Title :
A technology for retrieval of volume images from biomedical databases
Author :
Sarioz, Deniz ; Herman, Gabor T. ; Kong, T. Yung
Author_Institution :
City Univ. of New York, NY, USA
Abstract :
To facilitate the retrieval of volume images from a biomedical database (e.g., images of proteins from a macromolecular database), it is necessary to obtain concise descriptors of the images. Relatively recently developed successful algorithms for high-resolution three-dimensional reconstruction of biomedical structures from projections produce volume images represented as linear combinations of spherically symmetric basis functions (called blobs). In this paper, we discuss our work toward obtaining topological and geometric descriptors in the form of Betti triple sequences from such a linear combination of blobs, and give some preliminary experimental results.
Keywords :
image reconstruction; image resolution; image retrieval; image sequences; medical image processing; Betti triple sequences; biomedical databases; geometric descriptors; high-resolution three-dimensional of biomedical structure reconstruction; macromolecular database; protein images; spherically symmetric basis functions; topological descriptors; volume image retrieval; Computer science; Image databases; Image reconstruction; Image retrieval; Information retrieval; Linear approximation; Proteins; Shape; Spatial databases; Subspace constraints;
Conference_Titel :
Bioengineering Conference, 2004. Proceedings of the IEEE 30th Annual Northeast
Print_ISBN :
0-7803-8285-4
DOI :
10.1109/NEBC.2004.1299996