With the growth of computer power, Digital Image Processing plays a more and more important role in the modern world, including the field of industry, medical, communications, spaceflight technology etc. There is no clear definition how to divide the digital image processing, but normally, digital image processing includes three main steps: low-level, mid-level and highlevel processing. Low-level processing involves primitive operations, such as: image preprocessing to reduce the noise, contrast enhancement, and image sharpening. Mid-level processing on images involves tasks such as segmentation (partitioning an image into regions or objects), description of those objects to reduce them to a form suitable for computer processing, and classification (recognition) of individual objects. Finally, higher-level processing involves "making sense" of an ensemble of recognised objects, as in image analysis. Based on the theory just described in the last paragraph, this thesis is organised in three parts: Colour Edge and Face Detection; Hand motion detection; Hand Gesture Detection and Medical Image Processing. II In Colour Edge Detection, two new images G-image and R-image are built through colour space transform, after that, the two edges extracted from G-image and R-image respectively are combined to obtain the final new edge. In Face Detection, a skin model is built first, then the boundary condition of this skin model can be extracted to cover almost all of the skin pixels. After skin detection, the knowledge about size, size ratio, locations of ears and mouth is used to recognise the face in the skin regions. In Hand Motion Detection, frame differe is compared with an automatically chosen threshold in order to identify the moving object. For some special situations, with slow or smooth object motion, the background modelling and frame differencing are combined in order to improve the performance. In Hand Gesture Recognition, 3 features of every testing image are input to Gaussian Mixture Model (GMM), and then the Expectation Maximization algorithm (EM)is used to compare the GMM from testing images and GMM from training images in order to classify the results. In Medical Image Processing (mammograms), the Artificial Neural Network (ANN) and clustering rule are applied to choose the feature. Two classifier, ANN and Support Vector Machine (SVM), have been applied to classify the results, in this processing, the balance learning theory and optimized decision has been developed are applied to improve the performance.

<p>U disertaciji se predstavljaju istraživanja koja su rezultirala razvojem modela objektivne kontrole otpornosti premaznih papira prema površinskom oštećenju u procesima savijanja. Na bazi analize niza izabranih parametara procesa kontrole, ppedložena su tri obeležja digitalnih uzoraka premaznih papira za opis i ocenu površinskog oštećenja. Rezultati predloženih obeležja, kao i korelacione analize omogućuju primenu tih obeležja u funkciji kontrole kvaliteta kao osnove razvoja objektivne procesne kontrole premaznih papira u procesu savijanja.</p> / <p>The research presented in this dissertation resulted in development of the objective quality control model for fold cracking resistance of coated papers. Based on the analysis of chosen control process parameters, three different features of the digitalised coated paper samples were proposed for describing and classifying surface damages. The results of the proposed features along with their correlation analysis contribute to their usage in objective process quality control of coated papers in the folding process.</p>

Orientador: Carlos Roberto Padovani / Banca: Wilson da Silva Moraes / Banca: José Carlos Martinez / Banca: Marie Oshiwa / Banca: Sandra Fiorelli de Almeida Penteado / Resumo: O presente trabalho investigou a utilização do processamento digital de imagens conjuntamente com a análise de componentes principais e redes neurais artificiais como ferramentas de apoio para uma melhor identificação dos estádios iniciais do desenvolvimento da Sigatoka Negra, em nível de campo, para que medidas de controle sejam adotadas mais rapidamente e, assim, reduzir danos e prejuízos causados pela doença na bananicultura. Foram coletadas imagens digitais de folhas de bananeiras infectadas com a Sigatoka Negra nos estádios 1, 2 e 3, sadia e com fitotoxidez por óleo. A seguir, extraíram-se histogramas dos componentes de imagens no sistema RGB (Red, Green eBlue) para 256 intensidades de cinza das amostras, totalizando 768 variáveis para cada amostra. Com a aplicação de uma técnica de seleção de atributos, a análise de componentes principais, conseguiu-se reduzir as variáveis de entrada de 768 para 11 variáveis canônicas, representado uma redução de 98,6%. Em seguida, considerando-se as variáveis canônicas, realizou-se a fase de classificação com o uso de redes neurais artificiais. De maneira geral, as maiores freqüências de acertos do modelo foram para as classes que mais interessam ao monitoramento da enfermidade, mostrando a robustez do classificador gerado, evidenciada pela baixa probabilidade de classificação incorreta (19%). / Abstract: This study investigated the application, specifically the digital processing of images, with main components analysis and artificial neural networks as tools to support for a better identification of the primaries stages of the Black Sigatoka, in field level, so that control measures are adopted more quickly and consequently it reduces injuries and damages caused by the disease in the banana crops. It were collected digital images of banana leaves infected with Black Sigatoka in stages 1, 2, and 3, healthy and with oil fitotoxity. To proceed, histograms of the components of images were extracted in the system RGB (Red, Green and Blue) for 256 intensities shades of gray of the samples, totaling 768 variables for each sample. With the application of a technique of selection of attributes, the main components analysis, it was possible to reduce the variables of entrance of 768 for 11 canonical variables, represented a reduction of 98,6%. Therefore, being considered the canonical variables, it was accomplished the classification phase with the use of artificial neural networks. In a general way, the largest frequencies of successes of the model went to the classes that more they interest to the control of the diseases, showing the robustness of the generated classifier, evidenced by the low probability of wrong classification (19%). / Doutor

Orientador: Norian Marranghello / Banca: Adilson Gonzaga / Banca: Rodrigo Capobianco Guido / Resumo: A presença de sistemas automatizados é cada vez mais comum para as pessoas. Seus exemplos vão desde máquinas de lavar, que executam praticamente todo o processo de lavagem e secagem de roupas, até linhas de produção em fábricas dos mais diversos produtos. Esses são exemplos de aplicações que exigem pouca interferência humana no processo, já que as etapas realizadas pelos sistemas são bem definidas e iterativas. Porém, outros tipos de processos podem exigir capacidade de discernimento daquele - ou daquilo - que os executam. Para automatizar esse tipo de processo uma das alternativas é o uso de técnicas de inteligência artificial. Esse trabalho visa realizar uma análise comparativa entre técnicas de inteligência artificial, quais sejam Redes Neurais Artificiais e Máquinas de Vetores de Suporte. Com essa análise espera-se estabelecer qual técnica é mais vantajosa para implementação em hardware de sistemas inteligentes, por meio do uso das principais métricas de projeto de circuitos digitais: tamanho do circuito gerado, consumo de energia e desempenho. Para tanto, foram realizados diversos testes com técnicas de pré-processamento e extração de características das imagens para determinar requisitos necessários para o funcionamento do sistema. A partir desses requisitos foram implementadas diversas arquiteturas de sistemas inteligentes para obter-se o classificador mais adequado para resolver o problema. Por fim, o classificador escolhido foi implementado em FPGA na forma de um módulo, o qual se integrará a um sistema maior, para interpretação de imagens digitais para detecção de ervas daninhas em plantações de soja / Abstract: Automated systems have become common for people. Examples range from washing machines, which perform almost the entire cloth washing and drying process, to the production of many products. These are examples of applications that require modest human interference, since the steps taken by the systems are well defined and iterative. However, other processes may require a capacity of judgment of the natural or artificial system performing them. An alternative to automate this kind of process is the use of artificial intelligence techniques. This study aims at a comparative analysis of artificial intelligence techniques, namely Artificial Neural Networks and Support Vector Machines. With this analysis we hope to establish which technique is more advantageous for hardware implementation of an intelligent system, through the use of key metrics for digital circuit design: circuit size, power consumption and performance. Therefore, several tests were performed with image preprocessing and feature extraction techniques to determine requirements for system operation. From these requirements, various architectures for intelligent systems were implemented to obtain the most appropriate classifier to solve the problem. Finally, the chosen classifier was implemented in FPGA as a module to fit into a larger system for digital image interpretation for the detection of weeds in crops of soybeans / Mestre

With the drone industry's recent explosive advancement, aerial photography is becoming increasingly important for an array of applications ranging from construction to agriculture. A drone flyover can give a better overview of regions that are difficult to navigate, and is often significantly faster, cheaper and more accurate than man-made sketches and other alternatives. With this increased use comes a growing need for image processing methods to help in analyzing captured photographs. This thesis presents a method for automatic location detection in aerial photographs using databases of aerial photographs and satellite images. The proposed pipeline is based on an initial round of tests, performed by using existing feature detection, description and matching algorithms on aerial photographs with a high degree of similarity. After which further modifications and improvements were implemented to make the method functional also for handling aerial photographs with a high level of inherent differences, e.g., viewpoint changes, different camera- and lens parameters, temporary objects and weather effects. The method is shown to yield highly accurate results in geographical regions containing features with a low level of ambiguity, and where factors like viewpoint difference are not too extreme. In particular, the method has been most successful in cities and some types of farmland, producing very good results compared to methods based on camera parameters and GPS-location, which have been common in automatic location detection previously. Knowledge of these parameters is not necessary when applying the method, making it applicable more generally and also independently of the precision of the instruments used to determine said parameters.  Furthermore, the approach is extended for automatic processing of video streams. With lack of available ground truth data, no definite conclusions about absolute accuracy of the method can be drawn for this use case. But it is nevertheless clear that processing speeds can be greatly improved by making use of the fact that subsequent video snapshots have a large graphical overlap. And it can indeed also be said that, for the tested video stream, using a type of extrapolation can greatly reduce the risk of graphical noise making location detection impossible for any given snapshot. / Då drönarindustrin växer så det knakar, har flygfoton blivit allt viktigare för en rad applikationer i vårt samhälle. Att flyga över ett svårnavigerat område med en drönare kan ge bättre översikt och är ofta snabbare, billigare och mer precist än skisser eller andra alternativa översiktsmetoder. Med denna ökade användning kommer också ett ökat behov av automatisk bildprocessering för att hjälpa till i analysen av dessa fotografier. Denna avhandling presenterar en metod för automatisk positionsbedömning av flygfoton, med hjälp av databaser med flygfoton och satellitfoton. Den presenterade metoden är baserad på inledande tester av existerande feature detection, feature description och feature matching algoritmer på ett något förenklat problem, där givna foton är väldigt grafiskt lika. Efter detta implementerades ytterligare modifikationer och förbättringar för att göra metoden mer robust även för bilder med en hög nivå av grafisk diskrepans, exempelvis skillnad i synvinkel, kamera- och linsparametrar, temporära objekt och vädereffekter. Den föreslagna metoden ger nöjaktiga resultat i geografiska regioner med en proportionellt stor mängd grafiska särdrag som enkelt kan särskiljas från varandra och där den grafiska diskrepansen inte är allt för stor. Särskilt goda resultat ses i bland annat städer och vissa typer av jordbruksområden, där metoden kan ge betydligt bättre resultat än metoder baserade på kända kameraparametrar och fotografens GPS-positionering, vilket har varit ett vanligt sätt att utföra denna typ av automatisk positionsbestämning tidigare. Dessutom är den presenterade metoden ofta enklare att applicera, då precisionen för diverse mätinstrument som annars måste användas när fotot tas inte spelar in alls i metodens beräkningar. Dessutom har metoden utökats för automatisk processering av videoströmmar. På grund av bristfälligt referensdata kan inga definitiva slutsatser dras angående metodens precision för detta användningsområde. Men det är ändå tydligt att beräkningstiden kan minskas drastiskt genom att använda faktumet att två påföljande ögonblicksbilder har ett stort grafiskt överlapp. Genom att använda en sorts extrapolering kan inverkan från grafiskt brus också minskas, brus som kan göra positionsbestämning omöjligt för en given ögonblicksbild.

O presente trabalho consiste na elaboração de uma metodologia envolvendo técnicas computacionais para proporcionar informações provenientes de avaliação de qualidade de equipamentos mamográficos. A investigação conduzida levou em conta, além da necessária determinação de parâmetros operacionais - como tensão de pico (kVp), corrente de tubo, ponto focal, dose, tempo de exposição, camada semi-redutora -, a influência das características do digitalizador usado no processo de digitalização das imagens a ser avaliadas pelo esquema computacional, seja esse um sistema de aquisição digital direta ou indireta. Dessa forma, foi elaborado um protocolo de pré-processamento da imagem para compensar os efeitos do digitalizador antes da avaliação dos parâmetros de qualidade através dela. Simultaneamente ao desenvolvimento dos softwares necessários ao esquema, foi projetado e desenvolvido um simulador radiográfico para servir como instrumento para obtenção tanto das imagens a ser processadas pelo modelo computacional, como dos dados referentes aos parâmetros operacionais. O sistema foi desenvolvido tomando um mamógrafo calibrado e um instrumento de precisão como referências e testado em outros equipamentos mamográficos em operação em clínicas e hospitais. Os resultados foram consistentes com as análises comparativas utilizando as referências, o que podem fazer do sistema uma ferramenta útil na avaliação de qualidade em mamografia. / The present work consists on developing a computational methodology to provide information regarding to mammographic equipment quality evaluation. This investigation have taken into account, beyond the required operational parameters, such as kVp, electrical current, focal point, dose, exposition time, half-value layer, the influence of the film digitizer utilized for digitization process on the images to be evaluated by the computational scheme, either this a system of direct or indirect digital acquisition. Like so, it was elaborated an image pre-processing protocol to compensate the digitization effect on digital image, before the evaluation of quality control parameters through itself. Simultaneously to the development of the necessary software to the system, a radiographic phantom was developed to be used for achievement of either the images to be processed by the computational model, as operational parameters data. The system was developed taking calibrated mammographic equipment and a precise measurement instrument as references, besides, it was tested in other mammographic equipment in operation on clinics and hospitals. Results had shown consistent with the comparative analyses using those references, which can turn this system a useful tool for evaluation of mammography quality.

Podemos afirmar que deslocamentos da imagem em quadros consecutivos de uma seqüência de vídeo são causados por pequenas vibrações da câmera e/ou movimentos desejados pelo operador da câmera. A estabilização de imagem consiste no processo de remoção de pequenas vibrações que caracterizam movimentos indesejados de uma seqüência de imagens. Com este propósito, atualmente técnicas de processamento digital de vídeo vêm sendo comumente aplicadas na indústria eletrônica. No processo digital de estabilização de imagens são necessários métodos computacionais de estimação, de suavização e de correção de movimento, para os quais, existe uma grande variedade de técnicas de processamento. O emprego de uma técnica específica de processamento é determinado conforme o tipo de aplicação. Técnicas para a estimação de movimento como casamento de blocos (CB), e para a suavização de movimento como filtro de freqüência passa baixa, são freqüentemente encontradas na literatura. Este trabalho apresenta um sistema de estabilização digital de imagens em tempo real capturadas por uma câmera digital, estimando e compensando movimentos translacionais e rotacionais indesejados. / Undesirable shakes or jiggles, object motion within image or desirable motions caused by the camera operator causes image differences in consecutive frames of video sequences. The image stabilization consists of the process of removing inevitable and undesirable fluctuations, shakes and jiggles; with this purpose, nowadays digital processing techniques have been commonly applied in the electronic industry. On the digital processing of image stabilization, computational methods of estimation, smoothing and motion correction are necessary. In the literature various digital processing techniques for image stabilization are described, the most suitable technique should be chosen according to the kind of application. Techniques such as block matching used in motion estimation and low-pass filters used in motion smoothing are found in a great number of papers. This work presents a real time digital image stabilization system capable of stabilizing video sequences with undesirable translational and rotational displacements between frames.

As condições físicas do ambiente, pretéritas e atuais, determinam variações quanto à estrutura e distribuição dos manguezais ao longo das áreas litorâneas. O presente estudo visa caracterizar as tendências da dinâmica de bosques de mangue do Sistema Cananéia-Iguape. Tratamento de imagens digitais e dinâmica de feições sedimentares na região forneceram subsídios para o presente estudo. O Sistema Cananéia-Iguape está localizado no extremo sul do Estado de São Paulo (Brasil), latitude de 25oS. Imagens digitais TM/Landsat5, WRS 220/77 D, composição colorida (RGB) TM4/TM3/TM2, de duas datas (14/09/86 e 02/09/99) foram tratadas no SIG ILWIS (Integrated Land and Water Information System). Os pontos de amostragem de estrutura dos bosques de mangue e de topografia foram escolhidos considerando-se os resultados da classificação superviosionada e da dinâmica sedimentar das feições de deposição no sistema, segundo Tessler (1982) e Tessler & Furtado (1983). Para estudo da estrutura dos bosques de mangue adotou-se metodologia de Schaeffer-Novelli & Cintrón (1986). Análise de agrupamento por ligação simples confirmou os resultados obtidos no tratamento de dados de estrutura dos bosques de mangue. A dinâmica sedimentar e a topografia são fatores que determinam a colonização por determinadas espécies de mangue em feições de deposição. / Past and current environment conditions drive changes to mangrove structure and distribuition along the coast. This paper aims to caracterize mangrove forest dynamic tendencies at Cananeia-Iguape System. Digital image processing and region morphodynamics support the present study. Cananeia-Iguape System is located at the South of São Paulo State (Brazil), latitude 25oS. A colored composition (RGB TM4/TM3/TM2) of Landsat TM digital images (WRS 220/77D) from different dates (14/09/86 and 02/09/99) were processed with ILWIS SIG (Integrated Land and Water Information System). Mangrove forest structure and topographic sampling spots were chosen given the results of supervised classification and given its sedimentary morphodynamic deposition, following Tessler (1982) and Tessler & Furtado (1983). Mangrove forest structure study is based on Cintrón & Schaeffer-Novelli (1984). Single linkage cluster analysis has confirmed the results obtained from the mangrove forest structure study. Region sedimentary dynamics and topographic factors drive mangrove colonization by particular species on deposition shores.

É apresentado o desenvolvimento de um modelo computacional que visa relacionar imagens digitais obtidas em diferentes escalas e resoluções com aplicação de Wavelets. Seu desenvolvimento encontra-se no contexto multidisciplinar e situa-se na intersecção das linhas de pesquisa de áreas da Física, da Matemática e da Computação. Desta forma, optou-se na implementação por uma abordagem computacional dos estudos, com aplicação em imagens digitais provenientes da reconstrução de dados de tomografia computadorizada de Raios-X. Resultados indicam que a implementação do modelo computacional desenvolvido tem sua funcionalidade comprovada, uma vez que os atributos vetoriais dos objetos considerados para análise (poros) foram mantidos estáveis em diferentes resoluções estudadas. O modelo foi implementado em linguagem de programação C++ com uso de orientação a objetos e organizado em classes. Adicionalmente, sua aplicação é viabilizada para diversas plataformas computacionais no que tange a sistemas operacionais e processadores. Do ponto de vista científico, o sistema resultante, além de ser uma ferramenta importante no estudo de meios porosos através de imagens de tomografia computadorizada por Raios-X, contribui com métodos inovadores que fazem uso de Wavelets e são aplicados na suavização de bordas por técnica sub-pixel, na otimização de desempenho e no processamento de dados para interpolação / This work consists of the development of a computational model aimed at relating digital images obtained on different scales and resolutions to the application of Wavelets. The development of this model lies within a multidisciplinary context, at the intersection of the research lines of areas of Physics, Mathematics and Computation. The choice of these studies therefore fel1 on a computational approach, with the application of digital images originating from the reconstruction of computerized tomographic X-ray data. The results of the implementation of the computational model developed here confirm the model\'s functionality, since the vectorial attributes of the objects utilized for our analysis (pores) remained stable under different resolutions. The model was implemented in the C++ programming language using object orientation, and the model\'s methods were organized into classes based on their application on different computational platforms, from the standpoint of operational systems and processors. In the scientific point of view, the resulting system is an important tool in the porous means researches using computerized tomography by X-rays and it has exclusive methods. These methods use Wavelets and they have application in edge smoothing processes by sub-pixel technique, in optimizing processing time and in data processing for interpolation

Les nouvelles technologies d'imagerie basées sur la tomodensitométrie en coupe permettent l'évaluation de très haute qualité de la structure 3D de l'aorte thoracique. La reconstruction virtuelle et les modèles géométriques de l'aorte sont indispensables à l'exploitation des images dont le temps de traitement manuel reste cependant considérable et les outils numériques insuffisants ou inadaptés pour mesurer correctement sa morphologie. L'aorte n'est pas un simple tube de conduction du sang mais un organe de régulation de la pulsatilité des ondes de pression provoquées par l'éjection cardiaque. Ses désordres biomécaniques peuvent accélérer la formation de calcifications dans sa paroi et entrainer des risques de graves complications, comme les anévrismes et les dissections. La réparation aortique basée sur l'implantation d'endoprothèses est en pleine évolution et requiert des renseignements morphologiques précis pour en améliorer le taux de succès. Notre objectif a été d'étudier la géométrie tridimensionnelle de l'aorte en développant des algorithmes appropriés. Une plateforme informatique a été conçue et testée pour étudier trois pathologies de l'aorte: l'athérosclérose calcifiée, l'anévrisme et la dissection. L'hypothèse du travail a été que la géométrie spécifique des artères de chaque individu joue un rôle complémentaire à celui des facteurs de risque traditionnels dans le développement de ces pathologies. Notre premier travail a montré que trois facteurs résument 80% de la variabilité géométrique de l'aorte thoracique: le volume aortique, le déroulement et la symétrie de l'arche aortique, avec des taux de variabilité respectifs de 46%, 22% et 12%. Dans deux travaux suivants, nous avons montré que les calcifications de l'aorte thoracique se concentrent principalement dans la crosse et dans le segment descendant proximal, et que cette distribution était associée à la morphologie de l'aorte indépendamment de l'âge, du sexe, de la surface corporelle et des facteurs de risque traditionnels. Le quatrième travail a montré que le score de dépôt calcique dans toute l'aorte thoracique incluant la crosse était plus étroitement associé aux complications non-cardiaques, vasculaires périphériques et cérébrales, que le score traditionnel de calcium coronaire. Il faut noter que la crosse aortique n'est pas visualisée dans les études de routine de calcium coronaire sans injection. Le cinquième travail décrit un modèle déformable capable de segmenter la lumière aortique dans un contexte pathologique. Il a été appliqué pour étudier de façon automatisée la taille d'un anévrisme abdominal avant et après la pose d'une endoprothèse. Dans le dernier travail, la méthode précédente a été adaptée pour étudier la géométrie aortique des patients atteints de dissection comparativement à un groupe témoin de patients qui en étaient indemnes. Trois variables géométriques ont été identifiées dans le modèle de prédiction du risque de dissection: le diamètre de la crosse, la longueur de l'aorte thoracique et l'âge. En conclusion, nos résultats montrent que les maladies aortiques sont étroitement associées à la géométrie de l'aorte indépendamment des facteurs de risque traditionnels. Les algorithmes que nous avons développés ouvrent la voie à l'automatisation et à une réduction de la variabilité des mesures. / New imaging technologies, including those associated with multislice computed tomography, allow to evaluate the structure of the thoracic aorta in 3D with an impressive resolution. Aortic virtual reconstruction and geometric modeling are essential for imaging evaluation because manual measurements are time-consuming, and the available tools still need to be adapted to complex aortic morphologies. The aorta is more than a simple tubular conduit vessel for blood. It also regulates the pulsatile pressure waves that are injected into the arterial system by the left ventricle. The biomechanical disorders produced by these waves can accelerate the formation of calcium deposits within the arterial wall. Furthermore, they are thought to be responsible for severe aortic complications, including aneurysms and dissections. Endovascular aortic repair is a modern technique based on the implantation of an endograft to restore the normal blood flow. Precise morphological measurements are required to improve this technique, for both surgery planning and patient follow up. Our objective was to develop original algorithms to study the aortic geometry in 3D. A computing platform was designed and tested to analyze three main aortic pathologies: calcified atherosclerosis, aneurysms and dissections. The hypothesis of our study was that the individual arterial geometry of a subject plays a complementary role in the development of vascular pathologies beyond traditional risk factors. Our first work revealed that 80% of the total geometric variability in the thoracic aorta might be explained using 3 factors: the aortic volume, the aortic arc unfolding and its asymmetry. Variability percentages accounted for 46%, 22% and 12%, respectively. The next 2 works, showed that calcifications in the thoracic aorta were concentrated in the aortic arch and in the proximal descending segment. This spatial distribution was associated with aortic morphology, independently of age, sex, body surface area and traditional risk factors. Our fourth article revealed that calcium deposits in the entire thoracic aorta (including the aortic arch) was associated with non-cardiac events, beyond the standard coronary artery calcium score. It is noteworthy that the aortic arch region is systematically excluded from standard scans. Our fifth manuscript described a novel deformable model applied to the aortic segmentation under pathological contexts. It was used to estimate the size and shape of abdominal aneurysms before and after endograft implantation. In the last work, this method was adapted to study the geometry of the thoracic aorta of patients with an aortic dissection with respect to a control group. Three anatomic variables were identified for the risk prediction model: the aortic arch diameter, the thoracic aortic length and the age of the patient. In conclusion, our results show that aortic diseases are closely associated with aortic geometry, independently from traditional risk factors. The developed algorithms improved the automation of measurements and reduced the variability of the estimations.