Local versus global features for content-based image retrieval
- 27 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
It is now recognized in many domains that contentbasedimage retrieval (CBIR) from a database of imagescannot be carried out by using completely automatedapproaches. One such domain is medical radiologyfor which the clinically useful information inan image typically consists of gray level variationsin highly localized regions of the image. Currently,it is not possible to extract these regions by automaticimage segmentation techniques. To address thisproblem, we have implemented a...Keywords
This publication has 6 references indexed in Scilit:
- Image matching by means of intensity and texture matching in the Fourier domainPublished by SPIE-Intl Soc Optical Eng ,1996
- Query by image and video content: the QBIC systemComputer, 1995
- Interactive Learning of a Multiple-Attribute Hash Table Classifier for Fast Object RecognitionComputer Vision and Image Understanding, 1995
- Query by image example: the comparison algorithm for navigating digital image databases (CANDID) approachPublished by SPIE-Intl Soc Optical Eng ,1995
- Photobook: tools for content-based manipulation of image databasesPublished by SPIE-Intl Soc Optical Eng ,1994
- Content-based event selection from satellite images of the auroraPublished by SPIE-Intl Soc Optical Eng ,1993