no code implementations • 12 Apr 2024 • Kallil M. Zielinski, Leonardo Scabini, Lucas C. Ribas, Núbia R. da Silva, Hans Beeckman, Jan Verwaeren, Odemir M. Bruno, Bernard De Baets
In recent years, we have seen many advancements in wood species identification.
1 code implementation • 8 Mar 2023 • Leonardo Scabini, Kallil M. Zielinski, Lucas C. Ribas, Wesley N. Gonçalves, Bernard De Baets, Odemir M. Bruno
Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied.
Ranked #1 on Image Classification on KTH-TIPS2 (using extra training data)
no code implementations • 20 Jan 2023 • Mariane B. Neiva, Odemir M. Bruno
The adjacency matrix, which provides a one-to-one representation of a complex network, can also yield several metrics of the graph.
no code implementations • 18 Nov 2022 • Kallil M. C. Zielinski, Lucas C. Ribas, Jeaneth Machicao, Odemir M. Bruno
Network modeling has proven to be an efficient tool for many interdisciplinary areas, including social, biological, transport, and many other real world complex systems.
1 code implementation • 17 Jul 2022 • Leonardo Scabini, Bernard De Baets, Odemir M. Bruno
In this sense, PA rewiring only reorganizes connections, while preserving the magnitude and distribution of the weights.
1 code implementation • 29 Jul 2021 • Leonardo F. S. Scabini, Odemir M. Bruno
Results show that these measures are highly related to the network classification performance.
no code implementations • 10 Jul 2020 • Lucas C. Ribas, Leonardo F. S. Scabini, Jarbas Joaci de Mesquita Sá Junior, Odemir M. Bruno
Experimental results show a high classification performance of the proposed method when compared to other methods, indicating that our approach can be used in many image analysis problems.
1 code implementation • 13 Sep 2019 • Leonardo F. S. Scabini, Lucas C. Ribas, Odemir M. Bruno
Texture is one of the most-studied visual attribute for image characterization since the 1960s.
no code implementations • 27 Jun 2018 • Lucas C. Ribas, Wesley N. Goncalves, Odemir M. Bruno
In this paper, a new method for dynamic texture characterization based on diffusion in directed networks is proposed.
no code implementations • 24 Jun 2018 • Lucas C. Ribas, Jarbas J. M. Sa Junior, Leonardo F. S. Scabini, Odemir M. Bruno
This paper presents a high discriminative texture analysis method based on the fusion of complex networks and randomized neural networks.
no code implementations • 2 Apr 2018 • Leonardo F. S. Scabini, Rayner H M Condori, Wesley N Gonçalves, Odemir M. Bruno
A new method based on complex networks is proposed for color-texture analysis.
no code implementations • 14 Nov 2017 • Gisele H. B. Miranda, Jeaneth Machicao, Odemir M. Bruno
The proposed approach accounts for a more robust set of structural measurements, that improved the discriminant power of the shape descriptors.
no code implementations • 13 Mar 2017 • Mariane B. Neiva, Patrick Guidotti, Odemir M. Bruno
The main purpose of this paper is to propose a new preprocessing step in order to improve local feature descriptors and texture classification.
no code implementations • 26 Dec 2016 • Mayra Z. Rodriguez, Cesar H. Comin, Dalcimar Casanova, Odemir M. Bruno, Diego R. Amancio, Francisco A. Rodrigues, Luciano da F. Costa
We also found that the default configuration of the adopted implementations was not accurate.
no code implementations • 19 Dec 2016 • João B. Florindo, Odemir M. Bruno
This work presents a novel descriptor for texture images based on fractal geometry and its application to image analysis.
no code implementations • 8 Dec 2016 • João B. Florindo, Odemir M. Bruno
This work presents a new procedure to extract features of grey-level texture images based on the discrete Schroedinger transform.
no code implementations • 20 Oct 2016 • Jeaneth Machicao, Edilson A. Corrêa Jr., Gisele H. B. Miranda, Diego R. Amancio, Odemir M. Bruno
Remarkably, we have found a dependence of pre-processing steps (such as the lemmatization) on the obtained results, a feature that has mostly been disregarded in related works.
no code implementations • 26 Dec 2014 • João B. Florindo, Odemir M. Bruno
The method is based on the Bouligand-Minkowski descriptors.
no code implementations • 25 Dec 2014 • André R. Backes, Odemir M. Bruno
The proposed approach expands the idea of the Mass-radius fractal dimension, a method originally developed for shape analysis, to a set of coordinates in 3D-space that represents the texture under analysis in a signature able to characterize efficiently different texture classes in terms of complexity.
no code implementations • 25 Dec 2014 • Álvaro Gomez Z., João B. Florindo, Odemir M. Bruno
Texture analysis and classification remain as one of the biggest challenges for the field of computer vision and pattern recognition.
no code implementations • 11 Nov 2013 • Lucas Assirati, Núbia R. da Silva, Lilian Berton, Alneu de A. Lopes, Odemir M. Bruno
In image processing, edge detection is a valuable tool to perform the extraction of features from an image.
no code implementations • 10 May 2013 • Ricardo Fabbri, Ivan N. Bastos, Francisco D. Moura Neto, Francisco J. P. Lopes, Wesley N. Goncalves, Odemir M. Bruno
An excellent classification rate was obtained, at a success rate of 90%, 80%, and 83% for low (cathodic), high (anodic), and both potential ranges, respectively, using only 2% of the original profile data.