I'm currently an Associate Professor at the Federal University of Viçosa (UFV), Brazil.

I received a B.Sc. degree in Computer Science from UNIVEM, Brazil, in 2004, and an M.Sc. and Ph.D. degree in Computer Science from the Federal University of São Carlos (UFSCar) in 2007 and 2015, respectively.

My research interests include Image and Signal Processing, Computer Vision, Machine Learning, and Deep Learning.

João Fernando Mari

Associate Professor

Federal University of Viçosa
Campus Rio Paranaíba
Brazil

News

[2025-September] Tutorial accepted to SIBGRAPI 2025
[2025-August] Paper published in "Remote Sensing Applications: Society and Environment"
  • Silva, L.H.F.P.; Mari, J.F.; Escarpinati, M.C.; Backes, A.R.; Cloud removal with compact diffusion models: A residual block-based approach
  • Link to the paper
[2025-January] Full papers accepted to VISAPP 2025
  • Mari, J.F., Moreira, L.F.R., Silva, L.H.F.P.; Escarpinati, M.C.; Backes, A.R. Breast Cancer Image Classification Using Deep Learning and Test-Time Augmentation
  • Link to the paper.
  • Silva, L.H.F.P.; Mari, J.F., Escarpinati, M.C.; Backes, A.R. Evaluating Combinations of Optimizers and Loss Functions for Cloud Removal Using Diffusion Models
  • Link to the paper.
[2024-November] Full paper accepted to BRACIS 2024
[2024-June] Workshop on Computer Vision 2024 (WVC'2024) was held at UFV - Rio Paranaíba in Novemeber 2024.
[2024-February] The material for the Introduction to Digital Image Processing course (2023) is available.
[2024-January] Full paper accepted to VISAPP 2024
[2023-November] Best Paper AWARD! WVC 2023
[2023-November] Full papers accepted to WVC 2023
  • Pereira Neto, R.G.; Sousa, P.M.; Rodrigues Moreira, L.F.. Goog God, P.I.V.; Mari, J.F. Enhancing green coffee quality assessment through deep learning
  • Link to the paper.

Education and Background

PhD - Computer Science - 2015
MSc - Computer Science - 2007
BSc - Computer Science - 2004

Recent Publications

Journals
Conferences

Research

  • [2022-08-01 - now] Analysis of satellite images with applications in precision agriculture
  • [2021-09-01 - now] Development and evaluation of an automated system for analyzing and processing soybean seeds
  • [2020-08-01 - now] Pre-processing, correction and registration of agricultural images obtained by unmanned aerial vehicles
  • [2017-08 - 2018-07] Application of computational methods for analysis of water stress in plantations through thermal imaging
  • [2018-08 - 2022-07] Study of convolutional neural networks for classifying objects in microscopy images
  • [2016-08 - 2016-08] HEP-2 Cell Image Classification using convolutional neural networks enhanced by evolutionary algorithms
  • [2016-08 - 2018-07] Cell segmentation methods in microscopy images based on the watershed transform

Teaching

Undergratuate
Other materials

Awards

  • BEST POSTER AWARD:
  • Automated Segmentation of the Spinal Column in MRI Volumes Using Deep Learning
  • Carvalho, R.S.; Silva, L.H.F.P.; Mari, J.F.
  • XX Workshop on Computer Vision (WVC). São Carlos - SP, 2025.
  • BEST PAPER AWARD:
  • Classifying pests in crop images using deep learning.
  • Mota, G.S.L.; Silva, L.H.F.P.; Rodrigues Moreira, L.F.; Mari, J.F.
  • XVIII Workshop de Visão Computacional (WVC). S. B. do Campo - SP, 2022.
  • Article in the UFV portal. (Brazilian Portuguese)
  • BEST PAPER AWARD:
  • Cell classification using handcrafted features and bag of visual words.
  • Faria, L.C.; Rodrigues, L.F.; Mari, J.F.
  • XIV Workshop de Visão Computacional (WVC). Ilhéus - BA, 2018.
  • BEST POSTER AWARD:
  • Improving the definition of markers for the watershed transform by combining h-maxima transform and convex-hull.
  • Gonçalves, W.F.; Rodrigues, R.J.; Mari, J.F.
  • XIII Workshop de Visão Computacional (WVC). Natal - RN, 2017.
  • Article in the UFV portal. (Brazilian Portuguese)

Contact

Email
  • joaof.mari <at> ufv.br
Professional address

“An expert is a person who has made all the mistakes that can be made in a very narrow field.” - Niels Bohr.

Last updated in 2025-12-01
My old website (Brazilian Portuguese)
Plain Academic