Researchers have been involved for decades in search of an efficient skin detection method. Yet current methods have not overcome the major limitations. To overcome these limitations, in this dissertation, a clustering and region growing based skin detection method is proposed. These methods together with a significant insight result in a more effective algorithm. The insight concerns a capability to define dynamically the number of clusters in a collection of pixels organized as an image. In clustering for most problem domains, the number of clusters is fixed a priori and does not perform effectively over a wide variety of data contents. Therefore, in this dissertation, a skin detection method has been proposed using the above findings and validated. This method assigns the number of clusters based on image properties and ultimately allows freedom from manual thresholding or other manual operations. The dynamic determination of clustering outcomes allows for greater automation of skin detection when dealing with uncertain real-world conditions.

A new approach to improve the determination of building boundaries through automatic processing of light detection and ranging (LIDAR) data is presented. The LIDAR data is processed and interpolated into a grayscale image of intensity values corresponding to height measurements. Ground measurements are separated from non-ground measurements by using a progressive morphological filter. With these measurements now distinct, further separation of non-ground measurements into building and non-building measurements is performed by growing regions with similar characteristics. These building areas are then refined, resulting in a ground plan representation of building boundaries, known as building footprints. Several algorithms are then implemented to clean these footprints. A new method is developed to analyze actual known satellite imagery in order to confirm identified building footprints.

Conventional ultrasonographic examination of the bovine ovary is based on a sequence of two-dimensional (2D) cross-section images. Day-to-day estimation of the number, size, shape and position of the ovarian follicles is one of the most important aspects of ovarian research. Computer-assisted follicle segmentation of ovarian volume can relieve physicians from the tedious manual detection of follicles, provide objective assessment of spatial relationships between the ovarian structures and therefore has the potential to improve accuracy. Modern segmentation procedures are performed on 2D images and the three-dimensional (3D) visualization of follicles is obtained from the reconstruction of a sequence of 2D segmented follicles. <p>The objective of this study was to develop a semi-automatic 3D follicle segmentation method based on seeded region growing. The 3D datasets were acquired from a sequence of 2D ultrasound images and the ovarian structures were segmented from the reconstructed ovarian volume in a single step. A seed is placed manually in each follicle and the growth of the seed is controlled by the algorithm using a combination of average grey-level, standard deviation of the intensity, newly-developed volumetric comparison test and a termination criterion. One important contribution of this algorithm is that it overcomes the boundary leakage problem of follicles of conventional 2D segmentation procedures. The results were validated against the aspiration volume of follicles, the manually detected follicles by an expert and an existing algorithm.<p>We anticipate that this algorithm will enhance follicular assessment based on current ultrasound techniques in cases when large numbers of follicles (e.g. ovarian superstimulation) obviate accurate counting and size measurement.

Conventional ultrasonographic examination of the bovine ovary is based on a sequence of two-dimensional (2D) cross-section images. Day-to-day estimation of the number, size, shape and position of the ovarian follicles is one of the most important aspects of ovarian research. Computer-assisted follicle segmentation of ovarian volume can relieve physicians from the tedious manual detection of follicles, provide objective assessment of spatial relationships between the ovarian structures and therefore has the potential to improve accuracy. Modern segmentation procedures are performed on 2D images and the three-dimensional (3D) visualization of follicles is obtained from the reconstruction of a sequence of 2D segmented follicles. <p>The objective of this study was to develop a semi-automatic 3D follicle segmentation method based on seeded region growing. The 3D datasets were acquired from a sequence of 2D ultrasound images and the ovarian structures were segmented from the reconstructed ovarian volume in a single step. A seed is placed manually in each follicle and the growth of the seed is controlled by the algorithm using a combination of average grey-level, standard deviation of the intensity, newly-developed volumetric comparison test and a termination criterion. One important contribution of this algorithm is that it overcomes the boundary leakage problem of follicles of conventional 2D segmentation procedures. The results were validated against the aspiration volume of follicles, the manually detected follicles by an expert and an existing algorithm.<p>We anticipate that this algorithm will enhance follicular assessment based on current ultrasound techniques in cases when large numbers of follicles (e.g. ovarian superstimulation) obviate accurate counting and size measurement.

No description available.

The need for energy is constantly increasing, and fossil fuels are both harmful and neither everlasting. This puts higher demand on the production of renewable energy. In Sweden the production of renewable energy is relatively good, however the solar power is not utilized enough. The planning phase for the purpose of solar installation is a lengthy process, and will over the coming years need to be more efficient. Several different methods are used for planning today, with the help of geographic data in the form of ortophotos. Multiple studies today have successfully achieved the segmentation of roofs, which then is used in this process. The studies that have achieved this, has used software that is not widely available to private individuals and thus the information regarding precise solar potential assesments are unavailable to them. This study has not found a similar implementation which operates in a semi-automatic manner as a webservice, on the Internet which is the most used platform. Therefore this study will investigate how roofs can be segmented and drawn on a map in a web application, in an automated manner with image processing. This is accomplished using the region growing algorithm. The result is produced by a number of tests on a variation of roof designs and colors. Validation of the results are done visually, when the segmentation is drawn onto the map. In most cases the algorithm has not been able to correctly identify and segment parts of the roof, and in no case has been successful to segment an entire roof. This was largely because of lack of data, and shadow disturbance in the images used. The result shows the method could work in a better way, using more data and developing the image processing further. It also shows how easily this type of method can be integrated with a webmap. / Behovet av energi ökar konstant, och de fossila bränslena är både skadliga för miljön och inte heller föreviga. Detta ställer större krav på produktionen av förnybar energi. I Sverige produceras förnybar energi relativt bra, men solkraften är inte utnyttjad tillräckligt. Planeringsfasen i detta är väldigt stor, och kommer med stor sannolikhet behöva effektiviseras de närmaste åren. Flera olika metoder används idag, man utgår oftast från geografiska data i form av ortofoton. Flertalet arbeten har tidigare lyckats att korrekt segmentera takytor, för att sedan användas som underlag. De arbeten som lyckats med detta, har ofta gjort det i sådana program att det blir svårt för privatpersoner att ta del av informationen. Informationen innefattar en utförlig utvärdering av ett taks potential för solkraft. Detta arbete har inte hittat någon liknande implementation i form av webbtjänst där denna process är semi-automatisk, det vill saga på Internet, vilket är den mest använda plattformen. I detta arbete undersöks därför hur takytor kan segmenteras och ritas ut i en webbapplikation med tillhörande karta, på ett nästan helt automatiserat sätt med bildbehandling. Detta med hjälp av algoritmen region growing på ortofoton. Resultatet produceras av flertalet tester på varierande konstruktioner och färger på tak. Validering av testresultaten sker helt visuellt, efter utritning i karta. I de flesta testfallen har algoritmen på ett korrekt sätt lyckats identifiera och segmentera delar av taket, men inte i något fall ansetts ha lyckats segmentera ett helt tak på ett korrekt vis. Detta berodde till stor del på att inte fler typer av data än ortofoton var tillgängliga, samt störningar i de bilder som användes i form av skuggning. Resultatet visar att metoden kan fungera på ett bättre sätt, med tillgång till mer data och vidare utveckling av bildbehandlingen. Samt visar hur denna typ av operation enkelt kan integreras i en webbkarta.

In this thesis, the goal was to implement a method to do partial segmentation for general 3D volumetric datasets such as mummies, clay figurines or animal bodies. There are different approaches for segmenting volumes, such as automatic methods, semi-automatic methods and interactive methods. However, no automatic algorithm was found that could successfully segment any general 3D volume with high precision. Instead, the chosen approach are segmentation tools which allows the user to quickly and intuitively do partial segmentation from a 3D volume. The tools consist of a interactive 3D brush, a transfer function editor and a semi-automatic flood fill tool which performs region growing in 3D. User studies were carried out in order to evaluate the speed and effectiveness of the segmenting tools compared to the conventional method of segmenting using a stack of 2D images. Based on the user studies the results shows that the proposed method is faster compared to the old method as long as high precision is not required.

Rapid judgments about the properties and spatial relations of objects are the crux of visually guided interaction with the world. Vision begins, however, with essentially pointwise representations of the scene, such as arrays of pixels or small edge fragments. For adequate time-performance in recognition, manipulation, navigation, and reasoning, the processes that extract meaningful entities from the pointwise representations must exploit parallelism. This report develops a framework for the fast extraction of scene entities, based on a simple, local model of parallel computation.sAn image chunk is a subset of an image that can act as a unit in the course of spatial analysis. A parallel preprocessing stage constructs a variety of simple chunks uniformly over the visual array. On the basis of these chunks, subsequent serial processes locate relevant scene components and assemble detailed descriptions of them rapidly. This thesis defines image chunks that facilitate the most potentially time-consuming operations of spatial analysis---boundary tracing, area coloring, and the selection of locations at which to apply detailed analysis. Fast parallel processes for computing these chunks from images, and chunk-based formulations of indexing, tracing, and coloring, are presented. These processes have been simulated and evaluated on the lisp machine and the connection machine.

One important topic in medical image analysis is segmenting wall structures from different cardiac medical imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI). This task is typically done by radiologists either manually or semi-automatically, which is a very time-consuming process. To reduce the laborious human efforts, automatic methods have become popular in this research. In this thesis, features insensitive to data variations are explored to segment the ventricles from CT images and extract the left atrium from MR images. As applications, the segmentation results are used to facilitate cardiac disease analysis. Specifically, 1. An automatic method is proposed to extract the ventricles from CT images by integrating surface decomposition with contour evolution techniques. In particular, the ventricles are first identified on a surface extracted from patient-specific image data. Then, the contour evolution is employed to refine the identified ventricles. The proposed method is robust to variations of ventricle shapes, volume coverages, and image quality. 2. A variational region-growing method is proposed to segment the left atrium from MR images. Because of the localized property of this formulation, the proposed method is insensitive to data variabilities that are hard to handle by globalized methods. 3. In applications, a geometrical computational framework is proposed to estimate the myocardial mass at risk caused by stenoses. In addition, the segmentation of the left atrium is used to identify scars for MR images of post-ablation.

Medical imaging modalities provide effective information for anatomic or metabolic activity of tissues and organs in the body. Therefore, medical imaging technology is a critical component in diagnosis and treatment of various illnesses. Medical image segmentation plays an important role in converting medical images into anatomically, functionally or surgically identifiable structures, and is used in various applications. In this study, some of the major medical image segmentation methods are examined and applied to 2D CT images of upper torso for segmentation of heart, lungs, bones, and muscle and fat tissues. The implemented medical image segmentation methods are thresholding, region growing, watershed transformation, deformable models and a hybrid method / watershed transformation and region merging. Moreover, a comparative analysis is performed among these methods to obtain the most efficient segmentation method for each tissue and organ in torso. Some improvements are proposed for increasing accuracy of some image segmentation methods.