Advanced search
Start date
Betweenand

High-dimensional multimedia indexing: application to image and video retrieval

Grant number: 09/05951-8
Support type:Scholarships in Brazil - Post-Doctorate
Effective date (Start): August 01, 2009
Effective date (End): July 31, 2011
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computer Systems
Principal researcher:Ricardo da Silva Torres
Grantee:Eduardo Alves Do Valle Junior
Home Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Multimedia information retrieval is a thriving research subject, both in Brazilian and International contexts. In particular, the so called "content based" systems have drawn much attention, as they promise to offer classification and retrieval of documents without the need of the expensive and troublesome manual description. On the other hand, those systems face technical challenges, which start from the indexing of the feature vectors used to bridge the gap between the low-level information coding and the high-level user queries. This project aims at the creation of innovative, efficient and effective solutions to index high-dimensional feature vectors, in large-scale databases. Other objective is to advance the understanding of those methods, both empirically and theoretically. As an applicative context, we are interested in the problem of document identification on image and video databases, a problem which concerns both creators and custodians of visual documents. We propose to perform our research in cooperation with the University of Minas Gerais (UFMG) and the French universities of Cergy-Pontoise (UCP) and of Paris 6 (UPMC Paris 6), institutions where both the candidate and the supervisor have already connections. (AU)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY; TORRES, RICARDO DA S. A scalable re-ranking method for content-based image retrieval. INFORMATION SCIENCES, v. 265, p. 91-104, MAY 1 2014. Web of Science Citations: 34.
PENATTI, OTAVIO A. B.; SILVA, FERNANDA B.; VALLE, EDUARDO; GOUET-BRUNET, VALERIE; TORRES, RICARDO DA S. Visual word spatial arrangement for image retrieval and classification. PATTERN RECOGNITION, v. 47, n. 2, p. 705-720, FEB 2014. Web of Science Citations: 50.
PENATTI, OTAVIO A. B.; VALLE, EDUARDO; TORRES, RICARDO DA S. Comparative study of global color and texture descriptors for web image retrieval. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v. 23, n. 2, p. 359-380, FEB 2012. Web of Science Citations: 94.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.

Filed patent(s) as a result of this research project

MÉTODO DE INDEXAÇÃO PARA DADOS DE ALTA DIMENSIONALIDADE EM GRANDES BASES DE DADOS USANDO UMA CURVA DE PEANO (CURVA PREENCHEDORA DO ESPAÇO) E MÚLTIPLOS REPRESENTANTES PARA OS DADOS PI1005767-6 - Universidade Estadual de Campinas (UNICAMP) . Ricardo da Silva Torres; Eduardo Alves do Valle Junior; Fernando Cesar Akune - December 2010, 20