A PARAMETRIC FITTING ALGORITHM FOR SEGMENTATION OF CELL IMAGES

This paper presents a parametric fitting algorithm for segmentation of cervical and breast cell images from cytology smears. A parametric el liptical model for cells is introduced and the parameters adjusted to fit the cell shapes while minimizing a cost function. Segmentation res ults of noisy human cervical cell and textured breast cell images demo nstrate that the proposed parametric fitting algorithm is very success ful in segmentation of images of both nonoverlapped and overlapped ell iptically shaped cells.