ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Stochastic-Wavelet Analysis of Heterogeneous Biological Resources in Three-Dimensions

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  033094,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.15006) @2003
Authors:   Prabhakar R., Hubert J. Montas, Adel Shirmohammadi
Keywords:   3D Haar wavelets, multi-resolution analysis, octrees, hierarchical data structures, image processing, texture segmentation, Visible Human Project

A three-dimensional stochastic-wavelet image analysis procedure is presented and applied to the head section of the female Visible Human Project Data Set. The technique is successful at identifying Representative Elementary Volume support scales and determining the corresponding textural signatures. Classification results for Bone and Skin with Fat are very good, and generally better than those of the Brain class because of its similarity to muscle tissue (in CT scans). The stochastic-wavelet strategy is a promising tool for classifying heterogeneous 3-D data and coupling the results with continuum mechanics models for the analysis of biological systems.

(Download PDF)    (Export to EndNotes)