Στη συγκεκριμένη εργασία περιγράφουμε τρόπους κατάτμησης εικόνας ενώ ταυτόχρονα δίνουμε μια συνοπτική περιγραφή των χρωματικών χώρων και κάποιων βασικών αρχών της χρωματομετρίας. Στη συνέχεια συγκρίνουμε την αποδοτικότητα και σθεναρότητα των μεθόδων αυτών πάνω σε εικόνες υφασμάτων διαφορετικού χρώματος. Η σύγκριση αυτή γίνεται με βάση τα ιδιαίτερα χαρακτηριστικά των εικόνων (εικόνες π.χ. με περίπλοκα σχέδια παρουσιάζουν διαφορετική συμπεριφορά από άλλες με ένα μόνο σχέδιο) καθώς επίσης δίνεται ιδιαίτερη προσοχή στη δυνατότητα εξαγωγής αξιόπιστων αποτελεσμάτων στην περίπτωση όπου έχουμε εφαρμόσει υποδειγματοληψία. Τα αποτελέσματα αυτά σχολιάζονται στο τελευταίο κομμάτι της εργασίας όπου παρατίθενται τα αποτελέσματα που λάβαμε με τη χρήση του ΜATLAB. / -

Optimization methods have been widely utilized in the field of imaging science, such as image denoising, image segmentation, image contrast adjustment, high dynamic rang imaging, etc. In recent decades, it is becoming more and more popular to re- formulate an image processing problem into an energy minimization problem, then solve for the minimizer by some optimization based methods. In this thesis, we concern solving three popular issues in image processing and computational photography by optimization based methods, which are image segmentation, bit-depth expansion, and high dynamic range image tone mapping problems. The contribution of this thesis can be illustrated in three parts separately according to different topics. For the image segmentation problem, we present a multi-phase image segmentation model based on the histogram of the Gabor feature space, which consists of responses from a set of Gabor filters with various orientations, scales and frequencies. Our model replaces the error function term in the original fuzzy region competition model with squared 2-Wasserstein distance function, which is a metric to measure the distance of two histogram. The energy functional is minimized by alternating direction method of multiplier, and the existence of the closed-form solutions is guaranteed when the exponent of the fuzzy membership term being 1 or 2. The experimental results show the advantage of our proposed method compared to other recent methods. As for the bit-depth expansion problem, we develop a variational approach containing an energy functional to determine a local mapping function for bit-depth expansion via a smoothing technique, such that each pixel can be adjusted locally to a high bit-depth value. In order to enhance the contrast of the low bit-depth images, we make use of the histogram equalization technique for such local mapping function. Both bit-depth expansion and histogram equalization terms can be combined together into the resulting objective function. In order to minimize the differences among the local mapping functions at the nearby pixel locations, the spatial regularization of the mapping is incorporated in the objective function. Regarding the tone mapping problem for high dynamic range images, we pro- pose a computational tone mapping operator which makes use of a localized gamma correction. Our tone mapping operator combines the two subproblems in the tone mapping problem, i.e. luminance compression and color rendering, into one general framework. The bright regions and dark regions can be distinguished and treated differently. In our method, we propose two adjustment rules according to the perceptual preference of human visual system towards contrast and colors respectively. The resulting tone mapped images have a natural looking and the highest score in our observer subjective test. Based on the motivation of our computational tone mapping operator, we propose a variational method for image tone mapping problem. The core idea is to minimize the difference of the local contrast between the tone mapped image and the high dynamic range image under some constraints. The energy functional contains a local contrast fidelity term and a L-2 total variation regularization term. Local gamma correction is also applied as our previous computational model and the unknown variables are the non-uniform gamma values. The non-uniform gamma values for each pixel can be obtained by minimizing the fidelity term, while the smoothing term ensures the gamma values for nearby pixels not varying too much from each other. The results by both our computational and variational tone mapping operators show advantage in preserving the detailed image contents in the bright and dark regions. Keywords: optimization, alternating direction method of multipliers, variational model, image segmentation, Mumford-Shah model, Gabor filter, contrast adjustment, histogram equalization, bit-depth expansion, dynamic range, HDR imaging, tone mapping operators, gamma correction, color rendering.

Medical image analysis is a ubiquitous and essential part of modem health care. A crucial first step to this is segmentation, which is often complicated by many factors including subject diversity, pathology, noise corruption, and poor image resolution. Traditionally, manual tracing by experts was done. While considered accurate, this process is time consuming and tedious, especially when performed slice-by-slice on three-dimensional (3D) images over large datasets or on two-dimensional (2D) but topologically complicated images such as a retinography. On the other hand, fully-automated methods are typically faster, but work best with data-dependent, carefully tuned parameters and still require user validation and refinement. This thesis contributes to the field of medical image segmentation by proposing a highly-automated, interactive approach that effectively merges user knowledge and efficient computing. To this end, our work focuses on graph-based methods and offer globally optimal solutions. First, we present a novel method for 3D segmentation based on a 3D Livewire approach. This approach is an extension of the 2D Livewire framework, and this method is capable of handling objects with large protrusions, concavities, branching, and complex arbitrary topologies. Second, we propose a method for efficiently segmenting 2D vascular networks, called ‘Live-Vessel’. Live-Vessel simultaneously extracts vessel centrelines and boundary points, and globally optimizes over both spatial variables and vessel radius. Both of our proposed methods are validated on synthetic data, real medical data, and are shown to be highly reproducible, accurate, and efficient. Also, they were shown to be resilient to high amounts of noise and insensitive to internal parameterization. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

The segmentation of medical images is a difficult task due to the inhomogeneous intensity variations that occurs during digital image acquisition, the complicated shape of the object, and the medical expert’s lack of semantic knowledge. Automated segmentation algorithms work well for some medical images, but no algorithm has been general enough to work for all medical images. In practice, most of the time the segmentation results are corrected by the experts before the actual use. In this work, we are motivated to determine how to make use of manually segmented data in automatic segmentation. The key idea is to transfer the ground truth segmentation from the database of train images to a given test image. The ground truth segmentation of MR images is done by experts. The process includes a hierarchical image decomposition approach that performs the shape matching of test images at several levels, starting with the image as a whole (i.e. level 0) and then going through a pyramid decomposition (i.e. level 1, level 2, etc.) with the database of the train images and the given test image. The goal of pyramid decomposition is to find the section of the training image that best matches a section of the test image of a different level. After that, a re-composition approach is taken to place the best matched sections of the training image to the original test image space. Finally, the ground truth segmentation is transferred from the best training images to their corresponding location in the test image. We have tested our method on a hip joint MR image database and the experiment shows successful results on level 0, level 1 and level 2 re-compositions. Results improve with deeper level decompositions, which supports our hypotheses.

Image processing consists of a series of tasks which widely appear in many areas. It can be used for processing photos taken by people's cameras, astronomy radio, radar imaging, medical devices and tomography. Among these tasks, image segmentation is a fundamental task in a series of applications. Image segmentation is so important that it attracts hundreds of thousands of researchers from lots of fields all over the world. Given an image, the goal of image segmentation is to classify all pixels into several classes. Given an image defined over a domain, the segmentation task is to divide the domain into several different sub-domains such that pixels in each sub-domain share some common information. Variational methods showcase their performance in all kinds of image processing problems, such as image denoising, image debluring, image segmentation and so on. They can preserve structures of images well. In recent decades, it is more and more popular to reformulate an image processing problem into an energy minimization problem. The problem is then minimized by some optimization based methods. Meanwhile, convolutional neural networks (CNNs) gain outstanding achievements in a wide range of fields such as image processing, nature language processing and video recognition. CNNs are data-driven techniques which often need large datasets for training comparing to other methods like variational based methods. When handling image processing tasks with large scale datasets, CNNs are the first selections due to their superior performances. However, the class of each pixel is predicted independently in semantic segmentation tasks which are dense classification problems. Spatial regularity of the segmented objects is still a problem for these methods. Especially when given few training data, CNNs could not perform well in the details. Isolated and scattered small regions often appear in all kinds of CNN segmentation results. In this thesis, we successfully add spatial regularization to the segmented objects. In our methods, spatial regularization such as total variation (TV) can be easily integrated into CNNs and they produce smooth edges and eliminates isolated points. Spatial dependency is a very important prior for many image segmentation tasks. Generally, convolutional operations are building blocks that process one local neighborhood at a time, which means CNNs usually don't explicitly make use of the spatial prior on image segmentation tasks. Empirical evaluations of the regularized neural networks on a series of image segmentation datasets show its good performance and ability in improving the performance of many image segmentation CNNs. We also design a recurrent structure which is composed of multiple TV blocks. By applying this structure to a popular segmentation CNN, the segmentation results are further improved. This is an end-to-end framework to regularize the segmentation results. The proposed framework could give smooth edges and eliminate isolated points. Comparing to other post-processing methods, our method needs little extra computation thus is effective and efficient. Since long range dependency is also very important for semantic segmentation, we further present non-local regularized softmax activation function for semantic image segmentation tasks. We introduce graph operators into CNNs by integrating nonlocal total variation regularizer into softmax activation function. We find the non-local regularized softmax activation function by the primal-dual hybrid gradient method. Experiments show that non-local regularized softmax activation function can bring regularization effect and preserve object details at the same time

No description available.

Despite facing technical issues (e.g., overfitting, vanishing and exploding gradients), deep neural networks have the potential to capture complex patterns in data. Understanding how depth impacts neural networks performance is vital to the advancement of novel deep learning architectures. By varying hyperparameters on two sets of architectures with different depths, this thesis aims to examine if there are any potential benefits from developing deep networks for segmenting intracranial aneurysms from 3D TOF-MRA scans in the ADAM dataset. / Master of Science / With the technologies we have today, people are constantly generating data. In this pool of information, gaining insight into the data proves to be extremely valuable. Deep learning is one method that allows for automatic pattern recognition by iteratively improving the disparity between its prediction and the ground truth. Complex models can learn complex patterns, and such models introduce challenges. This thesis explores the potential benefits of deep neural networks whether they stand to gain improvement despite the challenges. The models will be trained to segment intracranial aneurysms from volumetric images.

The subject of digital image analysis deals with extracting relevant information from image data, stored in digital form in a computer. A fundamental problem in image analysis is image segmentation, i.e., the identification and separation of relevant objects and structures in an image. Accurate segmentation of objects of interest is often required before further processing and analysis can be performed. Despite years of active research, fully automatic segmentation of arbitrary images remains an unsolved problem. Interactive, or semi-automatic, segmentation methods use human expert knowledge as additional input, thereby making the segmentation problem more tractable. The goal of interactive segmentation methods is to minimize the required user interaction time, while maintaining tight user control to guarantee the correctness of the results. Methods for interactive segmentation typically operate under one of two paradigms for user guidance: (1) Specification of pieces of the boundary of the desired object(s). (2) Specification of correct segmentation labels for a small subset of the image elements. These types of user input are referred to as boundary constraints and regional constraints, respectively. This thesis concerns the development of methods for interactive segmentation, using a graph-theoretic approach. We view an image as an edge weighted graph, whose vertex set is the set of image elements, and whose edges are given by an adjacency relation among the image elements. Due to its discrete nature and mathematical simplicity, this graph based image representation lends itself well to the development of efficient, and provably correct, methods. The contributions in this thesis may be summarized as follows: Existing graph-based methods for interactive segmentation are modified to improve their performance on images with noisy or missing data, while maintaining a low computational cost. Fuzzy techniques are utilized to obtain segmentations from which feature measurements can be made with increased precision. A new paradigm for user guidance, that unifies and generalizes regional and boundary constraints, is proposed. The practical utility of the proposed methods is illustrated with examples from the medical field.

As demand for real-time image processing increases, the need to improve the efficiency of image processing systems is growing. The process of image segmentation is often used in preprocessing stages of computer vision systems to reduce image data and increase processing efficiency. This dissertation introduces a novel image segmentation approach known as leap segmentation, which applies a flexible definition of adjacency to allow groupings of pixels into segments which need not be spatially contiguous and thus can more accurately correspond to large surfaces in the scene. Experiments show that leap segmentation correctly preserves an average of 20% more original scene pixels than traditional approaches, while using the same number of segments, and significantly improves execution performance (executing 10x - 15x faster than leading approaches). Further, leap segmentation is shown to improve the efficiency of a high-level vision application for scene layout analysis within 3D scene reconstruction. The benefits of applying image segmentation in preprocessing are not limited to single-frame image processing. Segmentation is also often applied in the preprocessing stages of video analysis applications. In the second contribution of this dissertation, the fast, single-frame leap segmentation approach is extended into the temporal domain to develop a highly-efficient method for multiple-frame segmentation, called video leap segmentation. This approach is evaluated for use on mobile platforms where processing speed is critical using moving-camera traffic sequences captured on busy, multi-lane highways. Video leap segmentation accurately tracks segments across temporal bounds, maintaining temporal coherence between the input sequence frames. It is shown that video leap segmentation can be applied with high accuracy to the task of salient segment transformation detection for alerting drivers to important scene changes that may affect future steering decisions. Finally, while research efforts in the field of image segmentation have often recognized the need for efficient implementations for real-time processing, many of today’s leading image segmentation approaches exhibit processing times which exceed their camera frame periods, making them infeasible for use in real-time applications. The third research contribution of this dissertation focuses on developing fast implementations of the single-frame leap segmentation approach for use on both single-core and multi-core platforms as well as on both high-performance and resource-constrained systems. While the design of leap segmentation lends itself to efficient implementations, the efficiency achieved by this algorithm, as in any algorithm, is can be improved with careful implementation optimizations. The leap segmentation approach is analyzed in detail and highly optimized implementations of the approach are presented with in-depth studies, ranging from storage considerations to realizing parallel processing potential. The final implementations of leap segmentation for both serial and parallel platforms are shown to achieve real-time frame rates even when processing very high resolution input images. Leap segmentation’s accuracy and speed make it a highly competitive alternative to today’s leading segmentation approaches for modern, real-time computer vision systems.

Orientadores: Alexandre Campane Vidal, Alexandre Xavier Falcão / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica e Instituto de Geociências / Made available in DSpace on 2018-08-22T17:02:26Z (GMT). No. of bitstreams: 1 MingireanovFilho_Ivan_M.pdf: 33856245 bytes, checksum: 516137beeec348cf169f06272d16b0cb (MD5) Previous issue date: 2013 / Resumo: A caracterização de reservatórios é fundamental na construção do modelo geológico para a produção do campo. O melhoramento de técnicas matemáticas, que auxiliam a interpretação geológica, influencia diretamente o plano de desenvolvimento e gerenciamento dos poços. Nesse sentido, este trabalho utiliza uma aplicação inédita na caracterização de reservatórios da técnica de Transformada Imagem Floresta (Image Foresting Transform - IFT) em segmentação de imagens de rocha para a análise petrofísica. A técnica interpreta a imagem como um grafo, onde os pixels são os nós e os arcos são definidos por uma relação de adjacência entre os pixels. O custo de um caminho no grafo é determinado por uma função que depende das propriedades locais da imagem. As raízes da floresta surgem de um conjunto de pixels escolhidos como sementes e a IFT atribui um caminho de custo mínimo das sementes a cada pixel da imagem para gerar uma Floresta de Caminhos Ótimos (Optimum-Path Forest - OPF). Com isso, nas imagens de lâminas de arenito, os grãos são segmentados em relação ao poro e os grãos em contato são separados entre si. Com os resultados obtidos é possível o estudo da morfologia dos grãos e porosidade da amostra. O método consiste de dois processos principais, um totalmente automático para segmentar a imagem e outro que utiliza uma interface gráfica para permitir correções dos erros de classificação gerados pelo processo automático. A acurácia é medida comparando a imagem corrigida por interação do usuário com a segmentada automaticamente. Outra aplicação inédita apresentada no trabalho é a utilização do classificador supervisionado baseado em OPF para a classificação de dados de perfilagem geofísica do campo de Namorado / Abstract: The reservoir characterization is fundamental in the construction process of geological model for field production. The improvement of mathematical techniques that assist the geological interpretation, has a directly influence in the development plan and management of the wells. Accordingly, this study uses a novel application in reservoir characterization, Image Foresting Forest (IFT) technique to image segmentation of rock for petrophysical analysis. The IFT interprets an image as a graph, whose nodes are the image pixels, the arcs are defined by an adjacency relation between pixels, and the paths are valued by a connectivity function. The roots of forest are a set of pixels selected as seeds and the IFT assigns a minimum path-cost to each image pixel generation an Optimum-Path Forest (OPF). The result is a segmentation of grains from pore in sandstone thin section images and the separation of the touching grains automatically. This allows the study of grain morphology and sample porosity. The method consists of two major processes: first, a totally automatic image segmentation and second and user interaction to correct misclassified grains. The accuracy is computed comparing the corrected image by the user with the image segmented automatically. Another novel application presented in the work is the use of supervised classification based on OPF for classification of geophysical logging data from Campo de Namorado / Mestrado / Reservatórios e Gestão / Mestre em Ciências e Engenharia de Petróleo