Active contours in segmentation of fiber like objects

One of the most critical steps in the process of digital image analysis is segmentation: separation of an image into regions that have strong correlation with objects of the real world. Segmentation of fiber like objects is a key problem in several image processing application. This paper overviews deformable models, as well as segmentation techniques employed for fiber like objects and propose an algorithm for segmentation of endoplasmatic reticulum using deformable models with automatic initialization.