Abstract
Image segmentation is an important task in many image processing applications. Fuzzy C means clustering algorithm has been widely used for the segmentation. There are so many extended versions of the traditional FCM algorithm which utilizes the local spatial information to decrease the sensitivity of FCM algorithm to noise, but all these algorithms fail to segment the images heavily contaminated by noise. In order to overcome this problem, non-local spatial information is extracted from the image. During the extraction of non-local information, the filtering parameter h is a crucial parameter which needs to be appropriately determined. Instead of using a constant value of h, it can be adaptively determined using the standard deviation of noise present in the image and the non local information calculated by using this adaptive filtering parameter h is termed as noise adaptive non local spatial information. This property of adaptively determining the filtering parameter is utilized in the FCM algorithm, which uses both the local and non local spatial information (MFCM) for the segmentation of MRI images. In this paper Modified FCM algorithm (MFCM) using the noise adaptive non-local information is proposed. This algorithm is called Noise adaptive FCM algorithm for segmentation of MRI brain images using local and non-local spatial information. The trade off parameter which controls the trade-off between the two spatial information is also calculated using the non local spatial information, making it also adaptive in accordance with filtering parameter. Therefore the proposed algorithm adaptively utilizes both the local and non local information making it more robust against the noise as well as preserving the image details. The efficiency of the proposed algorithm is demonstrated by validation studies on synthetic as well as simulated brain MRI images. The results of the proposed algorithm show that the proposed algorithm is very robust to noise and other image artifacts as compared to other state of the art algorithms.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.