Leonardo de Melo João
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Leonardo de Melo João has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Alexandre Xavier Falcao
UNICAMP
5 shared publications - Isabela Borlido Barcelos
Pontifical Catholic University of Minas Gerais
3 shared publications - Silvio Jammil Ferzolli Guimaraes
Computer Science Department, Pontifcia Universidade Catlica de Minas Gerais, Belo Horizonte, Brazil
3 shared publications - Felipe Belém
University of Campinas
2 shared publications - Zenilton Kleber Goncalves Do Patrocinio
Pontifical Catholic University of Minas Gerais
2 shared publications Alexandre X. Falcao
Instituto de Computação Universidade Estadual de Campinas (UNICAMP) Rua Saturnino de Brito 2 13083-872 Campinas Sao Paulo Brazil
1 shared publication
Latest Publications
- 10 February 2026
- Published by Springer Nature
- p. 291-317
Automatically Improving Marked-Based Normalization for FLIM Networks
- 10 February 2026
- Published by Springer Nature
- p. 291-317
Automatically Improving Marked-Based Normalization for FLIM Networks
- Open Access
Flyweight FLIM Networks for Salient Object Detection in Biomedical Images
Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands but typically strive in complex and scarce labeled-data scenarios. Feature Learning from Image Markers (FLIM) learns an encoder's convolutional kernels among image patches extracted from discriminative regions marked on a few representative images, dismissing large annotated datasets, pretraining, and backpropagation. Such a methodology exploits information redundancy commonly found in biomedical image applications. This study presents methods to learn dilated-separable convolutional kernels and multi-dilation layers without backpropagation for FLIM networks. It also proposes a novel network simplification method to reduce kernel redundancy and encoder size. By combining a FLIM encoder with an adaptive decoder, a concept recently introduced to estimate a pointwise convolution per image, this study presents very efficient (named flyweight) SOD models for biomedical images. Experimental results in challenging datasets demonstrate superior efficiency and effectiveness to lightweight models. By requiring significantly fewer parameters and floating-point operations, the results show competitive effectiveness to heavyweight models. These advances highlight the potential of FLIM networks for data-limited and resource-constrained applications with information redundancy.
Open AccessFlyweight FLIM Networks for Salient Object Detection in Biomedical Images
Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands but typically strive in complex and scarce labeled-data scenarios. Feature Learning from Image Markers (FLIM) learns an encoder's convolutional kernels among image patches extracted from discriminative regions marked on a few representative images, dismissing large annotated datasets, pretraining, and backpropagation. Such a methodology exploits information redundancy commonly found in biomedical image applications. This study presents methods to learn dilated-separable convolutional kernels and multi-dilation layers without backpropagation for FLIM networks. It also proposes a novel network simplification method to reduce kernel redundancy and encoder size. By combining a FLIM encoder with an adaptive decoder, a concept recently introduced to estimate a pointwise convolution per image, this study presents very efficient (named flyweight) SOD models for biomedical images. Experimental results in challenging datasets demonstrate superior efficiency and effectiveness to lightweight models. By requiring significantly fewer parameters and floating-point operations, the results show competitive effectiveness to heavyweight models. These advances highlight the potential of FLIM networks for data-limited and resource-constrained applications with information redundancy.
- Open Access
- 10 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (8) , 1-39
A Comprehensive Review and New Taxonomy on Superpixel Segmentation
Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications, since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with a new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 23 strategies and a grid segmentation baseline based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in superpixel segmentation and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark .
- 10 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (8) , 1-39
Open AccessA Comprehensive Review and New Taxonomy on Superpixel Segmentation
Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications, since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with a new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 23 strategies and a grid segmentation baseline based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in superpixel segmentation and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark .
- 27 November 2023
- Published by Springer Nature
- p. 494-509
Graph-Based Feature Learning from Image Markers
- 27 November 2023
- Published by Springer Nature
- p. 494-509
Graph-Based Feature Learning from Image Markers
- 28 June 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 163, 107203
Toward automating the diagnosis of gastrointestinal parasites in cats and dogs
- 28 June 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 163, 107203
Toward automating the diagnosis of gastrointestinal parasites in cats and dogs
- 20 October 2022
- Published by Springer Nature
- p. 261-273
Fast and Effective Superpixel Segmentation Using Accurate Saliency Estimation
- 20 October 2022
- Published by Springer Nature
- p. 261-273
Fast and Effective Superpixel Segmentation Using Accurate Saliency Estimation
- Open Access
Iterative Saliency Enhancement using Superpixel Similarity
Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its saliency map. We fill this gap by introducing a hybrid approach, named \textit{Iterative Saliency Enhancement over Superpixel Similarity} (ISESS), that iteratively generates enhanced saliency maps by executing two operations alternately: object-based superpixel segmentation and superpixel-based saliency estimation -- cycling operations never exploited. ISESS estimates seeds for superpixel delineation from a given saliency map and defines superpixel queries in the foreground and background. A new saliency map results from color similarities between queries and superpixels at each iteration. The process repeats and, after a given number of iterations, the generated saliency maps are combined into one by cellular automata. Finally, the resulting map is merged with the initial one by the maximum bewteen their average values per superpixel. We demonstrate that our hybrid model can consistently outperform three state-of-the-art deep-learning-based methods on five image datasets.
Open AccessIterative Saliency Enhancement using Superpixel Similarity
Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its saliency map. We fill this gap by introducing a hybrid approach, named \textit{Iterative Saliency Enhancement over Superpixel Similarity} (ISESS), that iteratively generates enhanced saliency maps by executing two operations alternately: object-based superpixel segmentation and superpixel-based saliency estimation -- cycling operations never exploited. ISESS estimates seeds for superpixel delineation from a given saliency map and defines superpixel queries in the foreground and background. A new saliency map results from color similarities between queries and superpixels at each iteration. The process repeats and, after a given number of iterations, the generated saliency maps are combined into one by cellular automata. Finally, the resulting map is merged with the initial one by the maximum bewteen their average values per superpixel. We demonstrate that our hybrid model can consistently outperform three state-of-the-art deep-learning-based methods on five image datasets.