O objetivo desta tese foi avaliar a interferência da presença de materiais metálicos na imagem radiográfica e tomográfica por meio da análise da adaptação marginal de restaurações e coroas metálicas. Esta investigação resultou em 3 artigos: uma revisão sistemática da literatura para identificar o estado da arte com relação ao uso dos métodos radiográficos; um estudo in vitro comparando o desempenho do filme radiográfico convencional e dos sistemas digitais VistaScan Dürr Dental, Digora Classic Soredex e Express Instrumentarium – com e sem o emprego de filtros para o pós processamento da imagem; e um estudo in vitro avaliando o processamento das imagens da TCFC – utilizando diferentes espessuras de reconstrução. Na revisão sistemática foram incluídos 14 estudos, sendo classificados de baixa ou moderada qualidade, de acordo com os critérios QUADAS de classificação. Na investigação radiográfica (artigo 2), os maiores valores de sensibilidade (0,67 0,83), especificidade (0,81 0,92) e acurácia (0,73 0,86) foram obtidos com radiografias convencionais e imagens digitais originais. Na avaliação tomográfica (artigo 3), os valores da aucROC variaram de 0,60 a 0,72, sendo que o limite inferior do intervalo de confiança mostrou-se abaixo ou muito próximo da linha de referencia. Frente aos resultados, conclui-se que imagens radiográficas originais (convencionais ou digitais) devem ser preferidas para a avaliação de dentes com restaurações metálicas. Quanto à TCFC, mesmo quando se aumenta a espessura de reconstrução da imagem e diminui-se o artefato, ainda assim não há melhora na acurácia do diagnóstico. / The aim of this thesis was to evaluate the interference of the presence of metallic materials on radiographic and tomographic image by assessing misfits tooth and restoration in metal-restored teeth. This investigation resulted in three articles: a systematic review of the literature to identify the state of the art on the use of radiographic methods; an in vitro study comparing the performance of conventional film and digital phosphor plate systems Vistascan Dürr Dental, Digora Classic Soredex and Instrumentarium Express – exported as original images and with the use of post processing filters; and an in vitro study evaluating the post-processing of CBCT images – using diverse reconstruction thicknesses. The systematic review retrived 14 studies, classified as low- / moderate quality based on QUADAS criteria. For radiographic evaluation (article II), higher sensitivity (0.67 0.83), specificity (0.81 0.92) and accuracy (0.73 0.86) values were obtained with conventional and digital original images. For tomographic evaluation (article III), mean aucROC ranged from 0.60 to 0.72, and the analysis of the 95% CI showed the lower bound of the curve bellow or very close to the reference line. Based on the results, it is concluded that original images (conventional or digital) should be preferred for the assessment of teeth with metal restorations. Considering CBCT images, even thought increased reconstruction thickness decreased perceived artifact, it did not improve diagnosis accuracy.

Submitted by JÚLIO HEBER SILVA (julioheber@yahoo.com.br) on 2017-04-05T17:19:40Z No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-04-06T11:07:11Z (GMT) No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-04-06T11:07:11Z (GMT). No. of bitstreams: 2 Dissertação - Afonso Ueslei da Fonseca - 2017.pdf: 9310150 bytes, checksum: 0fc9668df93eccbc288295e41256b328 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-03-27 / According to the World Health Organization (WHO), more than 900,000 children, younger than five years old, have died in 2015 due to pneumonia. Many of these deaths could be avoided with earlier and more accurate diagnosis to provide proper medicine administration. Chest radiography is one of the most recommended test by the WHO in order to detect childhood pneumonia, and it is commonly used in computer aided diagnostic (CAD) systems. A science role is to develop systems that require a more precise medical diagnosis and treatment cost reducing, but mainly death rate decreasing. It is highlighted that quality radiography demands equipments very well installed and calibrated and staff trained to handle them. However, due limited budget resources, mainly in most vulnerable areas, the image quality is significantly damaged, so turning the medical diagnosis harder. Therefore, this work presents a method composed of a set of preprocessing techniques for pediatric radiography. These techniques intend to have simple implementation and low computational cost. The main goal of this work is to increase performance, accuracy and robustness of CAD systems, to improve database standardization and also to collaborate with the professionals training. Thus, techniques were developed, such as, visual quality enhancement, removal of unnecessary or confidential information, reconstruction of degraded areas due to the information removal, orientation correction and definition of a region of interest. All techniques were evaluated using a children chest X-ray database divided into three classes and results show significantly improve when compared to methods presented in literature. We expect these contributions will assist to development and improvement of new systems, construction of more standardized databases, staff training and the development of new techniques. / Segundo a Organização Mundial de Saúde (OMS) mais de 900 mil crianças, menores de cinco anos, foram a óbito em 2015, devido a pneumonia. Muitas dessas mortes poderiam ser evitadas com um diagnóstico mais preciso, precoce e com correta administração de medicamentos. A radiografia de tórax é um dos exames preconizados para detecção de pneumonia pela OMS, sendo comumente usada em sistemas de diagnóstico assistido por computador (CAD). Desenvolver sistemas que apoiem diagnóstico médico mais preciso, reduzam custos de tratamento e principalmente diminuam o número de óbitos é um papel da ciência. Destaca-se que radiografias de qualidade requerem equipamentos devidamente instalados/calibrados e pessoal capacitado para opera-los. Todavia, dado os recursos financeiros limitados, principalmente em áreas mais vulneráveis, a qualidade das imagens fica significativamente comprometida, dificultando o trabalho de diagnóstico pelo médico. Assim, este trabalho traz um método composto por técnicas de pré-processamento de radiografias de tórax pediátricas. As técnicas foram idealizadas para serem de simples implementação e baixo custo computacional. Os principais objetivos do trabalho são promover ganho de performance, acurácia e robustez aos sistemas CAD, favorecer a construção de bases de imagens padronizadas e além disso colaborar com o treinamento de profissionais de saúde. Para atingir esses objetivos foram desenvolvidas técnicas de melhoria da qualidade visual, remoção de informações desnecessárias ou confidenciais e reconstrução das áreas degradadas decorrente da remoção dessas informações, correção de orientação e definição de regiões de interesse. Esse método foi avaliado utilizando uma base de radiografias de tórax infantil divida em três classes e resultados mostram ganhos significativos em comparação a métodos presentes na literatura. Espera-se que essas contribuições favoreçam o aperfeiçoamento de sistemas, construção de bases mais padronizadas, treinamento de profissionais e surgimento de novas técnicas.

Image enhancement improves an image appearance by increasing dominance of some features or by decreasing ambiguity between different regions of the image. Image enhancement techniques have been widely used in many applications of image processing where the subjective quality of images is important for human interpretation. In many cases, the images have lack of clarity and have some effects on images due to fog, low light and other daylight effects exist. So, the images which have these scenarios should be enhanced and made clear to recognize the objects clearly. Histogram-based image enhancement technique is mainly based on equalizing the histogram of the image and increasing the dynamic range corresponding to the image. The Histogram equalization algorithm was performed and tested using different images facing the low light, fog images and colour contrast and succeeded in obtaining enhanced images. This technique is implemented by averaging the histogram values as the probability density function. Initially, we have worked with the MATLAB code on Histogram Equalization and made changes to implement an Application Program Interface i.e., API using Xamarin software. The mobile application developed using Xamarin software works efficiently and has less execution time when compared to the application developed in Android Studio. Debugging of the application is successfully done in both Android and IOS versions. The focus of this thesis is to develop a mobile application on Image enhancement using Xamarin on low light, foggy images.

abstract: Cameras have become commonplace with wide-ranging applications of phone photography, computer vision, and medical imaging. With a growing need to reduce size and costs while maintaining image quality, the need to look past traditional style of cameras is becoming more apparent. Several non-traditional cameras have shown to be promising options for size-constraint applications, and while they may offer several advantages, they also usually are limited by image quality degradation due to optical or a need to reconstruct a captured image. In this thesis, we take a look at three of these non-traditional cameras: a pinhole camera, a diffusion-mask lensless camera, and an under-display camera (UDC). For each of these cases, I present a feasible image restoration pipeline to correct for their particular limitations. For the pinhole camera, I present an early pipeline to allow for practical pinhole photography by reducing noise levels caused by low-light imaging, enhancing exposure levels, and sharpening the blur caused by the pinhole. For lensless cameras, we explore a neural network architecture that performs joint image reconstruction and point spread function (PSF) estimation to robustly recover images captured with multiple PSFs from different cameras. Using adversarial learning, this approach achieves improved reconstruction results that do not require explicit knowledge of the PSF at test-time and shows an added improvement in the reconstruction model’s ability to generalize to variations in the camera’s PSF. This allows lensless cameras to be utilized in a wider range of applications that require multiple cameras without the need to explicitly train a separate model for each new camera. For UDCs, we utilize a multi-stage approach to correct for low light transmission, blur, and haze. This pipeline uses a PyNET deep neural network architecture to perform a majority of the restoration, while additionally using a traditional optimization approach which is then fused in a learned manner in the second stage to improve high-frequency features. I show results from this novel fusion approach that is on-par with the state of the art. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2020

As the world has become more connected meetings have moved online. However, since few have access to studio lighting and uses the embedded webcam the video quality can be far from good. Hence, there is an interest in using a software solution to enhance the video quality in real time. This thesis investigates the feasibility to train a machine learning model to automatically enhance the quality of images. The model must learn without using paired images, since it is difficult to capture images with the exact same content but different quality. Furthermore, the model has to process at least 30 images per second which is a common frequency for videos. Therefore, this thesis investigates the possibility to train a model without paired images and whether such a model can be used in real-time. To answer these questions several sizes of the same model was trained. These were evaluated using six different measures during in order to determine if training without paired data is possible. The models image enhancement capabilities and inference speed were investigated followed by attempts at improving the speed. Finally, different combinations of datasets were investigated to test how well the model generalised to new data. The results show that it is possible to train models for image enhancement without paired data. However, to use such a model in real time a graphics card is needed to reach above 30 images per second.

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / This article proposes an algorithm oriented to the detection of the level of blood filling in patients, with detection capacity in millimeters. The objective of the software is to detect the amount of blood stored into the venipuncture tube and avoid coagulation problems due to excess fluid. It also aims to avoid blood levels below that required, depending on the type of analysis to be performed. The algorithm acquires images from a camera positioned in a rectangular structure located within an enclosure, which has its own internal lighting to ensure adequate segmentation of the pixels of the region of interest. The algorithm consists of an image improvement stage based on gamma correction, followed by a segmentation stage of the area of ​​pixels of interest, which is based on thresholding by HSI model, in addition to filtering to accentuate the contrast between the level of filling and staining, and as a penultimate stage, the location of the filling level due to changes in the vertical tonality of the image. Finally, the level of blood contained in the tube is obtained from the detection of the number of pixels that make up the vertical dimension of the tube filling. This number of pixels is then converted to physical dimensions expressed in millimeters. The validation results show an average percentage error of 0.96% by the proposed algorithm. / Revisión por pares

This thesis investigates the impact of image enhancement techniques on object detection for carsin real-world traffic scenarios. The study focuses on upscaling and light correction treatments andtheir effects on detecting cars in challenging conditions. Initially, a YOLOv8x model is trained on clear static car images. The model is then evaluated on a test dataset captured in real-world driving with images from a front-mounted camera on a car, incorporating various lighting conditions and challenges. The images are then enhanced with said treatments and then evaluated again. The results in this experiment with its specific context show that upscaling seems to decreasemAP performance while lighting correction slightly improves accuracy. Additional training on acomplex image dataset outperforms all other approaches, highlighting the importance of diverse and realistic training data. These findings contribute to advancing computer vision research for object detection models.

Digitization of physical artwork is usually done using image scanning devices in order to ensure that the output is accurate in terms of color and is of sufficiently high resolution, usually over 300 pixels per inch, however the usage of such a device is in some cases unfeasible due to medium or size constraints. Photography of the artwork is another method of artwork digitization, however such methods often produce results containing camera artifacts such as shadows, reflections or low resolution. This thesis project explores the possibility of creating an alternative to image scanners using smartphone photography and machine learning-based methods. Due to the very high memory requirement for enhancing images at very high resolutions, this is done in a two-stage process. The first stage uses an unpaired image style transfer model to remove shadows and highlights. The second stage uses a superresolution model to increase the resolution of the image. The results are evaluated on a small set of paired images using objective metrics and subjective metrics in the form of a user study. In some cases the method removed camera artifacts in the form of reflection and color accuracy, however the best results were achieved when the input data did not contain any major camera artifacts. Based on this it seems likely that style transfer models are not applicable for problems with a wide range of expected input and output. The use of super-resolution seems to be a crucial component of high-resolution image enhancement and the current state-of-the-art methods are able to convincingly increase the resolution of images provided that the input is of a sufficiently high resolution. The subjective evaluation shows that commonly used metrics such as structural similarity and Fréchet Inception Distance are applicable for this type of problem when analyzing the full image, however for smaller details other evaluation methods are required. / Digitalisering av fysiska konstverk görs vanligtvis med bildskannrar för att försäkra att den digitaliserade bilden är färgnoggrann och att upplösningen är tillräckligt hög, vanligtvis över 300 pixlar per tum. Dock är användandet av bildskannrar ibland svårt på grund av konstverkets material eller storlek. Fotografi av konstverk är en annan metod för digitalisering, men denna metod producerar ofta kameraartefakter i form av skuggor, reflektioner och låg upplösning. Detta examensarbete utforskar möjligheten att skapa ett alternativ till bildskannrar genom att använda smartphonefotografi och maskininlärningsbaserade metoder. På grund av de höga minneskraven för bildförbättring med mycket höga upplösningar görs detta i en tvåstegsprocess. Det första steget använder oparad bildstilöversättning för att eliminera skuggor och ljuspunkter. Det andra steget använder en superupplösningsmodell för att öka bildens upplösning. Resultaten utvärderas på en liten mängd parade bilder med objektiva jämförelser och subjektiva jämförelser i form av en användarstudie. I vissa fall reducerade metoden kameraartefakter i form av reflektioner och förbättrade färgexakthet, dock skedde dessa resultat i fall där indatan inte innehöll några större kameraartefakter. Baserat på detta är det sannolikt att stilöversättningsmodeller inte är applicerbara för problem med ett brett omfång av möjliga indata och utdata. Användandet av superupplösning verkar vara en viktig komponent av högupplöst bildförbättring och de bäst presenterande metoderna kan övertygande öka upplösningen av bilder i fall där indatan är av tillräckligt hög upplösning. Den subjektiva utvärderingen visar att vanligt använda utvärderingsmetoder som Fréchet-Inception-avstånd och strukturell likhet är applicerbara för denna typ av problem när de används för att analysera en hel bild, men för mindre detaljer behövs alternativa utvärderingsmetoder.

Corneal diseases are one of the major causes of visual impairment and blindness worldwide. Used for diagnoses, a laser confocal microscope provides a sequence of images, at incremental depths, of the various corneal layers and structures. From these, ophthalmologists can extract clinical information on the state of health of a patient’s cornea. However, many factors impede ophthalmologists in forming diagnoses starting with the large number and variable quality of the individual images (blurring, non-uniform illumination within images, variable illumination between images and noise), and there are also difficulties posed for automatic processing caused by eye movements in both lateral and axial directions during the scanning process. Aiding ophthalmologists working with long sequences of corneal image requires the development of new algorithms which enhance, correctly order and register the corneal images within a sequence. The novel algorithms devised for this purpose and presented in this thesis are divided into four main categories. The first is enhancement to reduce the problems within individual images. The second is automatic image classification to identify which part of the cornea each image belongs to, when they may not be in the correct sequence. The third is automatic reordering of the images to place the images in the right sequence. The fourth is automatic registration of the images with each other. A flexible application called CORNEASYS has been developed and implemented using MATLAB and the C language to provide and run all the algorithms and methods presented in this thesis. CORNEASYS offers users a collection of all the proposed approaches and algorithms in this thesis in one platform package. CORNEASYS also provides a facility to help the research team and Ophthalmologists, who are in discussions to determine future system requirements which meet clinicians’ needs. / The data and image files accompanying this thesis are not available online.

Corneal diseases are one of the major causes of visual impairment and blindness worldwide. Used for diagnoses, a laser confocal microscope provides a sequence of images, at incremental depths, of the various corneal layers and structures. From these, ophthalmologists can extract clinical information on the state of health of a patient’s cornea. However, many factors impede ophthalmologists in forming diagnoses starting with the large number and variable quality of the individual images (blurring, non-uniform illumination within images, variable illumination between images and noise), and there are also difficulties posed for automatic processing caused by eye movements in both lateral and axial directions during the scanning process. Aiding ophthalmologists working with long sequences of corneal image requires the development of new algorithms which enhance, correctly order and register the corneal images within a sequence. The novel algorithms devised for this purpose and presented in this thesis are divided into four main categories. The first is enhancement to reduce the problems within individual images. The second is automatic image classification to identify which part of the cornea each image belongs to, when they may not be in the correct sequence. The third is automatic reordering of the images to place the images in the right sequence. The fourth is automatic registration of the images with each other. A flexible application called CORNEASYS has been developed and implemented using MATLAB and the C language to provide and run all the algorithms and methods presented in this thesis. CORNEASYS offers users a collection of all the proposed approaches and algorithms in this thesis in one platform package. CORNEASYS also provides a facility to help the research team and Ophthalmologists, who are in discussions to determine future system requirements which meet clinicians’ needs.