Fábio Favarim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fábio Favarim has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Dalcimar Casanova
UTFPR
3 shared publications - Luiz Fernando Puttow Southier
UTFPR
3 shared publications - Elioenai Markson Ferreira Diniz
UTFPR
2 shared publications - Jefferson Tales Oliva
UTFPR
2 shared publications - João Victor Costa Mazzochin
Federal University of Technology - Parana
2 shared publications - Marcelo Teixeira
UTFPR
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 157120-157137
A Novel Graph-Based Approach for Infant Fingerprint Recognition
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 157120-157137
Open AccessA Novel Graph-Based Approach for Infant Fingerprint Recognition
- Open Access
- 20 February 2025
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 32 (1) , 188-195
Construction of Rolled Digital for Newborns Using Image Registration
This work aimed to reconstruct rolled fingerprint images from multiple flat fingerprints using image registration and composition techniques. The methodology involved selecting high-quality frames through a quality network, the application of preprocessing with remapping, cropping the area of interest, and adjusting colors. In addition to image registration steps, like key point identification, feature matching, and image distortion. Results indicated that while classical image registration had limitations, the composition technique significantly increased the number of features extracted, enhancing fingerprint identification. It was demonstrated that the composition method effectively captures important fingerprint details, offering a potential improvement in newborn biometric identification.
- 20 February 2025
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 32 (1) , 188-195
Open AccessConstruction of Rolled Digital for Newborns Using Image Registration
This work aimed to reconstruct rolled fingerprint images from multiple flat fingerprints using image registration and composition techniques. The methodology involved selecting high-quality frames through a quality network, the application of preprocessing with remapping, cropping the area of interest, and adjusting colors. In addition to image registration steps, like key point identification, feature matching, and image distortion. Results indicated that while classical image registration had limitations, the composition technique significantly increased the number of features extracted, enhancing fingerprint identification. It was demonstrated that the composition method effectively captures important fingerprint details, offering a potential improvement in newborn biometric identification.
- Open Access
- 6 November 2024
- Published by Sociedade Brasileira de Computação
- p. 1-7
A Mathematical Toolkit to improve the Similarity Analysis for Fingerprint Images
While fingerprint biometrics are a mature technology, preprocessing steps such as image alignment and minutiae filtering still significantly impact their performance. To address these challenges, this paper introduces a comprehensive package of analytical methods designed to enhance fingerprint image similarity analysis. Initially, we present an alignment method based on partitioning and statistical image analysis, which does not rely on specific information, such as the location of singular points. Next, a minutiae filtering method is developed, focusing on detecting and removing edge minutiae, which tend to provide non-discriminative information. To establish an agnostic distance metric approach, we conducted extensive experiments on public fingerprint datasets, incorporating an ablation study to evaluate the impact of alignment and filtering methods. Our results demonstrate that the proposed combination of rotation and filtering significantly outperforms untreated images, providing an efficient and competitive solution that improves and contributes to the biometric analysis field.
- 6 November 2024
- Published by Sociedade Brasileira de Computação
- p. 1-7
Open AccessA Mathematical Toolkit to improve the Similarity Analysis for Fingerprint Images
While fingerprint biometrics are a mature technology, preprocessing steps such as image alignment and minutiae filtering still significantly impact their performance. To address these challenges, this paper introduces a comprehensive package of analytical methods designed to enhance fingerprint image similarity analysis. Initially, we present an alignment method based on partitioning and statistical image analysis, which does not rely on specific information, such as the location of singular points. Next, a minutiae filtering method is developed, focusing on detecting and removing edge minutiae, which tend to provide non-discriminative information. To establish an agnostic distance metric approach, we conducted extensive experiments on public fingerprint datasets, incorporating an ablation study to evaluate the impact of alignment and filtering methods. Our results demonstrate that the proposed combination of rotation and filtering significantly outperforms untreated images, providing an efficient and competitive solution that improves and contributes to the biometric analysis field.
- Open Access
- 2 January 2024
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 17 (1) , 6310-6325
Análise da funcionalidade de sensores de distância, operando em superfície formada por grãos de soja e milho em movimento
Com a finalidade de verificar a possibilidade do uso de sensores de distância em fluxos operacionais de movimentação de grãos, foi montada uma bancada de ensaios que contou com uma correia transportadora que operou com dois produtos agrícolas, para o caso, soja e milho. Os produtos em transporte passavam por uma linha de sensores acima de sua seção transversal, que determinava as distâncias verticais até o produto. A implementação de um sistema microcontrolador de coleta de dados em tempo real, foi utilizada para captura das leituras dos sensores e conseguente cálculo do volume total transportado, que; comparado ao volume real, permitiu a determinação do erro de medição. Os dados obtidos demostraram proximidade com os valores reais, com um erro relativo absoluto máximo, menor que 10%. Também foi observado um comportamento diferente do erro, quando do transporte de soja e milho. Além disso foi possível identificar limitantes, fatores influenciadores que exigem maiores estudos, assim como, possibilidades melhorias para minimização dos erros.
- 2 January 2024
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 17 (1) , 6310-6325
Open AccessAnálise da funcionalidade de sensores de distância, operando em superfície formada por grãos de soja e milho em movimento
Com a finalidade de verificar a possibilidade do uso de sensores de distância em fluxos operacionais de movimentação de grãos, foi montada uma bancada de ensaios que contou com uma correia transportadora que operou com dois produtos agrícolas, para o caso, soja e milho. Os produtos em transporte passavam por uma linha de sensores acima de sua seção transversal, que determinava as distâncias verticais até o produto. A implementação de um sistema microcontrolador de coleta de dados em tempo real, foi utilizada para captura das leituras dos sensores e conseguente cálculo do volume total transportado, que; comparado ao volume real, permitiu a determinação do erro de medição. Os dados obtidos demostraram proximidade com os valores reais, com um erro relativo absoluto máximo, menor que 10%. Também foi observado um comportamento diferente do erro, quando do transporte de soja e milho. Além disso foi possível identificar limitantes, fatores influenciadores que exigem maiores estudos, assim como, possibilidades melhorias para minimização dos erros.
- 23 March 2021
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (3) , 468-479
EDT Method for Multiple Labelled Objects Subject to Tied Distances
- 23 March 2021
- Published by Springer Nature in International Journal of Automation and Computing
- Vol. 18 (3) , 468-479
EDT Method for Multiple Labelled Objects Subject to Tied Distances
- Open Access
- 6 March 2013
- Published by Universidade Tecnologica Federal do Parana (UTFPR) in Revista Eletrônica Científica Inovação e Tecnologia
- Vol. 4 (7) , 35-38
JGridTS: um framework Java para a execução de tarefas em ambientes de grades computacionais baseadas em espaços de Tuplas
JGridTS: um framework Java para a execução de tarefas em ambientes de grades computacionais baseadas em espaços de Tuplas
- 6 March 2013
- Published by Universidade Tecnologica Federal do Parana (UTFPR) in Revista Eletrônica Científica Inovação e Tecnologia
- Vol. 4 (7) , 35-38
Open AccessJGridTS: um framework Java para a execução de tarefas em ambientes de grades computacionais baseadas em espaços de Tuplas
JGridTS: um framework Java para a execução de tarefas em ambientes de grades computacionais baseadas em espaços de Tuplas
- 13 January 2012
- Published by Springer Nature in Journal of Internet Services and Applications
- Vol. 3 (2) , 159-172
Towards an opportunistic grid scheduling infrastructure based on tuple spaces
- 13 January 2012
- Published by Springer Nature in Journal of Internet Services and Applications
- Vol. 3 (2) , 159-172
Towards an opportunistic grid scheduling infrastructure based on tuple spaces