Unsupervised segmentation of cell nuclei in cervical smear images using active contour with adaptive local region fitting energy modelling

In this paper, we propose a method based on an adaptive active contour modelling to segment the cell nuclei from cervical smear images. The basic idea of our method is to make a contour to adaptively deform so as to get a minimized given region energy function. In order to make the evolution of the contour rely less on the intensity homogeneity and achieve the purpose of adaptive segmentation of the cell nuclei, the proposed method utilizes the morphology method to initialize the active contour modelling. Then a Gaussian kernel function is used to extract the local region and defines its local region fitting energy function which approximates the image intensities on the two sides of the contour in the local region. Finally, the Split Bregman method is used to obtain a robust numerical solution and to generate the segmentation results. In our experiments, the proposed approach can obtain accurate segmentation results compared with some state-of-the-art approaches.