LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes

by   Hongkai Yu, et al.
University of South Carolina
Zhejiang University
Utah State University

One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. Then, a binary labeling is performed to achieve a refined segmentation. One major issue of the existing algorithms for such interactive image segmentation is their preference of an input bounding box that tightly encloses the foreground 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 input bounding box only loosely covers the foreground object. We propose a new Markov Random Fields (MRF) model for segmentation with loosely bounded boxes, including a global similarity constraint to better distinguish the foreground and background, and an additional energy term to encourage consistent labeling of similar-appearance pixels. This MRF model is then solved by an iterated max-flow algorithm. In the experiments, we evaluate LooseCut in three publicly-available image datasets, and compare its performance against several state-of-the-art interactive image segmentation algorithms. We also show that LooseCut can be used for enhancing the performance of unsupervised video segmentation and image saliency detection.


page 5

page 7

page 8


Weakly Supervised Image Segmentation Beyond Tight Bounding Box Annotations

Weakly supervised image segmentation approaches in the literature usuall...

Foreground segmentation based on multi-resolution and matting

We propose a foreground segmentation algorithm that does foreground extr...

Interactive Binary Image Segmentation with Edge Preservation

Binary image segmentation plays an important role in computer vision and...

A New Run-based Connected Component Labeling for Efficiently Analyzing and Processing Holes

This article introduces a new connected component labeling and analysis ...

Interactive Image Segmentation Using Constrained Dominant Sets

We propose a new approach to interactive image segmentation based on som...

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

Manually labeling video datasets for segmentation tasks is extremely tim...

Dominant Sets for "Constrained" Image Segmentation

Image segmentation has come a long way since the early days of computer ...

Please sign up or login with your details

Forgot password? Click here to reset