Comparative Study of Segmentation Methods applied on Cervical Cytology Images

Abstract- Features of the cervical cytology cells determine the severity of cervical cancer. They are used to differentiate benign and malignant cancer cells. Cervical cytology images obtained from Papanicolaou test are segmented into background, nucleus and cytoplasm by various segmentation algorithms like Level Set, Active Contour, Watershed, K-Means Clustering, Morphological reconstruction and Gaussian Mixture model. A comparative study of these methods is carried out in this paper. The features of nucleus and cytoplasm extracted using the above mentioned methods are used to decide the stage of cancer