Orientador: Alexandre Xavier Falcão / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-19T04:43:31Z (GMT). No. of bitstreams: 1 Silva_MairaSaboiada_M.pdf: 1907857 bytes, checksum: 515dfcdf136f4e9cc1c1d8b0690b3116 (MD5) Previous issue date: 2011 / Resumo: Esta dissertação apresenta uma metodologia automática para separar objetos de interesse em imagens naturais. Objetos de interesse são definidos como os maiores objetos que se destacam com relação aos pixels em torno deles dentro de uma imagem. Estes objetos não precisam necessariamente estar centrados, mas devem possuir o mínimo possível de pixels na região assumida como fundo da imagem (e.g., borda de imagem com uma dada espessura). A metodologia é baseada em segmentação de fundo e pode ser dividida em duas etapas. Primeiramente, um modelo nebuloso é criado para o fundo da imagem utilizando um método de agrupamento baseado em função densidade de probabilidade das cores de fundo. A partir do modelo é criado um mapa de pertinência, onde os pixels de objeto são mais claros do que os pixels de fundo. Foram investigadas técnicas de agrupamento baseadas em deslocamento médio, transformada imagem floresta, mistura de Gaussianas e maximização da esperança. Três métodos para criação do mapa de pertinência foram propostos e comparados; um inteiramente baseado na transformada imagem floresta, o outro em mistura de Gaussianas e o terceiro em maximização da esperança. Nos dois últimos casos, o agrupamento baseado na transformada imagem floresta foi utilizado como estimativa inicial dos grupos. Em seguida, o mapa de pertinência é utilizado para possibilitar a seleção de pixels sementes de objeto e fundo. Estes pixels geram um agrupamento binário da imagem colorida que separa o fundo do(s) objeto(s). Os experimentos foram realizados com uma base heterogênea composta por 50 imagens naturais. Os melhores resultados foram os obtidos pela metodologia inteiramente baseada na Transformada Imagem Floresta. Para justificar o uso de um agrupamento binário das cores para segmentação, os resultados foram comparados com uma limiarização ótima, aplicada ao mapa de pertinência. Esses testes foram realizados com o algoritmo de Otsu, mas o agrupamento binário apresentou melhores resultados. Também foi proposto um método híbrido de binarização do mapa de pertinência, envolvendo a limiarização de Otsu e a transformada imagem floresta. Neste caso, a limiarização de Otsu reduz o número de parâmetros em relação à primeira / Abstract: This work presents a new methodology for automatic extraction of desired objects in natural images. Objects of interest are defined as the largest components that differ from their surrounding pixels in a given image. These objects do not need to be centered, but they should contain a minimum number of pixels in the region assumed as background (e.g., an image border of certain thickness). This methodology is based on background segmentation and it can be summarized in two steps. First, a fuzzy model is created by a clustering method based on probability density function of the background colors. This model is a membership map, wherein object pixels are brighter than background pixels. For clustering, the following techniques were investigated: mean-shift, image foresting transform, Gaussian mixture model and expectation maximization. We then propose and compare three approaches to create a membership map; a first method entirely based on the image foresting transform, a second approach based on Gaussian mixture model and a third tecnique using expectation maximization. The clustering based on image foresting transform was adopted as the initial estimate for the clusters in the case of the two last methods. In a second step, the membership map is used to enable the selection of object and background seed pixels. These pixels create a binary clustering of the color pixels that separates background and object(s). The experiments involved a heterogeneous dataset with 50 natural images. The approach entirely based on the image foresting transform provided the best result. In order to justify the use of a binary clustering of color pixels instead of optimum thresholding on the membership map, we demonstrated that the binary clustering can provide a better result than Otsu's approach. It was also proposed a hybrid approach to binarize the membership map, which combines Otsu's thresholding and image foresting transform. In this case, Otsu's thresholding reduces the number of parameters in regard to the first approach / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

Automated Guided Vehicle(AGV) as a kind of material conveying equipment has been widely used in modern manufacturing systems. [1] It carries the goods between the workshop along the designated paths. The ability of localization and recognizing the environment around themselves is the essential technology. AGV navigation is developed from several technologies such as fuzzy theory, neural network and other intelligent technology. Among them, visual navigation is one of the newer navigations, because of its path laying is easy to maintain, can identify variety of road signs. Compared with traditional methods, this approach has a better flexibility and robustness, since it can recognition more than one path branch with high anti-jamming capability. Recognizing the environment from imagery can enhance safety and dependability of an AGV, make it move intelligently and brings broader prospect for it. University West has a Patrolbot which is an AGV robot with basic functions. The task is to enhance the ability of vision analysis, to make it become more practical and flexible. The project is going to add object detection, object recognition and object localization functions on the Patrolbot. This thesis project develops methods based on image recognition, deep learning, machine vision, Convolution Neural Network and related technologies. In this project Patrolbot is a platform to show the result, we can also use this kind of program on any other machines. This report generally describes methods of navigation, image segmentation and object recognition. After analyzing the different methods of image recognition, it is easy to find that Neural Network has more advantages for image recognition, it can reduce the parameters and shorting the training and analyzing time, therefore Convolution Neural Network was introduced detailly. After that, the way to achieve image recognition using convolution neural network was presented and in order to recognize several objects at the same time, an image segmentation was also presented here. On the other hand, to make this image recognition processes to be used widely, the ability of transfer learning becomes important. Therefore, the method of transfer learning is presented to achieve customized requirement.

Submitted in fulfillment of the requirements for the Master's Degree in Information and Communication Technology, Durban, University of Technology, Durban, South Africa, 2017. / The topic of colour image segmentation has been and still is a hot issue in areas such as computer vision and image processing because of its wide range of practical applications. The urge has led to the development of numerous colour image segmentation algorithms to extract salient objects from colour images. However, because of the diverse imaging conditions in varying application domains, accuracy and robustness of several state-of-the-art colour image segmentation algorithms still leave room for further improvement. This dissertation reports on the development of a new image segmentation algorithm based on perceptual colour difference saliency along with binary morphological operations. The algorithm consists of four essential processing stages which are colour image transformation, luminance image enhancement, salient pixel computation and image artefact filtering. The input RGB colour image is first transformed into the CIE L*a*b colour image to achieve perceptual saliency and obtain the best possible calibration of the transformation model. The luminance channel of the transformed colour image is then enhanced using an adaptive gamma correction function to alleviate the adverse effects of illumination variation, low contrast and improve the image quality significantly. The salient objects in the input colour image are then determined by calculating saliency at each pixel in order to preserve spatial information. The computed saliency map is then filtered using the morphological operations to eliminate undesired factors that are likely present in the colour image. A series of experiments was performed to evaluate the effectiveness of the new perceptual colour difference saliency algorithm for colour image segmentation. This was accomplished by testing the algorithm on a large set of a hundred and ninety images acquired from four distinct publicly available benchmarks corporal. The accuracy of the developed colour image segmentation algorithm was quantified using four widely used statistical evaluation metrics in terms of precision, F-measure, error and Dice. Promising results were obtained despite the fact that the experimental images were selected from four different corporal and in varying imaging conditions. The results have indeed demonstrated that the performance of the newly developed colour image segmentation algorithm is consistent with an improved performance compared to a number of other saliency and non- saliency state-of-the-art image segmentation algorithms. / M

De nos jours, le traitement et l’analyse d’images trouvent leur application dans de nombreux domaines. Dans le cas de la navigation d’un robot mobile (fauteuil roulant) en milieu intérieur, l’extraction de repères visuels et leur suivi constituent une étape importante pour la réalisation de tâches robotiques (localisation, planification, etc.). En particulier, afin de réaliser une tâche de franchissement de portes, il est indispensable de détecter et suivre automatiquement toutes les portes qui existent dans l’environnement. La détection des portes n’est pas une tâche facile : la variation de l’état des portes (ouvertes ou fermées), leur apparence (de même couleur ou de couleur différentes des murs) et leur position par rapport à la caméra influe sur la robustesse du système. D’autre part, des tâches comme la détection des zones navigables ou l’évitement d’obstacles peuvent faire appel à des représentations enrichies par une sémantique adaptée afin d’interpréter le contenu de la scène. Pour cela, les techniques de segmentation permettent d’extraire des régions pseudo-sémantiques de l’image en fonction de plusieurs critères (couleur, gradient, texture…). En ajoutant la dimension temporelle, les régions sont alors suivies à travers des algorithmes de segmentation spatio-temporelle. Dans cette thèse, des contributions répondant aux besoins cités sont présentées. Tout d’abord, une technique de détection et de suivi de portes dans un environnement de type couloir est proposée : basée sur des descripteurs géométriques dédiés, la solution offre de bons résultats. Ensuite, une technique originale de segmentation multirésolution et hiérarchique permet d’extraire une représentation en régions pseudosémantique. Enfin, cette technique est étendue pour les séquences vidéo afin de permettre le suivi des régions à travers le suivi de leurs contours. La qualité des résultats est démontrée et s’applique notamment au cas de vidéos de couloir. / Nowadays, image processing remains a very important step in different fields of applications. In an indoor environment, for a navigation system related to a mobile robot (electrical wheelchair), visual information detection and tracking is crucial to perform robotic tasks (localization, planning…). In particular, when considering passing door task, it is essential to be able to detect and track automatically all the doors that belong to the environment. Door detection is not an obvious task: the variations related to the door status (open or closed), their appearance (e.g. same color as the walls) and their relative position to the camera have influence on the results. On the other hand, tasks such as the detection of navigable areas or obstacle avoidance may involve a dedicated semantic representation to interpret the content of the scene. Segmentation techniques are then used to extract pseudosemantic regions based on several criteria (color, gradient, texture...). When adding the temporal dimension, the regions are tracked then using spatiotemporal segmentation algorithms. In this thesis, we first present joint door detection and tracking technique in a corridor environment: based on dedicated geometrical features, the proposed solution offers interesting results. Then, we present an original joint hierarchical and multiresolution segmentation framework able to extract a pseudo-semantic region representation. Finally, this technique is extended to video sequences to allow the tracking of regions along image sequences. Based on contour motion extraction, this solution has shown relevant results that can be successfully applied to corridor videos.

Abstract The use of image-guidance in surgery and radiotherapy has significantly improved patient outcome in neurosurgery and radiotherapy treatments. This work developed volume definition and verification techniques for image-guided applications, using a number of algorithms ranging from image processing to visualization. Stereoscopic visualization, volumetric tumor model overlaid on an ultrasound image, and visualization of the treatment geometry were experimented with on a neurosurgical workstation. Visualization and volume definition tools were developed for radiotherapy treatment planning system. The magnetic resonance inhomogeneity correction developed in this work, possibly the first published data-driven method with wide applicability, automatically mitigates the RF field inhomogeneity artefact present in magnetic resonance images. Correcting the RF inhomogeneity improves the accuracy of the generated volumetric models. Various techniques to improve region growing are also presented. The simplex search method and combinatory similarity terms were used to improve the similarity function with a low additional computational cost and high yield in region correctness. Moreover, the effects of different priority queue implementations were studied. A fast algorithm for calculating high-quality digitally reconstructed radiographs has been developed and shown to better meet typical radiotherapy needs than the two alternative algorithms. A novel visualization method, beam's light view, is presented. It uses texture mapping for projecting the fluence of a radiation field on an arbitrary surface. This work suggests several improved algorithms for image processing, segmentation, and visualization used in image-guided treatment systems. The presented algorithms increase the accuracy of image-guidance, which can further improve the applicability and efficiency of image-guided treatments.

Active contours have been proven to be a powerful semiautomatic image segmentation approach, that seems to cope with many applications and different image modalities. However, they exhibit inherent drawbacks, including the sensibility to contour initialization due to the limited capture range of image edges and problems with concave boundary regions. The Gradient Vector Flow replaces the traditional image force and provides an enlarged capture range as well as enhanced concavity extraction capabilities, but it involves an expensive computational effort and considerably increased memory requirements at the time of computation. In this paper, we present an enhancement of the active contour model to facilitate semiautomatic contour detection in huge images. We propose a tile-based image decomposition accompanying an image force computation scheme on demand in order to minimize both computational and memory requirements. We show an efficient implementation of this approach on the basis of general purpose GPU processing providing for continuous active contour deformation without a considerable delay.

Three-Dimensional (3-D) imaging is vital in computer-assisted surgical planning including minimal invasive surgery, targeted drug delivery, and tumor resection. Selective Internal Radiation Therapy (SIRT) is a liver directed radiation therapy for the treatment of liver cancer. Accurate calculation of anatomical liver and tumor volumes are essential for the determination of the tumor to normal liver ratio and for the calculation of the dose of Y-90 microspheres that will result in high concentration of the radiation in the tumor region as compared to nearby healthy tissue. Present manual techniques for segmentation of the liver from Computed Tomography (CT) tend to be tedious and greatly dependent on the skill of the technician/doctor performing the task. This dissertation presents the development and implementation of a fully integrated algorithm for 3-D liver and tumor segmentation from tri-phase CT that yield highly accurate estimations of the respective volumes of the liver and tumor(s). The algorithm as designed requires minimal human intervention without compromising the accuracy of the segmentation results. Embedded within this algorithm is an effective method for extracting blood vessels that feed the tumor(s) in order to plan effectively the appropriate treatment. Segmentation of the liver led to an accuracy in excess of 95% in estimating liver volumes in 20 datasets in comparison to the manual gold standard volumes. In a similar comparison, tumor segmentation exhibited an accuracy of 86% in estimating tumor(s) volume(s). Qualitative results of the blood vessel segmentation algorithm demonstrated the effectiveness of the algorithm in extracting and rendering the vasculature structure of the liver. Results of the parallel computing process, using a single workstation, showed a 78% gain. Also, statistical analysis carried out to determine if the manual initialization has any impact on the accuracy showed user initialization independence in the results. The dissertation thus provides a complete 3-D solution towards liver cancer treatment planning with the opportunity to extract, visualize and quantify the needed statistics for liver cancer treatment. Since SIRT requires highly accurate calculation of the liver and tumor volumes, this new method provides an effective and computationally efficient process required of such challenging clinical requirements.

The haptic exploration of 2-D images is a challenging problem in computer haptics. Research on the topic has primarily been focused on the exploration of maps and curves. This thesis describes the design and implementation of a system for the haptic exploration of photographs. The system builds on various research directions related to assistive technology, computer haptics, and image segmentation. An object-level segmentation hierarchy is generated from the source photograph to be rendered haptically as a contour image at multiple levels-of-detail. A tool for the authoring of object-level hierarchies was developed, as well as an innovative type of user interaction by region selection for accurate and efficient image segmentation. According to an objective benchmark measuring how the new method compares with other interactive image segmentation algorithms shows that our region selection interaction is a viable alternative to marker-based interaction. The hierarchy authoring tool combined with precise algorithms for image segmentation can build contour images of the quality necessary for the images to be understood by touch with our system. The system was evaluated with a user study of 24 sighted participants divided in different groups. The first part of the study had participants explore images using haptics and answer questions about them. The second part of the study asked the participants to identify images visually after haptic exploration. Results show that using a segmentation hierarchy supporting multiple levels-of-detail of the same image is beneficial to haptic exploration. As the system gains maturity, it is our goal to make it available to blind users.

La segmentation d'image est le processus de partitionnement d'une image numérique en régions, non chevauchées, homogènes vis-à-vis de certaines caractéristiques, telles que le niveau de gris, la texture, le mouvement, etc. Elle a des applications dans plusieurs domaines comme l'imagerie médicale, la détection d'objets, la biométrie, l'imagerie par satellite, la navigation de robot, la vidéosurveillance, etc. Le processus de segmentation représente une étape cruciale dans les systèmes de vision par ordinateur, car les caractéristiques et décisions sont extraites et prises à partir de son résultat. Les premiers algorithmes de segmentation d'image ont vu le jour dans les années 1970. Depuis, de nombreuses techniques et méthodes de segmentation ont été expérimentées pour essayer d'améliorer les résultats. Néanmoins, jusqu'à nos jours, aucun algorithme de segmentation d'image n'arrive à fournir des résultats parfaits sur une large variété d'images. Les "métaheuristiques" sont des procédures conçues pour résoudre des problèmes d'optimisation dits difficiles. Ce sont en général des problèmes aux données incomplètes, incertaines, bruitées ou confrontés à une capacité de calcul limitée. Les métaheuristiques ont connu un succès dans une large variété de domaines. Cela découle du fait qu'elles peuvent être appliquées à tout problème pouvant être exprimé sous la forme d'un problème d'optimisation de critère(s). Ces méthodes sont, pour la plupart, inspirées de la physique (recuit simulé), de la biologie (algorithmes évolutionnaires) ou de l'éthologie (essaims particulaires, colonies de fourmis).Ces dernières années, l'introduction des métaheuristiques dans le domaine du traitement d'images a permis d'étudier la segmentation sous un angle différent, avec des résultats plus ou moins réussis. Dans le but d'apporter notre contribution et d'améliorer davantage les performances des méthodes de segmentation, nous avons proposé des algorithmes basés régions, contours et hybrides, mettant en œuvre des métaheuristiques d'optimisation dans des approches mono et multiobjectif. Les méthodes proposées ont été évaluées sur des bases de données expérimentales composées d'images synthétiques, d'images IRM simulées et d'images IRM réelles ainsi que des images de tomographie par émission de positons (TEP). Les résultats obtenus sont significatifs et prouvent l'efficacité des idées proposées / Image segmentation is the process of partitioning a digital image into homogeneous non-overlapped regions with respect to some characteristics, such as gray value, motion, texture, etc. It is used in various applications like medical imaging, objects detection, biometric system, remote sensing, robot navigation, video surveillance, etc. The success of the machine vision system depends heavily on its performance, because characteristics and decisions are extracted and taken from its result. The first image segmentation algorithms were introduced in the 70's. Since then, various techniques and methods were experimented to improve the results. Nevertheless, up till now, no method produces a perfect result for a wide variety of images. Metaheuristics are a high level procedure designed to solve hard optimization problems. These problems are in general characterized by their incomplete, uncertain or noised data, or faced to low computing capacity. Metaheuristics have been extremely successful in a wide variety of fields and demonstrate significant results. This is due to the fact that they can applied to solve any problem which can be formulated as an optimization problem. These methods are, mainly, inspired from physics (simulated annealing), biology (evolutionary algorithms), or ethology (particle swarm optimization, ant colony optimization).In recent years, metaheuristics are starting to be exploited to solve segmentation problems with varying degrees of success and allow to consider the problem with different perspectives. Bearing this in mind, we propose in this work three segmentation and post-segmentation approaches based on mono or multiobjective optimization metaheuristics. The proposed methods were evaluated on databases containing synthetic images, simulated MRI images, real MRI images and PET images. The obtained results show the efficiency of the proposed ideas

The aim of this master´s thesis is to find out whether dry skin type influences the consumer´s satisfaction with his appearance and whether possible dissatisfaction can arouse purchase behaviour in meaning of purchasing and consuming miosturizing skin care products. Based on findings, thesis proposes next target to compose corresponding orientation of marketing communication for selected segment. Thesis follows a concept of concentrated marketing, which starts with market segmentation of consumers with dry skin type in analytical tool Data Analyzer and continues with selection of one particular segment to get a focuse on. After target segment is selected, questionnaire survey is used to enhance its profile. The thesis is finished up with draft of marketing orientation for selected segment. This marketing orientation captures the results of relation between dry skin type and body image revealed from data analysis MML-TGI and questionnaire investigation.