Istituto di Scienza e Tecnologie dell'Informazione     
Amato G., Bolettieri P., Falchi F., Gennaro C., Vadicamo L. Using Apache Lucene to search vector of locally aggregated descriptors. In: VISAPP 2016 - 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Roma, Italy, 27-29 February 2016). Proceedings, vol. 4 pp. 383 - 392. Nadia Magnenat-Thalmann, Paul Richard, Lars Linsen, Alexandru Telea, Sebastiano Battiato, Francisco Imai, Josť Braz (eds.). SciTePress - Science and Technology Publications, 2016.
Surrogate Text Representation (STR) is a profitable solution to efficient similarity search on metric space using conventional text search engines, such as Apache Lucene. This technique is based on comparing the permutations of some reference objects in place of the original metric distance. However, the Achilles heel of STR approach is the need to reorder the result set of the search according to the metric distance. This forces to use a support database to store the original objects, which requires efficient random I/O on a fast secondary memory (such as flash-based storages). In this paper, we propose to extend the Surrogate Text Representation to specifically address a class of visual metric objects known as Vector of Locally Aggregated Descriptors (VLAD). This approach is based on representing the individual sub-vectors forming the VLAD vector with the STR, providing a finer representation of the vector and enabling us to get rid of the reordering phase. The experiments on a publ icly available dataset show that the extended STR outperforms the baseline STR achieving satisfactory performance near to the one obtained with the original VLAD vectors.
URL: http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=IX1NRClezpU=&t=1
DOI: 10.5220/0005722503830392
Subject Bag of Features
Bag of Words
Local Features
Compact Codes
Image Retrieval
Vector of Locally Aggregated Descriptors
H.3.3 INFORMATION STORAGE AND RETRIEVAL. Information Search and Retrieval

Icona documento 1) Download Document PDF

Icona documento Open access Icona documento Restricted Icona documento Private


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional