Roads are significant objects of an infrastructure and the extraction of roads from aerial and satellite images are important for different applications such as automated map generation and change detection. Roads are also important to detect other structures such as buildings and urban areas. In this thesis, the road extraction approach is based on Active Contour Models for 1- meter resolution gray level images. Active Contour Models contains Snake Approach. During applications, the road structure was separated as salient-roads, non-salient roads and crossings and extraction of these is provided by using Ribbon Snake and Ziplock Snake methods. These methods are derived from traditional snake model. Finally, various experimental results were presented. Ribbon and Ziplock Snake methods were compared for both salient and non-salient roads. Also these methods were used to extract roads in an image. While Ribbon snake is described for extraction of salient roads in an image, Ziplock snake is applied for extraction of non-salient roads. Beside these, some constant variables in literature were redefined and expressed in a formula as depending on snake approach and a new approach for extraction of crossroads were described and tried.

Many practical applications in the field of medical image processing require valid and reliable segmentation of images. In this dissertation, we propose three different semi-automatic segmentation frameworks for 2D-upper torso medical images to construct 3D geometric model of the torso structures. In the first framework, an extended version of the Otsu&rsquo / s method for three level thresholding and a recursive connected component algorithm are combined. The segmentation process is accomplished by first using Extended Otsu&rsquo / s method and then labeling in each consecutive slice. Since there is no information about pixel positions in the outcome of Extended Otsu&rsquo / s method, we perform some processing after labeling to connect pixels belonging with the same tissue. In the second framework, Chan-Vese (CV) method, which is an example of active contour models, and a recursive connected component algorithm are used together. The segmentation process is achieved using CV method without egde information as stopping criteria. In the third and last framework, the combination of watershed transformation and K-means are used as the segmentation method. After segmentation operation, the labeling is performed for the determination of the medical structures. In addition, segmentation and labeling operation is realized for each consecutive slice in each framework. The results of each framework are compared quantitatively with manual segmentation results to evaluate their performances.

No description available.

Salient contour detection is an important lowlevel visual process in the human visual system, and has significance towards understanding higher visual and cognitive processes. Salience detection can be investigated by examining the visual cortical response to visual input. Visual response activity in the early stages of visual processing can be approximated by a sequence of convolutions of the input scene with the difference-of-Gaussian (DoG) and the oriented Gabor filters. The filtered responses are unusually high for prominent edge locations in the image, and are uniformly similar across different natural image inputs. Furthermore, such a response follows a power law distribution. The aim of this thesis is to examine how these response properties could be utilized to the problem of salience detection. First, I identify a method to find the best threshold on the response activity (orientation energy) toward the detection of salient contours: compare the response distribution to a Gaussian distribution of equal variance. Second, I justify this comparison by providing an explanation under the framework of Suspicious Coincidence proposed by Barlow [1]. A connection is provided between perceived salience of contours and the neuronal goal of detecting suspiciousness, where salient contours are seen as affording suspicious coincidences by the visual system. Finally, the neural plausibility of such a salience detection mechanism is investigated, and the representational effciency is shown which could potentially explain why the human visual system can effortlessly detect salience.

This thesis recounts the study of contour blasting practices in the Appalachia coal region. Contour blasting practices vary widely and problems are often encountered. Several different sites were visited and contour blasting practices at each were studied. Based on the information gathered, a comprehensive plan was developed for blasting operations to follow and then was tested and compared to an example of blasting practices without use of the plan. The blasting practices were compared by examining monthly production rates as well as a time study to measure the efficiency a contour blast could be loaded and hauled away and a cost per cubic yard of material determined. The plan was found to be successful in keeping safety while increasing profitability. However, the plan will need to be backed and understood by management in order to achieve the same success.

A system for vessel characterization aimed at detecting deep vein thrombosis (DVT) in the lower limbs has been developed and evaluated using ultrasound image processing, location and force sensors measurements, blood flow information and a protocol based on the current clinical standard, compression ultrasound. The goal is to provide an objective and repeatable system to measure DVT in a rapid and standardized manner, as this has been suggested in the literature as an approach to improve overall detection of the disease. The system uses a spatial Kalman filter-based algorithm with an elliptical model in the measurement equation to detect vessel contours in transverse ultrasound images and estimate ellipse parameters, and temporal constant velocity Kalman filters for tracking vessel location in real-time. The vessel characterization also comprises building a 3-D vessel model and performing compression and blood flow assessments to calculate measures that indicate the possibility of DVT in a vessel. A user interface designed for assessing a vessel for DVT was also developed. The system and components were implemented and tested in simulations, laboratory settings, and clinical settings. Contour detection results are good, with mean and rms errors ranging from 1.47-3.64 and 3.69-9.67 pixels, respectively, in simulated and patient images, and parameter estimation errors of 5%. Experiments showed errors of 3-5 pixels for the tracking approaches. The measures for DVT were evaluated, independently and integrated in the system. The complete system was evaluated, with sensitivity of 67-100% and specificity of 50-89.5%. System learnability and memorability were evaluated in a separate user study, with good results. Contributions include a segmentation approach using a full parameter ellipse model in an extended Kalman filter, incorporating multiple measurements, an alternate sampling method for faster parameter convergence and application-specific initialization, and a tracking approach that includes a sub-sampled sum of absolutes similarity calculation and a method to detect vessel bifurcations using flow data. Further contributions include an integrated system for DVT detection that can combine ultrasound B-mode, colour flow and elastography images for vessel characterization, a system interface design focusing on usability that was evaluated with medical professionals, and system evaluations through multiple patient studies.

Unlike straight turning, the effective cutting conditions and tool geometry in contour turning operations are changing with changing workpiece profile. This causes a wide variation in machining performance such as chip flow and chip breakability during the operation. This thesis presents a new methodology for optimizing the machining performance, namely, chip breakability and surface roughness in contour finish turning operations. First, a computer program to calculate the effective cutting conditions and tool geometry along the contour workpiece profile is developed. Second, a methodology to predict the chip side-flow for complex grooved tool inserts is formulated and integrated in the current predictive model for contour turning operations. Third, experimental databases are established and numerical data interpolation is applied to predict the cutting forces, chip shape and size, and surface roughness for 1045 steel work material. Finally, based on the machining performance predictions, a new optimization program is developed to determine the optimum cutting conditions in contour finish turning operations.

Three collimators were designed and built with mouse irradiation in mind. They were made to have a shapeable aperture that could deliver strange or complex dose shapes to spots on the animals. Current collimators are either custom-built, expensive, or only provide limited dose shapes. These provide self-customizable collimation at a minimum of cost. A mouse holder was also devised to reproducibly hold a mouse under the collimator. Construction of the holder and of each collimator is also covered. Each collimator was analyzed for flaws, holes, and penumbral width across various shapes of interest. A Norelco MG300 X-ray generator at the Texas A&M Nuclear Science Center was used in these tests. The lead collimator had a radial penumbra of 1.2 mm. The clay / lead shot collimator had a radial penumbra of 1.6 mm. The brass collimator had a radial penumbra of 1.75 mm. Vertical and horizontal penumbras are dependent on distance from the center of the beam. All readings are + 0.3 mm according to the resolution of the scanner used in this experiment. Each collimator is useful for different purposes.

Honeybees have a rich genetic diversity in Anatolia. This is reflected in the presence of numerous subspecies of honeybee in Turkey. In METU, Department of Biology, honeybee populations of different regions in Turkey are investigated in order to characterize population variation in these regions. A total of 23 length and angle features belonging to the honeybee hindlegs and forewings are measured in these studies using a microscope and a monitor. These measurements are carried out by placing rulers on the monitor that shows the honeybee image and getting the length and angle features. However, performing measurements in this way is a time consuming process and is open to human-dependent errors. In this thesis, a &ldquo / semi-automated honeybee feature extraction system&rdquo / is presented. The aim is to increase the efficiency by decreasing the time spent on handling these measurements and by increasing the accuracy of measured hindleg and forewing features. The problem is studied from the acquisition of the microscope images, to the feature extraction of the honeybee features. In this scope, suitable methods are developed for segmentation of honeybee hindleg and forewing images. Within intermediate steps, blob analysis is utilized, and edges of the forewing and hindlegs are thinned using skeletonization. Templates that represent the forewing and hindleg edges are formed by either Bezier Curves or Polynomial Interpolation. In the feature extraction phase, Active Contour (Snake) algorithm is applied to the images in order to find the critical points using these templates.

Contour extraction of Drosophila embryos is an important step to build a computational system for pattern matching of embryonic images which aids in the discovery of genes. Automatic contour extraction of embryos is challenging due to several image variations such as size, shape, orientation and neigh- boring embryos such as touching and non-touching embryos. In this thesis, we introduce a framework for contour extraction based on the connected components in the gaussian scale space of an embryonic image. The active contour model is applied on the images to refine embryo contours. Data cleaning methods are applied to smooth the jaggy contours caused by blurred embryo boundaries. The scale space theory is applied to improve the performance of the result. The active contour adjusts better to the object for finer scales. The proposed framework contains three components. In the first component, we find the connected components of the image. The second component is to find the largest component of the image. Finally, we analyze the largest component across scales by selecting the optimal scale corresponding to the largest component having largest area. The optimal scale at which maximum area is attained is assumed to give information about the feature being extracted. We tested the proposed framework on BDGP images, and the results achieved promising accuracy in extracting the targeting embryo.