CANDID: Comparison algorithm for navigating digital image databases
Conference
·
OSTI ID:10139339
In this paper, we propose a method for calculating the similarity between two digital images. A global signature describing the texture, shape, or color content is first computed for every image stored in a database, and a normalized distance between probability density functions of feature vectors is used to match signatures. This method can be used to retrieve images from a database that are similar to an example target image. This algorithm is applied to the problem of search and retrieval for database containing pulmonary CT imagery, and experimental results are provided.
- Research Organization:
- Los Alamos National Lab., NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 10139339
- Report Number(s):
- LA-UR--94-721; CONF-940987--1; ON: DE94009307
- Country of Publication:
- United States
- Language:
- English
Similar Records
Experience with CANDID: Comparison algorithm for navigating digital image databases
Query by image example: The CANDID approach
Benchmarking, Research, Development, and Support for ORNL Automated Image and Signature Retrieval (AIR/ASR) Technologies
Conference
·
Sat Oct 01 04:00:00 UTC 1994
·
OSTI ID:10187616
Query by image example: The CANDID approach
Conference
·
Wed Feb 01 04:00:00 UTC 1995
·
OSTI ID:28339
Benchmarking, Research, Development, and Support for ORNL Automated Image and Signature Retrieval (AIR/ASR) Technologies
Technical Report
·
Tue Jun 01 04:00:00 UTC 2004
·
OSTI ID:940300