Open Access Open Access  Restricted Access Subscription or Fee Access

Histon-Based FCM for Medical Image Segmentation

Baowei Zhang, Tong Sun


This paper investigates FCM(fuzzy c-means) for medical image segmentation, which performs well in natural images while poor in complex medical images. In our opinion, one important reason for this is that membership matrix and cluster centers in FCM are assigned randomly. Aiming at this, this paper adopts the idea of discretization in data mining for initializing cluster centers, and the proposed schema is performed through 3 steps. First, histon of the given image is constructed based on a window defined in mean shift, including range and spatial information; second, local maximums of histon are retrieved and sorted in the descending order, and some of them are selected as initial cluster centers with the help of discretization method; finally, FCM performs based on initial centers for image segmentation. Experiments results show that the proposed schema can achieve the main parts of the given image compared to conventional FCM, together with high efficiency.


Medical image segmentation, FCM, histon, discretization.

Full Text:



  • There are currently no refbacks.

Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.