Alpha channel estimation in high resolution images and image sequences

25 August 2005

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 1, 1063-1068
https://doi.org/10.1109/cvpr.2001.990648

Abstract

For Motion Picture Special Effects, it is often necessary to take a source image of an actor, segment the actor from the unwanted background, and then composite over a new background. The standard approach requires the unwanted background to be a blue screen. While this technique is cap- able of handling areas where the foreground blends into the background, the physical requirements present many prac- tical problems. This paper presents an algorithm that re- quires minimal human interaction to segment Motion Pic- ture resolution images and image sequences. We show that it can be used not only to segment badly lit or noisy bluescreen images, but also to segment actors where the background is more varied.

Keywords

This publication has 7 references indexed in Scilit:

A fuzzy technique for image segmentation of color images
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Alpha estimation in natural images
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Environment matting and compositing
Published by Association for Computing Machinery (ACM) ,1999
Blue screen matting
Published by Association for Computing Machinery (ACM) ,1996
AutoKey
Published by Association for Computing Machinery (ACM) ,1995
Image Difference Threshold Strategies and Shadow Detection.
Published by British Machine Vision Association and Society for Pattern Recognition ,1995
Color quantization of images
IEEE Transactions on Signal Processing, 1991