Title :
Index trees for efficient deformable shape-based retrieval
Author :
Liu, Lifeng ; Sclaroff, Stan
Author_Institution :
Dept. of Comput. Sci., Boston Univ., MA, USA
Abstract :
An improved method for deformable shape-based image indexing and retrieval is described. A pre-computed index tree is used to improve the speed of our previously reported online model fitting method; simple shape features are used as keys in a pre-generated index tree of model instances. A coarse-to-fine indexing scheme is used at different levels of the tree to further improve speed. Experimental results show that the speedup is significant, while the accuracy of shape-based indexing is maintained. A method for shape population-based retrieval is also described. The method allows query formulation based on the population distributions of shapes in each image. Results of population-based queries for a database of blood cell micrographs are shown
Keywords :
blood; content-based retrieval; database indexing; deformation; medical image processing; medical information systems; query formulation; software performance evaluation; tree data structures; visual databases; accuracy; blood cell micrograph database; coarse-to-fine indexing scheme; computational speed; deformable shape-based image indexing; deformable shape-based image retrieval; index keys; model instances; online model fitting method; population-based queries; pre-computed index tree; query formulation; shape features; shape population distributions; shape population-based retrieval; shape-based indexing; speedup; Tree data structures;
Conference_Titel :
Content-based Access of Image and Video Libraries, 2000. Proceedings. IEEE Workshop on
Conference_Location :
Hilton Head Island, SC
Print_ISBN :
0-7695-0695-X
DOI :
10.1109/IVL.2000.853845
