No description available.

In this thesis, new methods for the efficient segmentation of images are presented. The proposed methods are based on the deformable model approach, and can be used efficiently in the segmentation of complex geometries from various imaging modalities. A novel deformable model that is based on a geometrically induced external force field which can be conveniently generalized to arbitrary dimensions is presented. This external force field is based on hypothesized interactions between the relative geometries of the deformable model and the object boundary characterized by image gradient. The evolution of the deformable model is solved using the level set method so that topological changes are handled automatically. The relative geometrical configurations between the deformable model and the object boundaries contributes to a dynamic vector force field that changes accordingly as the deformable model evolves. The geometrically induced dynamic interaction force has been shown to greatly improve the deformable model performance in acquiring complex geometries and highly concave boundaries, and give the deformable model a high invariance in initialization configurations. The voxel interactions across the whole image domain provides a global view of the object boundary representation, giving the external force a long attraction range. The bidirectionality of the external force held allows the new deformable model to deal with arbitrary cross-boundary initializations, and facilitates the handling of weak edges and broken boundaries. In addition, it is shown that by enhancing the geometrical interaction field with a nonlocal edge-preserving algorithm, the new deformable model can effectively overcome image noise. A comparative study on the segmentation of various geometries with different topologies from both synthetic and real images is provided, and the proposed method is shown to achieve significant improvements against several existing techniques. A robust framework for the segmentation of vascular geometries is described. In particular, the framework consists of image denoising, optimal object edge representation, and segmentation using implicit deformable model. The image denoising is based on vessel enhancing diffusion which can be used to smooth out image noise and enhance the vessel structures. The image object boundaries are derived using an edge detection technique which can produce object edges of single pixel width. The image edge information is then used to derive the geometric interaction field for optimal object edge representation. The vascular geometries are segmented using an implict deformable model. A region constraint is added to the deformable model which allows it to easily get around calcified regions and propagate across the vessels to segment the structures efficiently. The presented framework is ai)plied in the accurate segmentation of carotid geometries from medical images. A new segmentation model with statistical shape prior using a variational approach is also presented in this thesis. The proposed model consists of an image attraction force that propagates contours towards image object boundaries, and a global shape force that attracts the model towards similar shapes in the statistical shape distribution. The image attraction force is derived from gradient vector interactions across the whole image domain, which makes the model more robust to image noise, weak edges and initializations. The statistical shape information is incorporated using kernel density estimation, which allows the shape prior model to handle arbitrary shape variations. It is shown that the proposed model with shape prior can be used to segment object shapes from images efficiently.

Master of Science / Department of Computer Science / William H. Hsu / This thesis addresses the tasks of detecting vegetation and classifying plants into target crops and weeds using combinations of machine learning and pattern recognition algorithms and models. Solutions to these problems have many useful applications in precision agriculture, such as estimating the yield of a target crop or identifying weeds to help automate the selective application of weedicides and thereby reducing cost and pollution. The novel contribution of this work includes development and application of image processing and computer vision techniques to create training data with minimal human intervention, thus saving substantial human time and effort. All of the data used in this work was collected from corn fields and is in the RGB format. As part of this thesis, I first discuss several steps that are part of a general methodology and data science pipeline for these tasks, such as: vegetation detection, feature engineering, crop row detection, training data generation, training, and testing. Next, I develop software components for segmentation and classification subtasks based on extant image processing and machine learning algorithms. I then present a comparison of different classifier models developed through this process using their Receiver Operating Characteristic (ROC) curves. The difference in models lies in the way they are trained - locally or globally. I also investigate the effect of the altitude at which data is collected on the performance of classifiers. Scikit-learn, a Python library for machine learning, is used to train decision trees and other classification learning models. Finally, I compare the precision, recall, and accuracy attained by segmenting (recognizing the boundary of) plants using the excess green index (ExG) with that of a learned Gaussian mixture model. I performed all image processing tasks using OpenCV, an open source computer vision library.

Trabecular bone structure as well as bone mineral density (BMD) have impact on the biomechanical competence of bone. In osteoporosis-related fractures, there have been shown to exist disconnections in the trabecular network as well as low bone mineral density. Imaging of bone parameters is therefore of importance in detecting osteoporosis. One available imaging device is cone-beam computed tomography (CBCT). This device is often used in pre-operative imaging of dental implants, for which the trabecular network also has great importance. Fourteen or 15 trabecular bone specimens from the radius were imaged for conducting this in vitro project. The imaging data from one dual-energy X-ray absorptiometry (DXA), two multi-slice computed tomography (MSCT), one high-resolution peripheral quantitative computed tomography (HR-pQCT) and four CBCT devices were segmented using an in-house developed code based on homogeneity thresholding. Seven trabecular microarchitecture parameters, as well as two trabecular bone stiffness parameters, were computed from the segmented data. Measurements from micro-computed tomography (micro-CT) data of the same bone specimens were regarded as gold standard. Correlations between MSCT and micro-CT data showed great variations, depending on device, imaging parameters and between the bone parameters. Only the bone-volume fraction (BV/TV) parameter was stable with strong correlations. Regarding both HR-pQCT and CBCT, the correlations to micro-CT were strong for bone structure parameters as well as bone stiffness parameters. The CBCT device 3D Accuitomo showed the strongest correlations, but overestimated BV/TV more than three times compared to micro-CT. The imaging protocol most often used in clinical imaging practice at our clinic demonstrated strong correlations as well as low radiation dose. CBCT data of trabecular bone can be used for analysing trabecular bone properties, like bone microstructure and bone biomechanics, showing strong correlations to the reference method of micro-CT. The results depend on choice of CBCT device as well as segmentation method used. The in-house developed code based on homogeneity thresholding is appropriate for CBCT data. The overestimations of BV/TV must be considered when estimating bone properties in future clinical dental implant and osteoporosis research.

No description available.

No description available.

Vector graphics provides powerful tools for drawing scalable 2D imagery. With the rise of mobile computers, of different types of displays and image resolutions, vector graphics is receiving an increasing amount of attention. However, vector graphics is not the leading framework for creating and manipulating 2D imagery. The reason for this reluctance of employing vector graphical frameworks is that it is difficult to handle complex behaviour of colour across the 2D domain. A challenging problem within vector graphics is to define smooth colour functions across the image. In previous work, two approaches exist. The first approach, known as diffusion curves, diffuses colours from a set of input curves and points. The second approach, known as gradient meshes, defines smooth colour functions from control meshes. These two approaches are incompatible: diffusion curves do not support the local behaviour provided by gradient meshes and gradient meshes do not support freeform curves as input. My research aims to narrow the gap between diffusion curves and gradient meshes. With this aim in mind, I propose solutions to create control meshes from freeform curves. I demonstrate that these control meshes can be used to render a vector primitive similar to diffusion curves using subdivision surfaces. With the use of subdivision surfaces, instead of a diffusion process, colour gradients can be locally controlled using colour-gradient curves associated with the input curves. The advantage of local control is further explored in the setting of vector-centric image processing. I demonstrate that a certain contrast enhancement profile, known as the Cornsweet profile, can be modelled via surfaces in images. This approach does not produce saturation artefacts related with previous filter-based methods. Additionally, I demonstrate various approaches to artistic filtering, where the artist locally models given artistic effects. Gradient meshes are restricted to rectangular topology of the control meshes. I argue that this restriction hinders the applicability of the approach and its potential to be used with control meshes extracted from freeform curves. To this end, I propose a mesh-based vector primitive that supports arbitrary manifold topology of the mesh.

Obesity and being overweight have become growing concerns due to their association with many diseases, such as type II diabetes, several types of cancer and heart disease. Thus, obesity treatments have been the focus of a large number of recent studies. Because of these studies, researchers have found that the treatment of obesity and being overweight requires constant monitoring of the patient’s diet. Therefore, measuring food intake each day is considered an important step in the success of a healthy diet. Measuring daily food consumption for obese patients is one of the challenges in obesity management studies. Countless recent studies have suggested that using technology like smartphones may enhance the under-reporting issue in dietary intake consumption. In this thesis, we propose a Food Recognition System (FRS) for calories and nutrient values assumption. The user employs the built-in camera of the smartphone to take a picture of any food before and after eating. The system then processes and classifies the images to detect the type of food and portion size, then uses the information to estimate the number of calories in the food. The estimation and calculation of the food volume and amount of calories in the image is an essential step in our system. Via special approaches, the FRS can estimate the food volume and the existing calories with a high level of accuracy. Our experiment shows high reliability and accuracy of this approach, with less than 15% error.

M.Sc. (Computer Science) / Please refer to full text to view abstract

Deep learning methods for medical image segmentation are hindered by the lack of training data. This thesis aims to develop a method that overcomes this problem. Basic U-net trained on XCAT phantom data was tested first. The segmentation results were unsatisfactory even when artificial quantum noise was added. As a workaround, CycleGAN was used to add tissue textures to the XCAT phantom images by analyzing patient CT images. The generated images were used totrain the network. The textures introduced by CycleGAN improved the segmentation, but some errors remained. Basic U-net was replaced with Attention U-net, which further improved the segmentation. More work is needed to fine-tune and thoroughly evaluate the method. The results obtained so far demonstrate the potential of this method for the segmentation of medical images. The proposed algorithms may be used in iterative image reconstruction algorithms in multi-energy computed tomography.