Fuzzy Clustering Based Image Segmentation of Pap smear Images of Cervical Cancer Cell Using FCM Algorithm
Jyotismita Talukdar · 2013
The FCM clustering algorithm is advantageous over hard clustering methods. The FCM clustering technique, applied on colour image, preserves the colour and a chance of data loss is minimal. Here, we used two types of random number generators to form the membership matrix for each pixel. In this study, three validity measures are used; partition coefficient (PC), partition entropy (PE), and compactness and separation function (SC), which measures the goodness of the clustering result. Shape analysis is carried out to correlate the clustering result to the clinical paradigms of the Pap smear images. The method produces a reasonable result, with some common drawbacks of the FCM clustering In this paper, an attempt has been made to highlight the different shortcomings and usefulness of FCM clustering algorithm.