Tod Courtney and Narendra Ahuja

This paper presents a new method for multiscale segmentation of volume images. The segmentation is achieved using a recent nonlinear transform which leads to well-characterized regions at different spatial and intensity scales. The detected three-dimensional regions are closed and are homogeneous  relative to their surround. A pyramid is generated containing the region  information extracted across a range of homogeneity scales. The pyramid represents the multiscale volumetric structure. Experimental results are given for magnetic resonance data as well as video sequences. (10 References).

Keywords: volume image segmentation; multiscale transform; multiscale segmentation; nonlinear transform; well-characterized regions; spatial scales; intensity scales; three-dimensional region detection; pyramid; homogeneity scales; multiscale volumetric structure; magnetic resonance data; video sequences.

Full Text:  PDF