Initially Graph G = is formed by nodes V and edges E. We got better results for Grow cut algorithm.
![mex compiler matlab 64 bit mex compiler matlab 64 bit](http://khailaie.com/notes/MEX/mingw-w64-installation.jpg)
#Mex compiler matlab 64 bit 64 Bit#
So, it’s better to have MATLAB on 32 bit compiler rather than having it on 64 bit because of the “mex” compilation problem. But, there might be a small mistake which I am not able to find. Implemented the same equations as in the Yuri’s paper.This approach is compared with the other advanced techniques such as Grab cut, Lazy snapping. The effect of adding noise to the original image on the actual segmentation is studied. Implemented algorithm is tested on both the Synthetic medical images (Brain MRI) and Non-medical images.Here Interactive segmentation involves imposing both Hard Constraints (Indicate the pixels of the object region and the background region by the user) and soft constraints (Boundary and region properties of the segments).Implemented Interactive Segmentation using graph cut based on the paper Yuri Boykov Marie –Pierre Jolly “Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images”.I am including all my work in the RAR file, which can be downloaded here. This is part of my course work for Medical Image Analysis. Also, we have compared the performance of our algorithm with few other segmentation algorithms which are MATLAB programs and are available online. In this project we(I and my friend Raghu kiran) tried to implemented the paper “Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images”, by Y.Boykov,M.P Jolly, ICCV 2001 using Matlab.