Large scale near-duplicate image retrieval using Triples of Adjacent Ranked Features (TARF) with embedded geometric information

TL;DR

This paper introduces a new feature representation called TARF, combining three local descriptors with embedded geometric info, to improve large-scale near-duplicate image retrieval by reducing false matches and candidate list size.

Contribution

The paper proposes TARF, a novel feature combining three local descriptors with geometric info, enhancing discriminability and efficiency in large-scale image retrieval.

Findings

TARF significantly reduces false matches.

TARF shortens candidate lists after initial search.

TARF improves retrieval accuracy in large-scale datasets.

Abstract

Most approaches to large-scale image retrieval are based on the construction of the inverted index of local image descriptors or visual words. A search in such an index usually results in a large number of candidates. This list of candidates is then re-ranked with the help of a geometric verification, using a RANSAC algorithm, for example. In this paper we propose a feature representation, which is built as a combination of three local descriptors. It allows one to significantly decrease the number of false matches and to shorten the list of candidates after the initial search in the inverted index. This combination of local descriptors is both reproducible and highly discriminative, and thus can be efficiently used for large-scale near-duplicate image retrieval.