Main Article Content
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.
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.