Ricardo Toledo

Ricardo Toledo

Auto-generated profile, based on publicly available information

Ricardo Toledo

Computer Vision Center, Edifici O, Campus UAB, Bellaterra 08193, Barcelona, Spain

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2015 in International Journal on Document Analysis and Recognition (IJDAR)
Verified
Journal Article
Closed access
PDF file
DADavid Aldavert
David Aldavert
MRMarçal Rusiñol
Marçal Rusiñol
RTRicardo Toledo
Ricardo Toledo
JLJosep Llados-Masllorens
Josep Llados-Masllorens

15 April 2017 in Sensors
Verified
Journal Article
Open access
PDF file
Cristhian AguileraCristhian Aguilera
Cristhian Aguilera
ASAngel D. Sappa
Angel D. Sappa
CACristhian Aguilera
Cristhian Aguilera
RTRicardo Toledo
Ricardo Toledo
This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

1 June 2016 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
BSB.G. Sileshi
B.G. Sileshi
JOJoan Oliver
Joan Oliver
RTR. Toledo
R. Toledo
José GonçalvesJosé Gonçalves
José Gonçalves
Paulo José Cerqueira Gomes CostaPaulo José Cerqueira Gomes Costa
Paulo José Cerqueira Gomes Costa

1 November 2016 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
ASAngel Sappa
Angel Sappa
Cristhian AguileraCristhian Aguilera
Cristhian Aguilera
JCJuan Carvajal
Juan Carvajal
MOMiguel Oliveira
Miguel Oliveira
DRDennis Romero
Dennis Romero
RTRicardo Toledo
Ricardo Toledo

13 March 2017 in Preprints.org
Verified
Preprint
Open access
PDF file
Cristhian AguileraCristhian Aguilera
Cristhian Aguilera
ASAngel D. Sappa
Angel D. Sappa
CACristhian Aguilera
Cristhian Aguilera
RTRicardo Toledo
Ricardo Toledo
This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where for each matching pair there are always two possible non-matching patches; one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

11 January 2013
Verified
Book Chapter
Closed access
PDF file
MPMonica Piñol
Monica Piñol
ASAngel Sappa
Angel Sappa
RTRicardo Toledo
Ricardo Toledo