Share Email Print

Proceedings Paper

Skeletonization with hollow detection on gray image by gray weighted distance transform
Author(s): Prabir Bhattacharya; Kai Qian; Siqi Cao; Yi Qian
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A skeletonization algorithm that could be used to process non-uniformly distributed gray-scale images with hollows was presented. This algorithm is based on the Gray Weighted Distance Transformation. The process includes a preliminary phase of investigation in the hollows in the gray-scale image, whether these hollows are considered as topological constraints for the skeleton structure depending on their statistically significant depth. We then extract the resulting skeleton that has certain meaningful information for understanding the object in the image. This improved algorithm can overcome the possible misinterpretation of some complicated images in the extracted skeleton, especially in images with asymmetric hollows and asymmetric features. This algorithm can be executed on a parallel machine as all the operations are executed in local. Some examples are discussed to illustrate the algorithm.

Paper Details

Date Published: 1 October 1998
PDF: 9 pages
Proc. SPIE 3460, Applications of Digital Image Processing XXI, (1 October 1998); doi: 10.1117/12.323232
Show Author Affiliations
Prabir Bhattacharya, Univ. of Nebraska/Lincoln (United States)
Kai Qian, Southern Polytechnic State Univ. (United States)
Siqi Cao, Univ. of Nebraska/Lincoln (United States)
Yi Qian, Shanghai XiuHui Univ. (China)

Published in SPIE Proceedings Vol. 3460:
Applications of Digital Image Processing XXI
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top