Faster α-expansion via dynamic programming and image partitioning

Image segmentation is the task of assigning a label to each image pixel. When the number of labels is greater than two (multi-label) the segmentation can be modelled as a multi-cut problem in graphs. In the general case, finding the minimum cut in a graph is an NP-hard problem, in which improving th...

Full description

Saved in:
Bibliographic Details
Published in2020 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8
Main Authors Fontinele, Jefferson, Mendonca, Marcelo, Ruiz, Marco, Papa, Joao, Oliveira, Luciano
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2020
Subjects
Approximation algorithms
Dynamic programming
Heuristic algorithms
Image segmentation
multi-label
Optimization
Partitioning algorithms
Runtime
α-expansion
Online AccessGet full text

Cover

More Information
Summary:Image segmentation is the task of assigning a label to each image pixel. When the number of labels is greater than two (multi-label) the segmentation can be modelled as a multi-cut problem in graphs. In the general case, finding the minimum cut in a graph is an NP-hard problem, in which improving the results concerning time and quality is a major challenge. This paper addresses the multi-label problem applied in interactive image segmentation. The proposed approach makes use of dynamic programming to initialize an α-expansion, thus reducing its runtime, while keeping the Dice-score measure in an interactive segmentation task. Over BSDS data set, the proposed algorithm was approximately 51.2% faster than its standard counterpart, 36.2% faster than Fast Primal-Dual (FastPD) and 10.5 times faster than quadratic pseudo-boolean optimization (QBPO) optimizers, while preserving the same segmentation quality.
ISSN:2161-4407
DOI:10.1109/IJCNN48605.2020.9207032