Leonardo Scabini

Dr. Leonardo Scabini

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
17 February 2023 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
LSLeonardo Scabini
Leonardo Scabini
OBOdemir M. Bruno
Odemir M. Bruno

1 January 2021 in Talanta
Verified
Journal Article
Closed access
VRValquiria C. Rodrigues
Valquiria C. Rodrigues
JSJuliana C. Soares
Juliana C. Soares
Andrey Coatrini SoaresAndrey Coatrini Soares
Andrey Coatrini Soares
DBDaniel C. Braz
Daniel C. Braz
MMMatias Eliseo Melendez
Matias Eliseo Melendez
OOOsvaldo Oliveira
Osvaldo Oliveira

24 June 2021 in Materials Chemistry Frontiers
Verified
Journal Article
Closed access
PDF file
JSJuliana Coatrini Soares
Juliana Coatrini Soares
Andrey Coatrini SoaresAndrey Coatrini Soares
Andrey Coatrini Soares
VRValquiria Cruz Rodrigues
Valquiria Cruz Rodrigues
POPedro Ramon Almeida Oiticica
Pedro Ramon Almeida Oiticica
Paulo A. Raymundo-PereiraPaulo A. Raymundo-Pereira
Paulo A. Raymundo-Pereira
OOOsvaldo Oliveira
Osvaldo Oliveira
First genosensor for SARS-CoV-2 where multimodal detection principles can be employed, including image analysis based on machine learning.

3 July 2023 in Pattern Recognition
Verified
Journal Article
Closed access
LSLeonardo Scabini
Leonardo Scabini
KZKallil M. Zielinski
Kallil M. Zielinski
LRLucas C. Ribas
Lucas C. Ribas
WGWesley N. Gonçalves
Wesley N. Gonçalves
BBBernard De Baets
Bernard De Baets
OBOdemir M. Bruno
Odemir M. Bruno

5 September 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
LSLeonardo Scabini
Leonardo Scabini
ASAndre Sacilotti
Andre Sacilotti
KZKallil M. Zielinski
Kallil M. Zielinski
LRLucas C. Ribas
Lucas C. Ribas
Bernard De BaetsBernard De Baets
Bernard De Baets
OBOdemir M. Bruno
Odemir M. Bruno
Texture, a significant visual attribute in images, plays an important role in many pattern recognition tasks. While Convolutional Neural Networks (CNNs) have been among the most effective methods for texture analysis, alternative architectures such as Vision Transformers (ViTs) have recently demonstrated superior performance on a range of visual recognition problems. However, the suitability of ViTs for texture recognition remains underexplored. In this work, we investigate the capabilities and limitations of ViTs for texture recognition by analyzing 25 different ViT variants as feature extractors and comparing them to CNN-based and hand-engineered approaches. Our evaluation encompasses both accuracy and efficiency, aiming to assess the trade-offs involved in applying ViTs to texture analysis. Our results indicate that ViTs generally outperform CNN-based and hand-engineered models, particularly when using strong pre-training and in-the-wild texture datasets. Notably, BeiTv2-B/16 achieves the highest average accuracy (85.7%), followed by ViT-B/16-DINO (84.1%) and Swin-B (80.8%), outperforming the ResNet50 baseline (75.5%) and the hand-engineered baseline (73.4%). As a lightweight alternative, EfficientFormer-L3 attains a competitive average accuracy of 78.9%. In terms of efficiency, although ViT-B and BeiT(v2) have a higher number of GFLOPs and parameters, they achieve significantly faster feature extraction on GPUs compared to ResNet50. These findings highlight the potential of ViTs as a powerful tool for texture analysis while also pointing to areas for future exploration, such as efficiency improvements and domain-specific adaptations.

1 July 2020 in Pattern Recognition
Verified
Journal Article
Closed access
LRLucas C. Ribas
Lucas C. Ribas
JJJarbas Joaci de Mesquita Sá Junior
Jarbas Joaci de Mesquita Sá Junior
LSLeonardo Scabini
Leonardo Scabini
OBOdemir M. Bruno
Odemir M. Bruno