A Gradient Descent Approximation for Graph Cuts

Authors:
Alparslan Yildiz;Yusuf Sinan Akgul
Affiliations:
Computer Vision Lab., Department of Computer Engineering, Gebze Institute of Technology, Gebze, Turkey 41400;Computer Vision Lab., Department of Computer Engineering, Gebze Institute of Technology, Gebze, Turkey 41400
Venue:
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Year:
2009

Citing 5
Cited 0

A new approach to the maximum-flow problem

Journal of the ACM (JACM)
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multilevel Banded Graph Cuts Method for Fast Image Segmentation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Active Graph Cuts

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Dynamic Graph Cuts for Efficient Inference in Markov Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

Graph cuts have become very popular in many areas of computer vision including segmentation, energy minimization, and 3D reconstruction. Their ability to find optimal results efficiently and the convenience of usage are some of the factors of this popularity. However, there are a few issues with graph cuts, such as inherent sequential nature of popular algorithms and the memory bloat in large scale problems. In this paper, we introduce a novel method for the approximation of the graph cut optimization by posing the problem as a gradient descent formulation. The advantages of our method is the ability to work efficiently on large problems and the possibility of convenient implementation on parallel architectures such as inexpensive Graphics Processing Units (GPUs). We have implemented the proposed method on the Nvidia 8800GTS GPU. The classical segmentation experiments on static images and video data showed the effectiveness of our method.