Faculty profile
Max Mignotte
Back to facultyThis profile is built from public research funding records (CIHR, NSERC and SSHRC) and PubMed. We have not imported them from a Université de Montréal directory, so their courses may be missing. Find their university profile.
Research
Latest papers
CoSOV1Net: A Cone- and Spatial-Opponent Primary Visual Cortex-Inspired Neural Network for Lightweight Salient Object Detection.
Sensors (Basel, Switzerland) · 2023 · senior author
A perceptual map for gait symmetry quantification and pathology detection.
Biomedical engineering online · 2015
Analyzing gait pathologies using a depth camera.
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference · 2012
Latest funding
- $72,000
New unsupervised Bayesian and energy-based models dedicated to image processing and computer vision applications
NSERC · 2022 · Principal investigator
- $130,000
Bayesian fusion models based on multi-level constraints and multiple criteria in image processing and computer vision
NSERC · 2016 · Principal investigator
- $120,000
Bayesian statistical fusion models based on constraints and multiple criteria in image processing and computer vision
NSERC · 2011 · Principal investigator
14 publications.
CoSOV1Net: A Cone- and Spatial-Opponent Primary Visual Cortex-Inspired Neural Network for Lightweight Salient Object Detection.
Ndayikengurukiye D, Mignotte M
A perceptual map for gait symmetry quantification and pathology detection.
Moevus A, Mignotte M, de Guise JA, Meunier J
Analyzing gait pathologies using a depth camera.
Nguyen HA, Auvinet E, Mignotte M, de Guise JA, Meunier J
MDS-based multiresolution nonlinear dimensionality reduction model for color image segmentation.
Mignotte M
Depth Energy Image for gait symmetry quantification.
Rougier C, Auvinet E, Meunier J, Mignotte M, de Guise JA
A label field fusion bayesian model and its penalized maximum rand estimator for image segmentation.
Mignotte M
Segmentation by fusion of histogram-based k-means clusters in different color spaces.
Mignotte M
DCT-based complexity regularization for EM tomographic reconstruction.
Mignotte M, Meunier J, Soucy JP
Localization of shapes using statistical models and stochastic optimization.
Destrempes F, Mignotte M, Angers JF
Image denoising by averaging of piecewise constant simulations of image partitions.
Mignotte M
New unsupervised Bayesian and energy-based models dedicated to image processing and computer vision applications
Principal investigators: Mignotte, Max
Keywords: digital image processing; bayesian inference; markov random fields; parametric or non parametric statistical models; penalized likelihood (or energy--based) models; fusion models; bicriteria optimization models; detection; segmentation; computer vision
Bayesian fusion models based on multi-level constraints and multiple criteria in image processing and computer vision
Principal investigators: Mignotte, Max
Bayesian statistical fusion models based on constraints and multiple criteria in image processing and computer vision
Principal investigators: Mignotte, Max
Bayesian statistical models based on global constraints in computer vision and image processing
Principal investigators: Mignotte, Max
Hybrid Bayesian statistical models for the detection and recognition of deformable shapes
Principal investigators: Mignotte, Max
From CIHR, NSERC and SSHRC funding decisions: CIHR since 2008, NSERC since 1991 and SSHRC since 1998, including their latest published competition results.
Frequent collaborators
- Jean Meunier and Max Mignotte: 4 shared papers
- Hubert Labelle and Max Mignotte: 1 shared paper
- Dépt. d'Informatique et R.O.
- Informatique et recherche opérationnelle
- Orthopédie
Co-authors at Université de Montréal, colored by department. Thicker lines mean more shared papers; select anyone to open their profile and their own map.
A short, specific email works best. This draft uses one of their recent papers; replace the parts in brackets with your own details before sending.