SUPERCUT: An accurate and effective interactive image segmentation algorithm

Zhu, Qingsong, Shao, Ling, Song, Zhan and Xie, Yaoqin (2013) SUPERCUT: An accurate and effective interactive image segmentation algorithm. In: ICIP 2013 - 20th IEEE International Conference on Image Processing, 15th - 18th September 2013, Melbourne, Australia.

Full text not available from this repository. (Request a copy)

Abstract

The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT, a novel interactive algorithm for foreground object extraction and segmentation in images. In the algorithm, the mean shift algorithm with a boundary confidence prior is introduced to efficiently pre-segment the original image into super-pixels with precise boundary. Secondly, a Bayes decision theory is introduced to model and cluster the super-pixels so as to obtain an initial effective classification of super-pixels. To achieve a more accurate object segmentation result, a boundary refinement using Interactive rectangle box with GMM learning is adopted. Experimental results on a benchmark data set show that the proposed framework is highly effective and can accurately segment a wide variety of natural images with ease.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	16 Jun 2015 12:56
Last Modified:	13 Oct 2019 00:36
URI:	http://nrl.northumbria.ac.uk/id/eprint/22950

Downloads