Segmentation of brain MR images with directional weighted optimized fuzzy C-means clustering
One of the fundamental and significant distinctiveness of an image is that, adjacent pixels are extremely correlated. The spatial information in the image improves the quality of clustering which is not utilized in the standard Fuzzy C-Means (FCM). FCM algorithm is not robust against noise. In this...
| Main Authors: | , , |
|---|---|
| Format: | Proceeding |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/16516/ http://ir.unimas.my/id/eprint/16516/1/Segmentation%20of%20brain%20MR%20images%20with%20directional%20weighted%20optimized%20fuzzy%20C-means%20clustering%20%28abstrak%29.pdf |
| Summary: | One of the fundamental and significant distinctiveness of an image is that, adjacent pixels are extremely correlated. The spatial information in the image improves the quality of clustering which is not utilized in the standard Fuzzy C-Means (FCM). FCM algorithm is not robust against noise. In this paper, we proposed an enhanced version of Fuzzy C-Means algorithm that incorporates spatial information into the membership function for clustering of brain MR images. The modified Fuzzy C-Means finds optimal clusters in an automatic way with the help of some cluster validity criteria. Additionally, spatial weighted information is incorporated in the spatial FCM. The spatial function is the weighted summation of the membership function in the neighborhood of each pixel under consideration. The advantages of this new method are: (a) it yields regions more homogeneous than those of other methods and (b) it removes noisy spots. It is less sensitive to noise as compared to other techniques. We tested our method on various brain MR images, and the technique has proved as a powerful method in the segmentation of noisy images. |
|---|