Matching Items (5)
Filtering by
- All Subjects: Computer vision
- All Subjects: Three-dimensional printing
- Genre: Academic theses
- Creators: Frakes, David
Description
Image understanding has been playing an increasingly crucial role in vision applications. Sparse models form an important component in image understanding, since the statistics of natural images reveal the presence of sparse structure. Sparse methods lead to parsimonious models, in addition to being efficient for large scale learning. In sparse modeling, data is represented as a sparse linear combination of atoms from a "dictionary" matrix. This dissertation focuses on understanding different aspects of sparse learning, thereby enhancing the use of sparse methods by incorporating tools from machine learning. With the growing need to adapt models for large scale data, it is important to design dictionaries that can model the entire data space and not just the samples considered. By exploiting the relation of dictionary learning to 1-D subspace clustering, a multilevel dictionary learning algorithm is developed, and it is shown to outperform conventional sparse models in compressed recovery, and image denoising. Theoretical aspects of learning such as algorithmic stability and generalization are considered, and ensemble learning is incorporated for effective large scale learning. In addition to building strategies for efficiently implementing 1-D subspace clustering, a discriminative clustering approach is designed to estimate the unknown mixing process in blind source separation. By exploiting the non-linear relation between the image descriptors, and allowing the use of multiple features, sparse methods can be made more effective in recognition problems. The idea of multiple kernel sparse representations is developed, and algorithms for learning dictionaries in the feature space are presented. Using object recognition experiments on standard datasets it is shown that the proposed approaches outperform other sparse coding-based recognition frameworks. Furthermore, a segmentation technique based on multiple kernel sparse representations is developed, and successfully applied for automated brain tumor identification. Using sparse codes to define the relation between data samples can lead to a more robust graph embedding for unsupervised clustering. By performing discriminative embedding using sparse coding-based graphs, an algorithm for measuring the glomerular number in kidney MRI images is developed. Finally, approaches to build dictionaries for local sparse coding of image descriptors are presented, and applied to object recognition and image retrieval.
ContributorsJayaraman Thiagarajan, Jayaraman (Author) / Spanias, Andreas (Thesis advisor) / Frakes, David (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
There is a growing interest for improved high-accuracy camera calibration methods due to the increasing demand for 3D visual media in commercial markets. Camera calibration is used widely in the fields of computer vision, robotics and 3D reconstruction. Camera calibration is the first step for extracting 3D data from a 2D image. It plays a crucial role in computer vision and 3D reconstruction due to the fact that the accuracy of the reconstruction and 3D coordinate determination relies on the accuracy of the camera calibration to a great extent. This thesis presents a novel camera calibration method using a circular calibration pattern. The disadvantages and issues with existing state-of-the-art methods are discussed and are overcome in this work. The implemented system consists of techniques of local adaptive segmentation, ellipse fitting, projection and optimization. Simulation results are presented to illustrate the performance of the proposed scheme. These results show that the proposed method reduces the error as compared to the state-of-the-art for high-resolution images, and that the proposed scheme is more robust to blur in the imaged calibration pattern.
ContributorsPrakash, Charan Dudda (Author) / Karam, Lina J (Thesis advisor) / Frakes, David (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2012
Description
Diabetic retinopathy (DR) is a common cause of blindness occurring due to prolonged presence of diabetes. The risk of developing DR or having the disease progress is increasing over time. Despite advances in diabetes care over the years, DR remains a vision-threatening complication and one of the leading causes of blindness among American adults. Recent studies have shown that diagnosis based on digital retinal imaging has potential benefits over traditional face-to-face evaluation. Yet there is a dearth of computer-based systems that can match the level of performance achieved by ophthalmologists. This thesis takes a fresh perspective in developing a computer-based system aimed at improving diagnosis of DR images. These images are categorized into three classes according to their severity level. The proposed approach explores effective methods to classify new images and retrieve clinically-relevant images from a database with prior diagnosis information associated with them. Retrieval provides a novel way to utilize the vast knowledge in the archives of previously-diagnosed DR images and thereby improve a clinician's performance while classification can safely reduce the burden on DR screening programs and possibly achieve higher detection accuracy than human experts. To solve the three-class retrieval and classification problem, the approach uses a multi-class multiple-instance medical image retrieval framework that makes use of spectrally tuned color correlogram and steerable Gaussian filter response features. The results show better retrieval and classification performances than prior-art methods and are also observed to be of clinical and visual relevance.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Frakes, David (Committee member) / Arizona State University (Publisher)
Created2012
Description
The advent of medical imaging has enabled significant advances in pre-procedural planning, allowing cardiovascular anatomy to be visualized noninvasively before a procedure. However, absolute scale and tactile information are not conveyed in traditional pre-procedural planning based on images alone. This information deficit fails to completely prepare clinicians for complex heart repair, where surgeons must consider the varied presentations of cardiac morphology and malformations. Three-dimensional (3D) visualization and 3D printing provide a mechanism to construct patient-specific, scale models of cardiovascular anatomy that surgeons and interventionalists can examine prior to a procedure. In addition, the same patient-specific models provide a valuable resource for educating future medical professionals. Instead of looking at idealized images on a computer screen or pages from medical textbooks, medical students can review a life-like model of patient anatomy.
In cases where surgical repair is insufficient to return the heart to normal function, a patient may proceed to advanced heart failure, and a heart transplant may be required. Unfortunately, a finite number of available donor hearts are available. A mechanical circulatory support (MCS) device can be used to bridge the time between heart failure and reception of a donor heart. These MCS devices are typically constructed for the adult population. Accordingly, the size associated to the device is a limiting factor for small adults or pediatric patients who often have smaller thoracic measurements. While current eligibility criteria are based on correlative measurements, the aforementioned 3D visualization capabilities can be leveraged to accomplish patient-specific fit analysis.
The main objectives of the work presented in this dissertation were 1) to develop and evaluate an optimized process for 3D printing cardiovascular anatomy for surgical planning and medical education and 2) to develop and evaluate computational tools to assess MCS device fit in specific patients. The evaluations for objectives 1 and 2 were completed with a collection of qualitative and quantitative validations. These validations include case studies to illustrate meaningful, qualitative results as well as quantitative results from surgical outcomes. The latter results present the first quantitative supporting evidence, beyond anecdotal case studies, regarding the efficacy of 3D printing for pre-procedural planning; this data is suitable as pilot data for clinical trials. The products of this work were used to plan 200 cardiovascular procedures (including 79 cardiothoracic surgeries at Phoenix Children's Hospital), via 3D printed heart models and assess MCS device fit in 29 patients across 6 countries.
In cases where surgical repair is insufficient to return the heart to normal function, a patient may proceed to advanced heart failure, and a heart transplant may be required. Unfortunately, a finite number of available donor hearts are available. A mechanical circulatory support (MCS) device can be used to bridge the time between heart failure and reception of a donor heart. These MCS devices are typically constructed for the adult population. Accordingly, the size associated to the device is a limiting factor for small adults or pediatric patients who often have smaller thoracic measurements. While current eligibility criteria are based on correlative measurements, the aforementioned 3D visualization capabilities can be leveraged to accomplish patient-specific fit analysis.
The main objectives of the work presented in this dissertation were 1) to develop and evaluate an optimized process for 3D printing cardiovascular anatomy for surgical planning and medical education and 2) to develop and evaluate computational tools to assess MCS device fit in specific patients. The evaluations for objectives 1 and 2 were completed with a collection of qualitative and quantitative validations. These validations include case studies to illustrate meaningful, qualitative results as well as quantitative results from surgical outcomes. The latter results present the first quantitative supporting evidence, beyond anecdotal case studies, regarding the efficacy of 3D printing for pre-procedural planning; this data is suitable as pilot data for clinical trials. The products of this work were used to plan 200 cardiovascular procedures (including 79 cardiothoracic surgeries at Phoenix Children's Hospital), via 3D printed heart models and assess MCS device fit in 29 patients across 6 countries.
ContributorsRyan, Justin Robert (Author) / Frakes, David (Thesis advisor) / Collins, Daniel (Committee member) / LaBelle, Jeffrey (Committee member) / Pizziconi, Vincent (Committee member) / Pophal, Stephen (Committee member) / Arizona State University (Publisher)
Created2015
Description
With the growing popularity of 3d printing in recreational, research, and commercial enterprises new techniques and processes are being developed to improve the quality of parts created. Even so, the anisotropic properties is still a major hindrance of parts manufactured in this method. The goal is to produce parts that mimic the strength characteristics of a comparable part of the same design and materials created using injection molding. In achieving this goal the production cost can be reduced by eliminating the initial investment needed for the creation of expensive tooling. This initial investment reduction will allow for a wider variant of products in smaller batch runs to be made available. This thesis implements the use of ultraviolet (UV) illumination for an in-process laser local pre-deposition heating (LLPH). By comparing samples with and without the LLPH process it is determined that applied energy that is absorbed by the polymer is converted to an increase in the interlayer temperature, and resulting in an observed increase in tensile strength over the baseline test samples. The increase in interlayer bonding thus can be considered the dominating factor over polymer degradation.
ContributorsKusel, Scott Daniel (Author) / Hsu, Keng (Thesis advisor) / Sodemann, Angela (Committee member) / Kannan, Arunachala M (Committee member) / Arizona State University (Publisher)
Created2017