Image segmentation is a classical and crucial problem in the fields of computer vision and image understanding. This paper gives a review on the variation based active contour model and level set method developed in recent years for image segmentation. The basic ideas of three types of active contour models

i. e.

edge based

region based and edge- region based models

are presented

their advantages and disadvantages are summarized

and a number of improvements are analyzed in detail. The level set method

which is numerically stable and capable of describing the topology change of the contour

is briefly introduced as an advanced numeric algorithm to solve these models. Finally

the potential application of active contour in image registration is discussed.