PBIR - perception-based image retrieval
- 1 May 2001
- journal article
- conference paper
- Published by Association for Computing Machinery (ACM) in ACM SIGMOD Record
- Vol. 30 (2) , 613
- https://doi.org/10.1145/376284.375776
Abstract
We demonstrate a system that we have built on our proposed perception-based image retrieval (PBIR) paradigm. This PBIR system achieves accurate similarity measurements by rooting image characterization in human perception and by learning user's query concept through an intelligent sampling process. We show that our system can usually grasp a user's query concept with a small number of labeled instances.Keywords
This publication has 1 reference indexed in Scilit:
- Clustering for approximate similarity search in high-dimensional spacesIEEE Transactions on Knowledge and Data Engineering, 2002