Advanced search
Start date
Betweenand

Complex networks and content-based image retrieval supported by selective visual attention features

Grant number: 20/10049-0
Support type:Scholarships in Brazil - Post-Doctorate
Effective date (Start): September 01, 2020
Effective date (End): August 31, 2023
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal researcher:Agma Juci Machado Traina
Grantee:Cláudio Douglas Gouveia Linhares
Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Associated research grant:16/17078-0 - Mining, indexing and visualizing Big Data in clinical decision support systems (MIVisBD), AP.TEM

Abstract

The goal of this project is to explore the use of selective visual attention models to identify the most important visual regions in an image and use this information to build feature extraction techniques that allow mitigating the semantic gap between human perception and computational description. These models can lead attention to specific places of interest in the image according to human perception and/or the application domain. The motivation is to enrich the construction of computer systems closer to the human interpretation, in order to improve the solution of difficult problems for many applications, such as object recognition through complex networks and content-based image retrieval. Thus, it complex networks will be used as a way of identifying the relationship between the images and their structure, in order to boost their usability from different metrics and pre-existing visualization techniques, paying attention to scalability issues. The final objective of this project is to develop a theoretical and practical tool that can characterize the visual content of the images in compact, scalable and discriminative data, seeking to obtain a content-based image retrieval system that has effective and efficient perceptual performance. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

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)
LINHARES, CLAUDIO D. G.; PONCIANO, JEAN R.; PAIVA, JOSE GUSTAVO S.; TRAVENCOLO, BRUNO A. N.; ROCHA, LUIS E. C.. A comparative analysis for visualizing the temporal evolution of contact networks: a user study. JOURNAL OF VISUALIZATION, v. 24, n. 5, p. 1011-1031, . (16/17078-0, 20/10049-0)
PONCIANO, JEAN R.; LINHARES, CLAUDIO D. G.; FARIA, ELAINE R.; TRAVENCOLO, BRUNO A. N.. An online and nonuniform timeslicing method for network visualisation & nbsp;. COMPUTERS & GRAPHICS-UK, v. 97, p. 170-182, . (20/10049-0)

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