Medical image indexing and compression based on vector quantization: image retrieval efficiency evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2001

Medical image indexing and compression based on vector quantization: image retrieval efficiency evaluation

Résumé

Addresses the problem of efficient image retrieval from a compressed image database, using information derived from the compression process. Images in the database are compressed applying two approaches: vector quantization (VQ) and quadtree image decomposition. Both are based on Konohen's self-organizing feature maps (SOFM) for creating vector quantization codebooks. However, while VQ uses one codebook of one resolution to compress the images, Quadtree decomposition uses simultaneously 4 codebooks of four different resolutions. Image indexing is implemented by generating a feature vector (FV) for each compressed image. Accordingly, images are retrieved by means of FVs similarity evaluation between the query image and the images in the database, depending on a distance measure. Three distance measures have been analyzed to assess FV index similarity: Euclidean, intersection and correlation distances. Distance measures efficiency retrieval is evaluated for different VQ resolutions and different quadtree image descriptors. Experimental results using real data, esophageal ultrasound and eye angiography images, are presented.
Fichier non déposé

Dates et versions

hal-02134279 , version 1 (20-05-2019)

Identifiants

Citer

John Richard Ordonez, Guy Cazuguel, John Puentes, Basel Solaiman, Christian Roux, et al.. Medical image indexing and compression based on vector quantization: image retrieval efficiency evaluation. 23rd Annual International Conference of the IEEE EMBS, Oct 2001, Istanbul, Turkey. ⟨10.1109/IEMBS.2001.1017277⟩. ⟨hal-02134279⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More