A knowledge driven stochastic active contour model (KDS-SNAKE) for contour finding of distinct features
G.I. Chiou, Jenq–Neng Hwang · 2005
Contour finding of distinct features in 2D/3D 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 knowledge driven stochastic active contour model (KDS-SNAKE), which integrates a neural network classifier for systematic knowledge building, an active contour model (also known as "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 KDS-SNAKE to extraction of several types of contours in magnetic resonance (MR) images is presented.