho apresenta uma metodologia específica para o desenvolvimento de software para processamento e análise de imagens, chamada nesse trabalho de MetImage. O objetivo dessa metodologia é suprir as deficiências detectadas nas metodologias existentes, tais como o excesso de recursos, burocracia, controle exagerado e falta de documentação, em alguns casos específicos. A metodologia proposta foi implantada no contexto de um grupo de pesquisa. Os principais resultados obtidos foram: a especificação das atividades da equipe, a inclusão de uma etapa de aprendizagem sobre os métodos matemáticos necessários para a implementação das funcionalidades requeridas pelos sistemas e a padronização de código. Além disso, a documentação gerada pode servir de apoio para o entendimento entre especialistas das diferentes áreas que fazem parte do grupo de pesquisa.
Ivarsson, Adam. "Expediting Gathering and Labeling of Data from Zebrafish Models of Tumor Progression and Metastasis Using Bespoke Software." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148691.
Full textSmrt, Richard D., Sara A. Lewis, Robert Kraft, and Linda L. Restifo. "Primary culture of Drosophila larval neurons with morphological analysis using NeuronMetrics." University of Oklahoma, 2015. http://hdl.handle.net/10150/604939.
Full textMagula, Filip. "Software pro zpracování retinálních snímků." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2010. http://www.nusl.cz/ntk/nusl-218653.
Full textColeti, Thiago Adriano. "Um ambiente de avaliação da usabilidade de software apoiado por técnicas de processamento de imagens e reconhecimento de fala." Universidade de São Paulo, 2013. http://www.teses.usp.br/teses/disponiveis/100/100131/tde-06032014-140810/.
Full textFilming and verbalization are considered fundamental usability test methods to support software usability evaluation, due to the reason that allows the evaluator to collect real data about the software interaction capacity and how it influences the user. The tests are, usually, performed by real software users because they can submit the system to several situations that were not presupposed by evaluator in the labs. Although effective, the filming and the verbalization are not efficient due to the reason that require a long time to analyzing the data and identify usability problems. Researches performed in the area present that the time to data analysis is two to ten times the test time. This research aimed to develop an environment that used events as words pronounced and face reactions to support the collect, analysis and identification of interfaces with usability problems easily and safe. The environment is composed by a software to monitoring (background) of the user activities. The software collects key words pronounced by the participant and face images in specific time intervals. Besides these data, snapshots of the interfaces were registered in order to present which interfaces were in used in the event moment. After the collect stage, these data were processed and available to the evaluator with highlights to events that could indicate unsatisfactory events or potential utilization problems. In this research, was possible to conclude that the verbalization events using key words were effective to support the analysis and identification of problematic interfaces because the words were related to specific context that indicated the user opinion. The verbalization activities were more effective in the moments that the data analysis was performed using the face images to support it, allowing more reliable and comprehensive data analysis. In this analysis, the evaluator was able to identify which interfaces were classified negatively by the participant and which was the user focus of view/use in the event moment. In analysis performed using key words and/or not using the face images, the time to identifying the interfaces and potentials usability problems was reduced to less than twice the time of test.
John, Björn, Daniel Markert, Norbert Englisch, Michael Grimm, Marc Ritter, Wolfram Hardt, and Danny Kowerko. "Quantification of geometric properties of the melting zone in laser-assisted welding." Wissenschaftliche Gesellschaft für Lasertechnik e.V, 2017. https://monarch.qucosa.de/id/qucosa%3A21479.
Full textStrand, Mattias. "A Software Framework for Facial Modelling and Tracking." Thesis, Linköping University, Department of Electrical Engineering, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-54563.
Full textThe WinCandide application, a platform for face tracking and model based coding, had become out of date and needed to be upgraded. This report is based on the work of investigating possible open source GUIs and computer vision tool kits that could replace the old ones that are unsupported. Multi platform GUIs are of special interest.
Karuppuswamy, Jaiganesh. "Detection and Avoidance of Simulated Potholes in Autonomous Vehicles in an Unstructured Environment." University of Cincinnati / OhioLINK, 2001. http://rave.ohiolink.edu/etdc/view?acc_num=ucin990731390.
Full textDave, Palak P. "A Quantitative Analysis of Shape Characteristics of Marine Snow Particles with Interactive Visualization: Validation of Assumptions in Coagulation Models." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7279.
Full textMEYER, ANSTETT COLETTE. "Analyse d'images de cellules en culture : description automatique de cellules musculaires lisses vasculaires et suivi de leur comportement." Université Louis Pasteur (Strasbourg) (1971-2008), 1986. http://www.theses.fr/1986STR13063.
Full textOzgenel, Caglar Firat. "Developing A Tool For Acoustical Performance Evaluation Throughout The Design." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614066/index.pdf.
Full textPoulsen, Andrew Joseph. "Real-time Adaptive Cancellation of Satellite Interference in Radio Astronomy." Diss., CLICK HERE for online access, 2003. http://contentdm.lib.byu.edu/ETD/image/etd238.pdf.
Full textPelcat, Yann S. "Soil landscape characterization of crop stubble covered fields using Ikonos high resolution panchromatic images." Thesis, Winnipeg : University of Manitoba, 2006. http://www.collectionscanada.ca/obj/s4/f2/dsk3/MWU/TC-MWU-224.pdf.
Full textA thesis submitted to the Faculty of Graduate Studies in partial fulfillment of the requirements for the degree of Master of Science, Department of Soil Science. Includes bibliographical references.
Kadlec, Jiri. "Design, Development and Testing of Web Services for Multi-Sensor Snow Cover Mapping." BYU ScholarsArchive, 2016. https://scholarsarchive.byu.edu/etd/5727.
Full textAdolphe, Fabienne. "Programme pour l'analyse de la qualité et la stratégie des collecte des données de mono-cristaux avec détecteurs bi-dimensionnels." Grenoble INPG, 1997. http://www.theses.fr/1997INPG0197.
Full textBodnarova, Adriana. "Texture analysis for automatic visual inspection and flaw detection in textiles." Thesis, Queensland University of Technology, 2000.
Find full textBarros, Netto Stelmo Magalhães. "Métodos computacionais para identificação, quantificação e análise de mudanças no tecido da lesão pulmonar através de imagens de tomografia computadorizada." Universidade Federal do Maranhão, 2016. http://tedebc.ufma.br:8080/jspui/handle/tede/1700.
Full textMade available in DSpace on 2017-06-26T19:30:57Z (GMT). No. of bitstreams: 1 Stelmo.pdf: 9433038 bytes, checksum: 2b73bb4f0f32aec1145044fb676465e6 (MD5) Previous issue date: 2016-10-17
Lung cancer is one of the most common types of cancer around the world. Temporal evaluation has become a very useful tool when to whoever needs to analyze a lung lesion. The analysis occurs when a malignant lesion is under treatment or when there are indeterminate lesions, but they are probably benign. The objective from this work is to develop computational methods to detect, quantify and analyze local and global density changes of pulmonary lesions over time. Thus, it were developed four groups of methods to perform this task. The rst identi es local density changes and it has been denominated voxel-based. The second one is composed of the Jensen divergence and the hypothesis test with global and local approaches. Similarly, the third group has only one method, the principal component analysis. The last group has one method, it has been denominated modi ed quality threshold, and identi es the local density changes. In order to reach the objectives, it was proposed a methodology composed of ve steps: The rst step consists in image acquisition of the lesion at various instants. Two image databases were acquired and two models of lesions were created to evaluate the methods. The rst database has 24 lesions under treatment (public database) and the second has 13 benign nodules (private database) in monitoring. The second step refers to rigid registration of the lesion images. The next step is to apply the proposed four groups of methods. As a result, the second group of methods detected more density changes than the fourth group, which in turn, this latter detected more regions than the rst group and this more than the third group, for the public database. For the private database, the fourth group of density change methods detected more regions than the rst group. The third group detected few regions of changes when compared to the rst group and the second group had the lowest number of detected regions. In addition to the density changes found, the proposed classi cation model with texture features had accuracy above 98% in the diagnosis prediction. The results state that there are changes in both databases. However, the detected changes for each group of methods have di erent intensity and location to the databases. This conclusion is based from high accuracy that was obtained from the prediction of the lesion diagnosis from both databases.
O câncer de pulmão é um dos tipos de câncer de maior incidência no mundo. A avaliação temporal aparece como ferramenta bastante útil quando se deseja analisar uma lesão. A análise pode ocorrer quando uma lesão maligna está em tratamento ou quando surgem lesões indeterminadas, mas essas são provavelmente benignas. O objetivo deste trabalho é desenvolver métodos computacionais para detectar, quantifi car e analisar mudanças de densidade locais e globais das lesões pulmonares ao longo do tempo. Desta forma, foram desenvolvidos quatro conjuntos de métodos para realização da tarefa de detectar mudanças de densidade em lesões pulmonares. O primeiro conjunto identifi ca mudanças de densidade locais e foi denominado de métodos baseados em voxel. O segundo conjunto é composto da divergência de Jensen e do teste de hipótese com abordagens locais e globais. Com o mesmo propósito de detectar mudanças de densidade locais em lesões pulmonares, o terceiro conjunto possui um único método, a análise de componentes principais. O último conjunto também possui um único método, denominado de quality threshold modi ficado e identifi ca as mudanças locais de densidade. Para cumprir o objetivo deste trabalho, propõe-se uma metodologia composta de cinco etapas. A primeira etapa consiste na aquisição das imagens da lesão em diversos instantes. Duas bases de lesões foram utilizadas e dois modelos de lesões foram propostos para avaliação dos métodos. A primeira base possui 24 lesões em tratamento (base pública) e a segunda possui 13 nódulos benignos (base privada) em acompanhamento. A segunda etapa corresponde ao registro rígido das imagens da lesão. A próxima etapa é a aplicação dos quatro conjuntos de métodos propostos. Como resultado, o segundo conjunto de métodos detectou mais mudanças de densidade que o quarto conjunto, que por sua vez, este ultimo detectou mais regões que o primeiro conjunto e este mais que o terceiro conjunto, para a base pública de lesões. Em relação a base privada, o quarto conjunto de métodos detectou mais regiões de mudança de densidade que o primeiro conjunto. O terceiro conjunto detectou menos regiões de mudança quando comparado ao primeiro conjunto e o segundo conjunto teve o menor n úmero de regiões detectadas. Em adição às mudanças de densidade encontradas, o modelo de classi ficação proposto com medidas clássicas de textura para predição do diagnóstico da lesão teve acurácia acima de 98%. Os resultados encontrados indicam que existem mudanças de densidade em ambas as bases de lesões pulmonares. Entretanto, as mudanças detectadas por cada um dos métodos propostos possuem características de intensidade e localização diferentes em ambas as bases. Essa conclusão é motivada pela alta acurácia obtida em seu diagnóstico para as bases utilizadas.
Garrigues, Matthieu. "Accélération Algorithmique et Logicielle del’Analyse Vidéo du Mouvement." Electronic Thesis or Diss., Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLY018.
Full textMotion analysis in a video consists in estimating, from a sequence of images, the displacement of the objects projected on the focal plane of a camera, static or mobile. A large number of fields such as robotics, video surveillance, cinema or military applications rely on this analysis to interpret the contentof a video.This problem was one of the first to be approached by researchers in image processing. Numerous solutions have been proposed and allow a sufficiently accurate and robust estimate for a large number of applications. However, the algorithmic complexity of these solutions and/or the lack of optimizations of their software implementations make their use in applications with high computational constraints difficult or impossible.In the work presented in this thesis, we optimized three types of motion analysis taking into account not only the algorithmic complexity, but also all the factors affecting computation time on current processors such as parallelization, memory consumption, the regularity of memory accesses, or the type of arithmetic operations. This led us to develop our thesis at the intersection of software engineering and image processing. Our contributions have enabled the development of real-time applications such as action recognition, video stabilization andsegmentation of mobile objects
Buchanan, Aeron Morgan. "Tracking non-rigid objects in video." Thesis, University of Oxford, 2008. http://ora.ox.ac.uk/objects/uuid:82efb277-abc9-4725-9506-5d114a83bd96.
Full textSilva, Samuel de Sousa. "Left ventricle functional analysis from coronary CT angiography." Doctoral thesis, Universidade de Aveiro, 2012. http://hdl.handle.net/10773/8077.
Full textCoronary CT angiography is widely used in clinical practice for the assessment of coronary artery disease. Several studies have shown that the same exam can also be used to assess left ventricle (LV) function. LV function is usually evaluated using just the data from end-systolic and end-diastolic phases even though coronary CT angiography (CTA) provides data concerning multiple cardiac phases, along the cardiac cycle. This unused wealth of data, mostly due to its complexity and the lack of proper tools, has still to be explored in order to assess if further insight is possible regarding regional LV functional analysis. Furthermore, different parameters can be computed to characterize LV function and while some are well known by clinicians others still need to be evaluated concerning their value in clinical scenarios. The work presented in this thesis covers two steps towards extended use of CTA data: LV segmentation and functional analysis. A new semi-automatic segmentation method is presented to obtain LV data for all cardiac phases available in a CTA exam and a 3D editing tool was designed to allow users to fine tune the segmentations. Regarding segmentation evaluation, a methodology is proposed in order to help choose the similarity metrics to be used to compare segmentations. This methodology allows the detection of redundant measures that can be discarded. The evaluation was performed with the help of three experienced radiographers yielding low intraand inter-observer variability. In order to allow exploring the segmented data, several parameters characterizing global and regional LV function are computed for the available cardiac phases. The data thus obtained is shown using a set of visualizations allowing synchronized visual exploration. The main purpose is to provide means for clinicians to explore the data and gather insight over their meaning, as well as their correlation with each other and with diagnosis outcomes. Finally, an interactive method is proposed to help clinicians assess myocardial perfusion by providing automatic assignment of lesions, detected by clinicians, to a myocardial segment. This new approach has obtained positive feedback from clinicians and is not only an improvement over their current assessment method but also an important first step towards systematic validation of automatic myocardial perfusion assessment measures.
A angiografia coronária por TC (angio-TC) é prática clínica corrente para a avaliação de doença coronária. Alguns estudos mostram que é também possível utilizar o exame de angio-TC para avaliar a função do ventrículo esquerdo (VE). A função ventricular esquerda (FVE) é normalmente avaliada considerando as fases de fim de sístole e de fim de diástole, apesar de a angio-TC proporcionar dados relativos a diferentes fases distribuídas ao longo do ciclo cardíaco. Estes dados não considerados, devido à sua complexidade e à falta de ferramentas apropriadas para o efeito, têm ainda de ser explorados para que se perceba se possibilitam uma melhor compreensão da FVE. Para além disso, podem ser calculados diferentes parâmetros para caracterizar a FVE e, enquanto alguns são bem conhecidos dos médicos, outros requerem ainda uma avaliação do seu valor clínico. No âmbito de uma utilização alargada dos dados proporcionados pelos angio- TC, este trabalho apresenta contributos ao nível da segmentação do VE e da sua análise funcional. É proposto um método semi-automático para a segmentação do VE de forma a obter dados para as diferentes fases cardíacas presentes no exame de angio- TC. Foi também desenvolvida uma ferramenta de edição 3D que permite aos utilizadores a correcção das segmentações assim obtidas. Para a avaliação do método de segmentação apresentado foi proposta uma metodologia que permite a detecção de medidas de similaridade redundantes, a usar no âmbito da avaliação para comparação entre segmentações, para que tais medidas redundantes possam ser descartadas. A avaliação foi executada com a colaboração de três técnicos de radiologia experientes, tendo-se verificado uma baixa variabilidade intra- e inter-observador. De forma a permitir explorar os dados segmentados, foram calculados vários parâmetros para caracterização global e regional da FVE, para as diversas fases cardíacas disponíveis. Os resultados assim obtidos são apresentados usando um conjunto de visualizações que permitem uma exploração visual sincronizada dos mesmos. O principal objectivo é proporcionar ao médico a exploração dos resultados obtidos para os diferentes parâmetros, de modo a que este tenha uma compreensão acrescida sobre o seu significado clínico, assim como sobre a correlação existente entre diferentes parâmetros e entre estes e o diagnóstico. Finalmente, foi proposto um método interactivo para ajudar os médicos durante a avaliação da perfusão do miocárdio, que atribui automaticamente as lesões detectadas pelo médico ao respectivo segmento do miocárdio. Este novo método obteve uma boa receptividade e constitui não só uma melhoria em relação ao método tradicional mas é também um primeiro passo para a validação sistemática de medidas automáticas da perfusão do miocárdio.
Edvinsson, Marcus. "Implementing the circularly polarized light method for determining wall thickness of cellulosic fibres." Thesis, Uppsala universitet, Bildanalys och människa-datorinteraktion, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-174066.
Full textBernd, Arthur Barcellos. "Registros dinâmicos de representação e aprendizagem de conceitos de geometria analítica." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2017. http://hdl.handle.net/10183/175209.
Full textThe Registers of Representation Theory, from Duval, understands and analysis the peculiarity of mathematics objects, accessible through its different representations. Fischbein and Hershkowitz, among others researchers, developed the notions of Mental Image and Conceptual Image to explain the construction process of mathematical concepts by the subject. This dissertation establishes connections between these theories and uses this approach to propose a didactic sequence for teaching some concepts of Analytic Geometry using dynamic representation offered by the GeoGebra software. The proposal was implemented in a 3rd grade private high school. The research is a case study. The analysis of students’ production establishes constant dialog with the theoretical approach and presents results that can be a contribution to research in the area of dynamic representations and learning of school mathematics.
Malmgren, Henrik. "Revision of an artificial neural network enabling industrial sorting." Thesis, Uppsala universitet, Institutionen för teknikvetenskaper, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-392690.
Full text