Log In Sign Up

Foreground segmentation based on multi-resolution and matting

by   Xintong Yu, et al.

We propose a foreground segmentation algorithm that does foreground extraction under different scales and refines the result by matting. First, the input image is filtered and resampled to 5 different resolutions. Then each of them is segmented by adaptive figure-ground classification and the best segmentation is automatically selected by an evaluation score that maximizes the difference between foreground and background. This segmentation is upsampled to the original size, and a corresponding trimap is built. Closed-form matting is employed to label the boundary region, and the result is refined by a final figure-ground classification. Experiments show the success of our method in treating challenging images with cluttered background and adapting to loose initial bounding-box.


page 1

page 2

page 3

page 4


LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes

One popular approach to interactively segment the foreground object of i...

An automatic and efficient foreground object extraction scheme

This paper presents a method to differentiate the foreground objects fro...

A Robust Regression Approach for Background/Foreground Segmentation

Background/foreground segmentation has a lot of applications in image an...

Adaptive Foreground and Shadow Detection inImage Sequences

This paper presents a novel method of foreground segmentation that disti...

Automatic Foreground Extraction using Multi-Agent Consensus Equilibrium

While foreground extraction is fundamental to virtual reality systems an...

Better Foreground Segmentation Through Graph Cuts

For many tracking and surveillance applications, background subtraction ...

Unsupervised segmentation via semantic-apparent feature fusion

Foreground segmentation is an essential task in the field of image under...