An Experiment with Random Walks and GrabCut in One Cut Interactive Image Segmentation Techniques on MRI Images

This research work proposes the Random Walks and GrabCut in One Cut interactive image segmentation techniques using MRI images, particularly those posing segmentation challenges in terms of complexity in texture, indistinct and/or noisy object boundaries, lower contrast, etc. We have computed accuracy measures such as Jaccard Index (JI), Dice Coefficient (DC) and Hausdorff Distance (HD) besides Visual assessment to understand and assess segmentation accuracy of these techniques. Comparison of the ground truth with segmented image reveals that Random Walks can detect edges/boundaries quite well, especially when those are noisy, however, has tendency to latch onto stronger edges nearby the desired object boundary. GrabCut in One Cut on the other hand sometimes needs more scribbles to achieve acceptable segmentation.