Hybrid Segmentation Approach using FCM and Dominant Intensity Grouping with Region Growing on Medical Image

Main Article Content

S.Zulaikha Beevi
M.Mohammed Sathik,K.Senthamarai Kannan, J.H Jaseema Yasmin,


Image segmentation is a critical part of clinical diagnostic tools. Medical image segmentation demands an efficient and robust seg-mentation algorithm against noise. Therefore, accurate segmentation of medical images is highly challenging; however, accurate segmentation of these images is very important in correct diagnosis by clinical tools. The conventional fuzzy c-means algorithm is an efficient clustering algo-rithm that is used in medical image segmentation. But FCM is highly vulnerable to noise since it uses only intensity values for clustering the images. This paper aims to develop a novel and efficient fuzzy spatial c-means clustering algorithm which is robust to noise. The proposed seg-mentation is based on improved spatial fuzzy c mean with dominant grey level of image. In this method, the color image is converted to grey level image and to make the approach more robust to noise. The input image is deniosed using an efficient denoising algorithm to decrease noise. Afterwards, the fuzzy spatial information is used to calculate membership value. Clusters with error more than a threshold are divided to two sub clusters. This process continues until there remain no such, erroneous, clusters. The dominant connected component of each cluster is obtained -- if existed. In obtained dominant connected components, the n biggest connected components are selected. N is specified based upon considered number of clusters. Averages of grey levels of n selected components, in grey level image, are considered as dominant grey levels. Dominant grey levels are used as cluster center. Eventually, the image is clustered using specified cluster center. Using the dominant cluster center, the image is segmented using region growing. Experimental results are demonstrated to show effectiveness of new method.


Keywords: FCM, Dominant grey level, Medical image, segmentation.


Download data is not yet available.

Article Details