Skip to main content


eCommons@Cornell >
College of Engineering >
Computer Science >
Computer Science Technical Reports >

Please use this identifier to cite or link to this item:
Title: A Variable Window Approach to Early Vision
Authors: Boykov, Yuri
Veksler, Olga
Zabih, Ramin
Keywords: computer science
technical report
Issue Date: Dec-1997
Publisher: Cornell University
Abstract: Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object boundaries. We describe an efficient method for choosing an arbitrarily shaped connected window, in a manner which varies at each pixel. Our approach can be applied to many problems, including image restoration and visual correspondence. It runs in linear time, and takes a few seconds on traditional benchmark images. Performance on both synthetic and real imagery with ground truth appears promising.
Appears in Collections:Computer Science Technical Reports

Files in This Item:

File Description SizeFormat
97-1657.pdf771.99 kBAdobe PDFView/Open
97-1657.ps6.06 MBPostscriptView/Open

Refworks Export

Items in eCommons are protected by copyright, with all rights reserved, unless otherwise indicated.


© 2014 Cornell University Library Contact Us