BulDML at Institute of Mathematics and Informatics >
Proceedings >
DiPP >
DiPP 2014 >

Please use this identifier to cite or link to this item:

Title: Aggregating Local Descriptors for Epigraphs Recognition
Authors: Amato, Giuseppe
Falchi, Fabrizio
Rabitti, Fausto
Vadicamo, Lucia
Keywords: Epigraphs Recognition
Object Recognition
Content-Base Image Retrieval
Issue Date: 2014
Publisher: Institute of Mathematics and Informatics Bulgarian Academy of Sciences
Citation: Digital Presentation and Preservation of Cultural and Scientific Heritage, Vol. 4, No 1, (2014), 49p-58p
Abstract: In this paper, we consider the task of recognizing epigraphs in images such as photos taken using mobile devices. Given a set of 17,155 photos related to 14,560 epigraphs, we used a k-NearestNeighbor approach in order to perform the recognition. The contribution of this work is in evaluating state-of-the-art visual object recognition techniques in this specific context. The experimental results conducted show that Vector of Locally Aggregated Descriptors obtained aggregating SIFT descriptors is the best choice for this task.
ISSN: 1314-4006
Appears in Collections:DiPP 2014

Files in This Item:

File Description SizeFormat
049-058-iDiPP2014-17-G.Amato-et-al-final.pdf622.09 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License