A Low Memory Cost Fast Retrieval Method Based on Bucket Map Chain

Abstract

To reduce the high memory cost of fast retireval method, we present a fast retrieval method based on bucket map chain on the basis of Exact Euclidean Locality Sensitive Hashing (E2LSH). The bucket map chain contains all the points projected from feature space in multiple buckets, which store the nearby points. When conducting query, it searches the chain by the bucket index of query point and locates the position of related buckets, then reads the related points in related buckets and measurs the similarity of these points with query point. The experiments show that this method can efficiently decrease the memory cost of retrieval. It is very important for increasing the feasibility of large scale information retrieval especially image retrieval.