PZMLIR: Pseudo-Zernike Moments and LSH-based Image Retrieval in P2P datacenter

摘要

Since lots of data is stored in datacenters, it is difficult to locate data in such a distributed system. However, traditional search techniques cannot satisfy the requirements of content based image retrieval (CBIR). In this paper, we present the newel image retrieval framework which can efficiently support content similarity search and semantic search in the distributed environment. Its key idea is to integrate image feature vectors into distributed hash tables (DHTs) by exploiting the property of locality sensitive hashing (LSH). Thus, the similar images are more likely gathered into the same node without the knowledge of any global information. We show that our approach yields high recall rate, keeps load balance and only requires a few number of hops.