CHEF: convex hull of elliptic features for 3D blob detection

Author

Yang, Qing ; Parvin, Bahram

Author_Institution

Comput. Sci., Lawrence Berkeley Nat. Lab., CA, USA

Volume

2

fYear

2002

fDate

2002

Firstpage

282

Abstract

We present an efficient protocol for robust detection of 3D blobs from volumetric datasets. The approach has three steps. The first step of the process detects elliptic features by classifying the Hessian of the scale space representation of the volume data. These features are then grouped into 3D connected components, which are subsequently partitioned by computing a convex hull of each connected component. The proposed framework was applied to a database of multicellular systems for detailed quantitative analysis.

Keywords

Hessian matrices; biology computing; feature extraction; image segmentation; object recognition; protocols; stereo image processing; 3D blobs detection; CHEF algorithm; Hessian matrices; cell cultured colony; cell segmentation; convex hull; elliptic features; feature extraction; multicellular systems; protocol; scale space representation; volumetric datasets; Biomedical imaging; Cells (biology); Computed tomography; Image analysis; Laboratories; Large-scale systems; Magnetic resonance imaging; Neoplasms; Protocols; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2002. Proceedings. 16th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-1695-X

Type

conf

DOI

10.1109/ICPR.2002.1048295

Filename

1048295