Multiregion graph cut image partitioning via kernel mapping is used to segment any type of the image data.The piecewise constant model of the graph cut formulation becomes applicable when the image data is transformed by a kernel function. The objective function contains an original data term to evaluate the deviation of the transformed data within each segmentation region, from the piecewise constant model, and a smoothness boundary preserving regularization term. Using a common kernel function, energy minimization typically consists of iterating image partitioning by graph cut iterations and evaluations of region parameters via fixed point computation.The method results in good segmentations and runs faster the graph cut methods. The segmentation from MRI data is an important but time consuming task performed manually by medical ex- perts. The segmentation of MRI image is challenging due to the high diversity in appearance of tissue among thepatient.A semi-automatic interactive brain segmentation system with the ability to adjust operator control is achieved in this method. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.
CITATION STYLE
Ramya, R., & Jayanthi, K. B. (2012). Multiregion image segmentation by graph cuts for brain tumour segmentation. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (Vol. 108 LNICST, pp. 329–332). https://doi.org/10.1007/978-3-642-35615-5_51
Mendeley helps you to discover research relevant for your work.