Local grayvalue invariants for image retrieval
- 1 May 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 19 (5) , 530-535
- https://doi.org/10.1109/34.589215
Abstract
This paper addresses the problem of retrieving images from large image databases. The method is based on local grayvalue invariants which are computed at automatically detected interest points. A voting algorithm and semilocal constraints make retrieval possible. Indexing allows for efficient retrieval from a database of more than 1,000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective deformations.Keywords
This publication has 30 references indexed in Scilit:
- The illumination-invariant recognition of 3D objects using local color invariantsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- An active vision architecture based on iconic representationsArtificial Intelligence, 1995
- Color constant color indexingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Higher order differential structure of imagesImage and Vision Computing, 1994
- General intensity transformations and differential invariantsJournal of Mathematical Imaging and Vision, 1994
- Multidimensional indexing for recognizing visual shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Computing reflectance ratios from an imagePattern Recognition, 1993
- Distortion invariant object recognition in the dynamic link architectureIEEE Transactions on Computers, 1993
- Model-based recognition in robot visionACM Computing Surveys, 1986
- Feature space transforms for curve detectionPattern Recognition, 1978