Large scale near-duplicate image retrieval using Triples of Adjacent Ranked Features (TARF) with embedded geometric information
This work addresses efficiency and accuracy issues in image retrieval systems, though it appears incremental as it builds on existing inverted index and geometric verification methods.
The paper tackled the problem of reducing false matches in large-scale near-duplicate image retrieval by proposing a feature representation combining three local descriptors, which significantly decreased false matches and shortened candidate lists after initial search.
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.