IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Image segmentation with ratio cut
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
This paper puts forward a segmentation algorithm for undersea hydrrothermal vent image. Basing on the in-depth analysis on the difference between sea-water area, rock and smoke area, which are the three kinds of objects in the typical undersea hydrothermal vent image, we employ both OTSU thresholding and Fuzzy C-Mean (FCM) clustering to segment the image, and discard all the non-interested area living only smoke area. Experiments show that this algorithm can segment the image both quickly and precisely.