Share Email Print
cover

Proceedings Paper

Three-dimensional adaptive split-and-merge method for medical image segmentation
Author(s): Jin-Shin Chou; Chin-Tu Chen; Shiuh-Yung James Chen; Wei-Chung Lin
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We have developed a three-dimensional image segmentation algorithm using adaptive split- and-merge method. The framework of this method is based on a two-dimensional (2-D) split- and-merge scheme and the region homogeneity analysis. Hierarchical oct-tree is used as the basic data structure throughout the analysis, analogous to quad-tree in the 2-D case. A localized feature analysis and statistical tests are employed in the testing of region homogeneity. In feature analysis, standard deviation, gray-level contrast, likelihood ratio, and their corresponding co-occurrence matrix are computed. Histograms of the near-diagonal elements of the co-occurrence matrix are calculated. An optimal thresholding method is then applied to determine the desired threshold values. These values are then used as constraints in the tests, such that decision of splitting or merging can be made.

Paper Details

Date Published: 26 June 1992
PDF: 7 pages
Proc. SPIE 1660, Biomedical Image Processing and Three-Dimensional Microscopy, (26 June 1992); doi: 10.1117/12.59573
Show Author Affiliations
Jin-Shin Chou, Univ. of Chicago and Northwestern Univ. (United States)
Chin-Tu Chen, Univ. of Chicago (United States)
Shiuh-Yung James Chen, Northwestern Univ. (United States)
Wei-Chung Lin, Northwestern Univ. (United States)


Published in SPIE Proceedings Vol. 1660:
Biomedical Image Processing and Three-Dimensional Microscopy
Raj S. Acharya; Carol J. Cogswell; Dmitry B. Goldgof, Editor(s)

© SPIE. Terms of Use
Back to Top