Efficient Graph Cuts for Multi-region Segmentation
University essay from Lunds universitet/Matematik LTH
Abstract: Many problems in computer vision can be formulated as optimization problems that can be solved using minimum cuts in flow networks. However, these applications can be demanding, with the memory bandwidth being the main bottleneck on the performance. This thesis introduces an efficient solver that reduces the memory requirements while improving the speed. The code is freely available on-line.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)