Journal
PATTERN RECOGNITION
Volume 44, Issue 4, Pages 839-853Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2010.10.015
Keywords
Shape from focus; Multifocus; Image fusion; Depth map estimation; Curvelet transform; Contrast limited adaptive histogram equalization
Funding
- Canada Research Chair program
- NSERC
- AUTO21 NCE
Ask authors/readers for more resources
A new method for focus measure computation is proposed to reconstruct 3D shape using image sequence acquired under varying focus plane. Adaptive histogram equalization is applied to enhance varying contrast across different image regions for better detection of sharp intensity variations. Fast discrete curvelet transform (FDCT) is employed for enhanced representation of singularities along curves in an input image followed by noise removal using bivariate shrinkage scheme based on locally estimated variance. The FDCT coefficients with high activity are exploited to detect high frequency variations of pixel intensities in a sequence of images. Finally, focus measure is computed utilizing neighborhood support of these coefficients to reconstruct the shape and a well-focused image of the scene being probed. (C) 2010 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available