Evaluating Hybrid Approximate Nearest Neighbor Indexing and Search (HANNIS) for High-dimensional Image Feature Search

M. M. Mahabubur Rahman, Jelena Tesic

Abstract: In this paper, we evaluate the performance of a novel method for efficient and effective retrieval of similar high-dimensional image features. The proposed solution —- hybrid approximate nearest neighbor indexing and search (HANNIS) —-retrieves truly similar items in the database, even if the retrieval set is large. This approach enables us to load items that are truly close to the incoming query at retrieval time. HANNIS outperforms all state-of-the-art methods in terms of recall, precision, and F1 score at depths of up to 100 and offers the fastest index loading and consistent retrieval performance.