Similarity measures for image databases

Ramesh Jain, S. N.Jayaram Murthy, Peter L.J. Chen, Shankar Chatterjee

Research output: Contribution to conferencePaperpeer-review

33 Scopus citations


Similarity images is used for storage and retrieval in image databases. In this article, several experiments designed to compare various similarity measures for application to image databases are outlined. As a first step for comparison, the similarity matrices for each of the similarity measure is computed over a set of selected textures and are presented as visual images. Comparative analysis of these images show the relative characteristics of each of these measures. Experiments which are being conducted to study the sensitivity of these matrices to small changes in images are also described. Results obtained from these experiments could offer assistance in selecting the appropriate measure for applications to image databases.

Original languageEnglish
Number of pages8
StatePublished - 1995
EventProceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5) - Yokohama, Jpn
Duration: Mar 20 1995Mar 24 1995


ConferenceProceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5)
CityYokohama, Jpn


Dive into the research topics of 'Similarity measures for image databases'. Together they form a unique fingerprint.

Cite this