DCDalcimar Casanova

Dalcimar Casanova

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article



Latest Publications

  • Newborn Fingerprint Recognition: Toward Reliable Super-Resolution Equivalences

    by Barbara de O. Koop, João H. P. Machado, Luiz F. P. Southier, Jefferson T. Oliva, Marcelo Teixeira, Marcelo Filipak, Luiz A. Zanlorensi, Myriam R. B. S. Delgado, Dalcimar Casanova

  • Open Access

    Comparative analysis of the Support Vector Machine and Convolutional Neural Network algorithms applied in classifying Acer Palmatum plant subspecies

    by Patrick de Souza Sagioratto, Rúbia Eliza de Oliveira Schultz Ascari, Dalcimar Casanova

    Background: Plant identification is an essential task as it provides valuable information about plant characteristics and helps determine the population and distribution of species. This paper presents an artificial intelligence solution developed to automatically classify subspecies of the plant species Acer palmatum based on images. A database containing subspecies of Acer palmatum was created, and supervised learning algorithms such as Support Vector Machine (SVM) and Convolutional Neural Network (CNN) were used to classify them. The experiments included different scenarios, such as original images, feature extraction, and data augmentation techniques. Results: The results showed that the CNN with transfer learning and data augmentation performed best, standing out as the best model tested regardless of the dataset evaluated. Conclusions: These findings suggest that advanced Machine Learning techniques can be highly effective in classifying subspecies of Acer palmatum, providing a valuable biodiversity monitoring and mapping tool.

  • Open Access

    A deep learning approach to age newborns' fingerprints minutiae maps

    by Luiz Fernando Puttow Southier, Dalcimar Casanova

    Apesar da necessidade reconhecida de sistemas de identificação neonatal, eles dependem de mapas de minúcias que se distorcem ao longo do tempo devido ao crescimento dos dedos, perda de peso e alterações na pele, afetando as taxas de reconhecimento. A literatura tentou abordar o desafio de emular as mudanças no mapa de minúcias utilizando fatores de escalonamento. No entanto, a eficácia dessas abordagens, especialmente em indivíduos mais jovens, permanece incerta. Embora os fatores de escalonamento tenham sido usados para mitigar o efeito da idade, esse método simplifica excessivamente a suposição de padrão de crescimento, negligenciando padrões de crescimento distintos observados em crianças pequenas. Este estudo visa preencher essa lacuna desenvolvendo e avaliando uma solução de inteligência artificial para emular as mudanças no mapa de minúcias de um recém-nascido ao longo do tempo. A hipótese é que um modelo de crescimento baseado em Deep Learning poderia fornecer uma abordagem mais eficaz do que os fatores de escalonamento tradicionais, oferecendo uma representação mais precisa e adaptável do desenvolvimento dos recém-nascidos e mitigando o impacto do efeito da idade nas características biométricas. No entanto, sem um banco de dados longitudinal de alta qualidade, uma função de perda diferenciável baseada na diferença entre dois mapas de minúcias e um método para alinhar esses mapas, a implementação de tal abordagem torna-se inviável. Pesquisas futuras devem abordar esses aspectos críticos para avançar no desenvolvimento de soluções biométricas eficazes para identificação neonatal.

  • Open Access

    Recursive Class Connectivity Classification (R3C) Applied to Binary Image Segmentation for Improved Infant Fingerprint Enhancement

    by João Leonardo Harres Dall Agnol, Luiz Fernando Puttow Southier, Jefferson Tales Oliva, Marcelo Teixeira, Rodrigo Minetto, Marcelo Filipak, Dalcimar Casanova, Érick Oliveira Rodrigues

    Image enhancement plays a crucial role in infant fingerprint matching, as child-specific characteristics such as smaller finger dimensions and thinner ridge structures often degrade image quality during acquisition. To address these limitations, enrollment typically depends on specialized high-resolution scanners, which most existing enhancement methods are not designed to support. Consequently, identification rates for children remain significantly lower than those achieved with adult fingerprints. This study introduces Recursive Class Connectivity Classification (R3C), a novel framework that iteratively refines binary segmentation outputs from existing enhancement methods by extending ridge structures. R3C does not require modifications to the underlying classifier and operates without training data, which is not currently available for infant fingerprints. Instead, the method improves segmentation by repeatedly feeding the classified image back into the classification process, while combining each intermediate segmentation with the original input image. Experiments conducted on three fingerprint datasets using four different enhancement classifiers show that R3C can increase the True Acceptance Rate (TAR) by up to 4% for children and over 40% for newborns, compared to using the enhancement methods alone. A qualitative analysis further demonstrates that R3C reconnects fragmented ridge patterns, improving the visual quality of segmentation. Because it functions independently of the enhancement method used, R3C provides a flexible and broadly applicable solution for improving binary segmentation.


  • Open Access

    A Systematic Literature Review on Neonatal Fingerprint Recognition

    by Luiz Fernando Puttow Southier, Gustavo Alexandre Tuchlinowicz Nunes, João Henrique Pereira Machado, Matheus Buratti, Pedro Henrique de Viveiros Trentin, Wesley Augusto Catuzzo de Bona, Barbara de Oliveira Koop, Elioenai Markson Ferreira Diniz, João Victor Costa Mazzochin, João Leonardo Harres Dall Agnol, et al.

    Neonatal biometrics, especially those based on fingerprint traits, can potentially improve early childhood identification with decisive applications in healthcare, identity management, and other critical social domains. Although many biometric approaches to human recognition exist, most of them cannot be directly applied to neonates. The main barrier is the reduced size of children’s biometric traits, which affects image quality as these traits are still developing. Another issue is the lack of child biometric databases, as a periodic recollection of images is a fundamental part of neonatal identification regarding the feasibility evaluation of temporal recognition. Several works can be found in the literature addressing some of these issues. However, there is still no systematic review allowing a general understanding of these solutions, discussing their links, gaps, comparisons, and open challenges. In this sense, this article presents a systematic literature review on neonatal biometrics. In total, 1,878 papers were screened and classified, resulting in 45 being selected to be analyzed in this study. We detail and compare the results of datasets, scanners, methods, and techniques to achieve and improve neonatal recognition. Finally, research trends are identified and discussed based on the main gaps in the literature.


  • Open Access

    The Use of Long Short-Term Memory Models to Estimate Soybean Pricing: A Regional Climate Data Evaluation From Brazil

    by Jefferson Tales Oliva, Otávio Pigozzo Martelli, Marco Antônio de Castro Barbosa, Viviane Dal Molin, Dalcimar Casanova, Marcelo Teixeira

    This work uses machine learning methods to analyze the influence of the Brazilian climate on international soybean price variability. For this purpose, climatic data, historical series of the extended national consumer price index, dollar price historical series, soybean harvest historical series, and international soybean price historical series are collected from different data sources. The data is then preprocessed and grouped by state. Afterward, data from the five most productive Brazilian states, Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS), which together correspond to 74.9% of total production, are chosen. Then, predictive models were built using the long short-term memory (LSTM) method, which is applied to each state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. These models are evaluated using 10-fold sequential split cross-validation, whose predictive results are used for performance comparison through statistical hypothesis testing. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest average values of root mean squared error (RMSE) and mean absolute error (MAE), which are 20.90 and 16.72, respectively. Regarding predictors trained without climate data, the RS and PR obtained the lowest averaged values of RMSE (20.84) and MAE (16.81), respectively. After performing statistical hypothesis tests, no significant differences were found between the models, stating, with certainty 95%, that the Brazilian climatic data did not influence soybean prices in our study.


  • Open Access

    Review of: "Cardiac Adipose Tissue, Imaging Segmentation, and Quantification for Cardio-Vascular Disease Assessment – A survey"

    by Dalcimar Casanova

    The manuscript titled "CARDIAC ADIPOSE TISSUE, IMAGING SEGMENTATION, AND QUANTIFICATION FOR CARDIO-VASCULAR DISEASE ASSESSMENT – A SURVEY" presents a comprehensive and technically detailed review of the role of cardiac adipose tissue (CAT) in cardiov...

  • Open Access

    A Super-Resolution Approach for Image Resizing of Infant Fingerprints With Vision Transformers

    by João H. P. Machado, Barbara De O. Koop, Marcelo Filipak, Marco A. C. Barbosa, Jefferson T. Oliva, Luiz Fernando Puttow Southier, Dalcimar Casanova, Marcelo Teixeira

    Digital biometrics is one of the most widespread and reliable means of recognizing human identity. Despite being well-established for adults, digital biometrics for newborns constitutes a considerable open challenge in the literature. The very small size of the fingers exposes subtle features that can neither be visually inspected nor computationally captured. This leads conventional biometric matchers, which generally rely on the distance between ridges, not to work as expected for newborns. To some extent, this problem can be mitigated by increasing the scanner’s resolution, which is an expensive strategy. Besides, the saturation limit for resolution is unknown beforehand. Another alternative is to resize images using interpolation, but this can introduce unexpected noises or highlight preexisting ones. This paper proposes an approach for image resizing based on Super-Resolution networks that train Vision Transformer (ViT) how to handle newborn fingerprints, avoiding the introduction of noises while keeping and improving important details for biometric recognition. For biometric identification and verification, results show an increase in the order of 10% for resized images in comparison with traditional resizing algorithms.


  • Open Access

    Literacia digital dos professores de português do Ensino Médio

    by Caroline Vieira Neves, Dalcimar Casanova, Edilson Pontarolo

    Medir a literacia digital dos professores é importante, pois pode indicar necessidades de treinamentos e embasar políticas públicas voltadas à formação docente, essenciais para uma integração mais eficaz das Tecnologias Digitais de Informação e Comunicação (TDIC) no ensino. A escala AliDip é uma ferramenta desenvolvida para avaliar as competências docentes no uso das TDIC, permitindo verificar perfis e níveis de apropriação tecnológica em diferentes contextos educacionais. Este trabalho propõe aplicar a escala AliDip para medir a literacia digital de professores de Língua Portuguesa do Ensino Médio em escolas públicas, buscando preencher uma lacuna de estudos focados nesse nível de ensino e contexto específico, como o município de Pato Branco. Ao compreender as competências e desafios enfrentados por esses docentes, espera-se fornecer um diagnóstico que possa direcionar iniciativas de capacitação e fortalecer o uso pedagógico das TDIC na educação local, promovendo práticas educativas mais conectadas com as demandas do mundo digital.

  • Open Access

    New Approach for Soil Carbon and Nitrogen Assessment through Image Analysis: A Case Study with Oxisols and Inceptisols

    by Juliano Tiago Rinaldi, Dalcimar Casanova, Larissa Macedo dos Santos Tonial, Marcelo Teixeira, Heitor Silvério Lopes

    This paper presents a new method for predicting carbon and nitrogen content in Oxisols and Inceptisols soils using image analysis. The dataset comprises 40 Oxisols images and 51 Inceptisols images collected in southern Brazil. The images were segmented to isolate the soil area, resulting in the extraction of 12,744 windows. A pre-trained EfficientNetV2-S model was fine-tuned for regression, adding five layers at the end. The model was evaluated using RMSE and R² metrics. Two experiments were conducted: one predicting carbon and nitrogen content for each window and another predicting the median values of the windows for each soil sample. The results show that the median-based prediction significantly improved model performance, achieving an R² of 0.7425 for carbon and 0.7774 for nitrogen. This method offers a faster, non-destructive alternative to laboratory analysis for estimating soil carbon and nitrogen content, contributing to sustainable agricultural practices.