Share Email Print
cover

Proceedings Paper

A new image thresholding and gradient optimization algorithm using object class uncertainty theory
Author(s): Yinxiao Liu; Punam K. Saha
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The knowledge of thresholding and gradients at different object interfaces is of paramount interest for image segmentation and other imaging applications. Most thresholding and gradient optimization methods primarily focus on image histograms and therefore, fail to harness the information embedded in image intensity patterns. Here, we investigate the role of a recently conceived object class uncertainty theory in image thresholding and gradient optimization. The notion of object class uncertainty, a histogram-based feature, is formulated and a computational solution is presented. An energy function is designed that captures spatio-temporal correlation between class uncertainty and image gradient which forms objects and shapes. Optimum thresholds and gradients for different object interfaces are determined from the shape of this energy function. The underlying theory behind the method is that objects manifest themselves with fuzzy boundaries in an acquired image and, in a probabilistic sense, intensities with high class uncertainty are associated with high image gradients generally appearing at object interfaces. The method has been applied on several medical as well as natural images and both thresholds and gradients have successfully been determined for different object interfaces even when some of the thresholds are almost impossible to locate in respective histograms.

Paper Details

Date Published: 30 October 2009
PDF: 9 pages
Proc. SPIE 7497, MIPPR 2009: Medical Imaging, Parallel Processing of Images, and Optimization Techniques, 749702 (30 October 2009); doi: 10.1117/12.851184
Show Author Affiliations
Yinxiao Liu, The Univ. of Iowa (United States)
Punam K. Saha, The Univ. of Iowa (United States)


Published in SPIE Proceedings Vol. 7497:
MIPPR 2009: Medical Imaging, Parallel Processing of Images, and Optimization Techniques
Faxiong Zhang; Faxiong Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top