Multi - Scale Active Shape
نویسندگان
چکیده
A multi-scale shape description tool based on active contour models has been developed, allowing to regularize and describe shape changes across scales. The internal energy of this spline-based model depends on analytic shape forces, and the external energy incorporates geometric image features like the image gradient and isophote curvature. Results of applying this technique to artiicial images with known shapes are presented, and the application to medical imaging in clinical neurology is discussed.
منابع مشابه
Hierarchical Shape Description of MR Brain Images Based on Active Contour Models and Multi-Scale Differential Invariants
We have developed a novel hierarchical shape description tool, combining two recently developed and powerful techniques in image processing: differential invariants in scale space, and active contour models. We employ this tool for data-driven quantitative shape studies of Magnetic Resonance (MR) images of the brain at multiple scales. Extracting a shape at different levels of scale yields a mu...
متن کاملMulti-scale and hierarchical description using energy controlled active balloon model
A novel multi-scale tree construction algorithm for three dimensional shape using \Energy Controlled Active Balloon Model(EC-ABM)" is proposed. The key idea is that (1) internal and external energies and a number of surfaces which make up the ABM are controlled at each shrinking steps, and (2) each converged shape is regarded as one multi-scale shape. Some experimental three dimensional recogni...
متن کاملMulti-Scale Shape Description in Medical Imaging
We have developed a hierarchical tool for shape description in medical imaging, based on the concepts of scale space and active contour models. The scale space representation allows to capture global shape outlines at a high level of scale or low image resolution, while finer scale shape details can be tracked for increasing levels of image resolution or decreasing scales, thus allowing to quan...
متن کاملMulti-Scale and Shape Constrained Localized Region-Based Active Contour Segmentation of Uterine Fibroid Ultrasound Images in HIFU Therapy
PURPOSE To overcome the severe intensity inhomogeneity and blurry boundaries in HIFU (High Intensity Focused Ultrasound) ultrasound images, an accurate and efficient multi-scale and shape constrained localized region-based active contour model (MSLCV), was developed to accurately and efficiently segment the target region in HIFU ultrasound images of uterine fibroids. METHODS We incorporated a...
متن کاملA multi-scale method for automatically extracting the dominant features of cervical vertebrae in CT images
Localization of the dominant points of cervical spines in medical images is important for improving the medical automation in clinical head and neck applications. In order to automatically identify the dominant points of cervical vertebrae in neck CT images with precision, we propose a method based on multi-scale contour analysis to analyzing the deformable shape of spines. To extract the spine...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1997