Interactive Binary Image Segmentation with Edge Preservation

09/10/2018
by   Jianfeng Zhang, et al.
6

Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition. In this paper, we propose a novel interactive binary image segmentation method based on the Markov Random Field (MRF) framework and the fast bilateral solver (FBS) technique. Specifically, we employ the geodesic distance component to build the unary term. To ensure both computation efficiency and effective responsiveness for interactive segmentation, superpixels are used in computing geodesic distances instead of pixels. Furthermore, we take a bilateral affinity approach for the pairwise term in order to preserve edge information and denoise. Through the alternating direction strategy, the MRF energy minimization problem is divided into two subproblems, which then can be easily solved by steepest gradient descent (SGD) and FBS respectively. Experimental results on the VGG interactive image segmentation dataset show that the proposed algorithm outperforms several state-of-the-art ones, and in particular, it can achieve satisfactory edge-smooth segmentation results even when the foreground and background color appearances are quite indistinctive.

READ FULL TEXT

page 1

page 6

page 7

research
07/11/2015

LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes

One popular approach to interactively segment the foreground object of i...
research
02/21/2017

Crowd Sourcing Image Segmentation with iaSTAPLE

We propose a novel label fusion technique as well as a crowdsourcing pro...
research
01/13/2012

NegCut: Automatic Image Segmentation based on MRF-MAP

Solving the Maximum a Posteriori on Markov Random Field, MRF-MAP, is a p...
research
07/08/2017

Fast Asymmetric Fronts Propagation for Image Segmentation

In this paper, we introduce a generalized asymmetric fronts propagation ...
research
02/01/2019

Fast and Optimal Laplacian Solver for Gradient-Domain Image Editing using Green Function Convolution

In computer vision, the gradient and Laplacian of an image are used in m...
research
01/09/2015

Filter Design and Performance Evaluation for Fingerprint Image Segmentation

Fingerprint recognition plays an important role in many commercial appli...
research
08/17/2021

A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

Image co-segmentation has attracted a lot of attentions in computer visi...

Please sign up or login with your details

Forgot password? Click here to reset