Title :
An extended image force model of snakes for medical image segmentation and smoothing
Author :
Lu, Hongyu ; Bao, Shanglian
Author_Institution :
Beijing Key Lab. of Med. Phys. & Eng., Peking Univ., Beijing
Abstract :
A scheme of the image force for Snakes, named the eSnake Model, has been introduced based on the electrostatic theory. To improve the ability for segmenting medical images with uneven grayscale intensity, a novel extended eSnake model, eeSnake, is developed to get the desirable image force distribution for Snakes. Breaking through the limitation of the Coulomb law, it can work better with the elasticity and balloon forces of Snakes than eSnake. The pre-calculated data stencil of distance functions is adopted to accelerate the computing speed of the potential field. The analysis points out that the eeSnake model can also function as a smoothing filter. Experiments show that the proposed eeSnake model is satisfactory in both segmentation and noise reduction applications
Keywords :
image denoising; image segmentation; medical image processing; smoothing methods; Coulomb law; eeSnake Model; electrostatic theory; extended image force model; medical image segmentation; noise reduction applications; smoothing; Active contours; Biomedical imaging; Elasticity; Electrostatics; Gray-scale; Image segmentation; Laboratories; Noise reduction; Physics; Smoothing methods;
Conference_Titel :
Signal Processing, 2006 8th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9736-3
Electronic_ISBN :
0-7803-9736-3
DOI :
10.1109/ICOSP.2006.345613