Paper Info
Title
Loosecut: Interactive Image Segmentation With Loosely Bounded Boxes
Abstract
One popular approach to interactively segment an object of interest from an image is to annotate a bounding box that covers the object, followed by a binary labeling. However, the existing algorithms for such interactive image segmentation prefer a bounding box that tightly encloses the object. This increases the annotation burden, and prevents these algorithms from utilizing automatically detected bounding boxes. In this paper, we develop a new LooseCut algorithm that can handle cases where the bounding box only loosely covers the object. We propose a new Markov Random Fields (MRF) model for segmentation with loosely bounded boxes, including an additional energy term to encourage consistent labeling of similar appearance pixels and a global similarity constraint to better distinguish the foreground and background. This MRF model is then solved by an iterated max-flow algorithm. We evaluate LooseCut in three public image datasets, and show its better performance against several state-of-the-art methods when increasing the bounding-box size.
Year
DOI
Venue
2015
10.1109/icip.2017.8296900
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Keywords
Field
DocType
Interactive image segmentation, Graph cut, Loosely bounded box
Scale-space segmentation,Salience (neuroscience),Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Minimum bounding box,Computer vision,Pattern recognition,Segmentation,Pixel,Machine learning,Bounding overwatch
Journal
Volume
ISSN
Citations 
abs/1507.03060
1522-4880
3
PageRank 
References 
Authors
0.38
16
9
Name
Order
Citations
PageRank
Hongkai Yu15211.49
Youjie Zhou2747.79
Hui Qian35913.26
Min Xian4215.84
Yuewei Lin516011.18
Dazhou Guo6305.90
kang zheng730.38
kareem abdelfatah892.18
Song Wang911912.91