Title :
A neural network-based stochastic active contour model (NNS-SNAKE) for contour finding of distinct features
Author :
Chiou, Greg I. ; Hwang, Jenq-Neng
Author_Institution :
Boeing Comput. Services, Seattle, WA, USA
fDate :
10/1/1995 12:00:00 AM
Abstract :
Contour finding of distinct features in 2-D/3-D images is essential for image analysis and computer vision. To overcome the potential problems associated with existing contour finding algorithms, we propose a framework, called the neural network-based stochastic active contour model (NNS-SNAKE), which integrates a neural network classifier for systematic knowledge building, an active contour model (also known as the “Snake”) for automated contour finding using energy functions, and the Gibbs sampler to help the snake to find the most probable contour using a stochastic decision mechanism. Successful application of the NNS-SNAKE to extraction of several types of contours on magnetic resonance (MR) images is presented
Keywords :
biomedical NMR; computer vision; feature extraction; image sampling; medical image processing; neural nets; stochastic processes; 2-D images; 3-D images; Gibbs sampler; MRI; NNS-SNAKE; Snake; automated contour finding; computer vision; contour finding; contour finding algorithms; distinct features; energy functions; image analysis; magnetic resonance images; neural network classifier; neural network stochastic active contour model; stochastic decision mechanism; systematic knowledge; Active contours; Computer vision; Helium; Image edge detection; Magnetic resonance; Neural networks; Shape; Stochastic processes; Stochastic systems; Tracking;
Journal_Title :
Image Processing, IEEE Transactions on
