Scalable similar image search by joint indices
Open Access
- 29 October 2012
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1325-1326
Abstract
Text-based image search is able to return desired images for simple queries, but has limited capabilities in finding images with additional visual requirements. As a result, an image is usually used to help describe the appearance requirements. In this demonstration, we show a similar image search system that can support the joint textual and visual query. We present an efficient and effective indexing algorithm, neighborhood graph index, which is suitable for millions of images, and use it to organize joint inverted indices to search over billions of images.Keywords
This publication has 6 references indexed in Scilit:
- Similar image search with a tiny bag-of-delegates representation2012
- Query-driven iterated neighborhood graph search for large scale indexing2012
- Complementary hashing for approximate nearest neighbor search2011
- Interactive Image Search by Color MapACM Transactions on Intelligent Systems and Technology, 2011
- Image search by concept map2010
- Optimizing kd-trees for scalable visual descriptor indexing2010