Multiscale Active Contour Methods in Computer Vision with Applications in Tomography

FAS multigrid;Tranmission tomography;Tomographic reconstruction;CT Scan;Surface initialization;Optical flow;Contour registration;Medical imaging;Mumford-Shah;Scale space;Minimal surfaces

Alvino, Christopher Vincent ; Electrical and Computer Engineering

University:Georgia Institute of Technology

Department:Electrical and Computer Engineering

关键词: FAS multigrid;    Tranmission tomography;    Tomographic reconstruction;    CT Scan;    Surface initialization;    Optical flow;    Contour registration;    Medical imaging;    Mumford-Shah;    Scale space;    Minimal surfaces;   

Others  :  https://smartech.gatech.edu/bitstream/1853/6896/1/alvino_christopher_v_200505_phd.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

Most applications in computer vision suffer from two major difficulties.The first is they are notoriously ridden with sub-optimal local minima.The second is that they typically require highcomputational cost to be solved robustly.The reason for these two drawbacks is that most problems in computer vision, even whenwell-defined, typically require finding a solution in a very large high-dimensional space.It is for these two reasons that multiscale methods are particularly well-suited to problems in computer vision.Multiscale methods, byway of looking at the coarse scale nature of a problem before considering the fine scale nature, often have the ability to avoid sub-optimal local minima and obtain a more globally optimal solution. In addition, multiscale methods typically enjoy reduced computationalcost.This thesis applies novel multiscale active contour methods to several problems in computer vision, especially in simultaneous segmentationand reconstruction of tomography images.In addition, novel multiscale methods are applied to contour registration using minimal surfaces and to the computation of non-linear rotationally invariant optical flow.Finally, a methodology for fast robust image segmentation is presented that relies on a lower dimensional imagebasis derived from an image scale space.The specific advantages of using multiscale methods in each of these problems is highlighted in the various simulations throughout thethesis, particularly their ability to avoid sub-optimal local minima and their ability to solve the problems at a lower overallcomputational cost.