Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
What Energy Functions Can Be Minimizedvia Graph Cuts?
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object segmentation using graph cuts based active contours
Computer Vision and Image Understanding
Modification of the segmentation based on Graph cut method
CSCS '11 Proceedings of the 2nd international conference on Circuits, systems, control, signals
| Hi-index | 0.00 |
This paper presents the possibility of deformation of the object contours using Graph cut method. The user interactively defines the contour of the object based on own requirements for segmentation. The procedure proposed in this article seeks global optimal solution Graph cut segmentation for local parts of the input image versus finding a global optimal solution for the whole input image in classical Graph cut segmentation. On the basis of local segmentation the contour of the object was deformed, which was defined by the user. The advantage of local processing in this process is rapid implementation of Graph cut segmentation even if the input resolution of the image is high. Higher speed is achieved by the local segmentation determined only on the vicinity of the route initialization contour and the segmentation is not performed on the entire input image. The size of the vicinity of the initialization contour which is taken into account by the processing of the image is determined interactively by the user. Terminals of the object and background in this procedure are determined automatically from initialization contours specified by the user. The paper presents the experimental results and comparison with the classical procedure using Graph cut segmentation.