Active contours algorithm with an adaptive gaussian distribution fitting energies and its application to industrial CT image segmentation
Xiao Luo, Yongning Zou · 2015
In image segmentation, Local binary fitting model (LBF) is widely used to cope with intensity inhomogeneity.It is insensitive to the initial contour with a large scale parameter and it can make the active contours become smooth and close to the object of the real border with the reduction of scale parameters.For the purpose of enhancing the quality of intensity inhomogeneity image segmentation, we advance a new adaptive rule to obtain the scale parameter.Experimental results on industrial CT image demonstrate that our method is insensitive to the initial contour and accurate for extracting the object.