Learning Graph Cut Energy Functions for Image Segmentation
Abstract: In this paper we address the task of learning how to segment a particular class of objects, by means of a training set of images and their segmentations. In particular we propose a method to overcome the extremely high training time of a previously proposed solution to this problem, Kernelized Structural Support Vector Machines. We employ a one-class SVM working with joint kernels to robustly learn significant support vectors (representative image-mask pairs) and accordingly weight them to build a suitable energy function for the graph cut framework. We report results obtained on two public datasets and a comparison of training times on different training set sizes.
Citation:
Manfredi, Marco; Grana, Costantino; Cucchiara, Rita "Learning Graph Cut Energy Functions for Image Segmentation" Proceedings of the 22nd International Conference on Pattern Recognition, Stockholm, Sweden, pp. 960 -965 , Aug. 24-28, 2014 DOI: 10.1109/ICPR.2014.175
not available
Paper download:
- Author version:
- DOI: 10.1109/ICPR.2014.175