Petr Dokladal

Chargé de recherche

Thème(s): Analyse d'image médicale, Fabrication additive, Nucléaire

Mots-clés

Équipe

STIM

Biographie

Petr Dokladal est un chercheur spécialisé en traitement d’images, vision par ordinateur et apprentissage automatique appliqués aux sciences des matériaux et à l’industrie. Ses travaux se concentrent sur le développement de méthodes avancées pour l’analyse et l’optimisation de microstructures, notamment dans les matériaux composites, les énergies renouvelables et les systèmes critiques comme les matériaux énergétiques. Son expertise inclut l’utilisation de modèles génératifs profonds, tels que les réseaux antagonistes génératifs (GAN) et les modèles de diffusion, pour la conception et l’interprétation de microstructures complexes, ainsi que l’intégration de techniques de physique informée pour la modélisation et la segmentation. Petr Dokladal a également contribué à des problématiques industrielles, comme l’inspection automatisée de composants en remanufacturing ou la détection d’anomalies dans les procédés de fabrication additive, en combinant des approches robustes et généralisables. Ses recherches abordent des enjeux transversaux, tels que l’efficacité énergétique des systèmes de calcul haute performance (HPC) et l’optimisation des ressources dans les infrastructures critiques.

Publication(s)

2026
Image generation of short glass fibre composite microstructures: From control to optimisation and damage prediction DOI : 10.1016/j.cma.2025.118686
2025
Dynamics simulations of RDX-based explosive materials during impact: role of the microstructure DOI : 10.1007/s00193-025-01243-3
2025
A Framework for Analytical Performance and Energy Prediction of DL Training on GPUs DOI : 10.1109/SBAC-PAD66369.2025.00028
2025
A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturing DOI : 10.1109/ETFA65518.2025.11205777
2025
Euclidean Distance to Convex Polyhedra and Application to Class Representation in Spectral Images DOI : 10.5220/0013385600003905
2025
Benchmark-Based Study of CPU/GPU Power-Related Features Through JAX and TensorFlow DOI : 10.1109/ACCESS.2025.3625414
2024
Physics informed self-supervised segmentation of elastic composite materials DOI : 10.1016/j.cma.2024.117355
2024
Power Consumption in HPC-AI Systems DOI : 10.1007/978-3-031-78698-3_6
2024
A Flexible Operational Framework for Energy Profiling of Programs DOI : 10.1109/SBAC-PADW64858.2024.00014
2023
Characterization by image analysis of materials heterogeneities produced by the Deep Soil Mixing technique DOI : 10.1016/j.matpr.2023.03.720
2022
Pixel-accurate road crack detection in presence of inaccurate annotations DOI : 10.1016/j.neucom.2022.01.051
2022
Inline monitoring of 3D concrete printing using computer vision DOI : 10.1016/j.addma.2022.103175
2022
A Parallel, O(n) Algorithm for an Unbiased, Thin Watershed DOI : 10.5201/ipol.2022.215
2022
Syncrack: Improving Pavement and Concrete Crack Detection through Synthetic Data Generation DOI : 10.5220/0010837300003124
2022
Automated analysis of platelet microstructures using a feature length orientation space DOI : 10.1007/s10853-021-06630-6
2021
Morphological characterization and elastic response of a granular material DOI : 10.1016/j.commatsci.2020.110247
2021
Rotation invariant networks for image classification for HPC and embedded systems DOI : 10.3390/electronics10020139
2021
A minimal model for classification of rotated objects with prediction of the angle of rotation DOI : 10.1016/j.jvcir.2021.103054
2020
A labeling algorithm based on a forest of decision trees DOI : 10.1007/s11554-019-00912-8
2020
Fast macula detection and application to retinal image quality assessment DOI : 10.1016/j.bspc.2019.101567
2020
Quantitative analysis of similarity measures of distributions
2019
Rotation Invariant CNN Using Scattering Transform for Image Classification DOI : 10.1109/ICIP.2019.8804467
2019
Combination of traction assays and multiphoton imaging to quantify skin biomechanics DOI : 10.1007/978-1-4939-9095-5_11
2018
Morphological co-processing unit for embedded devices DOI : 10.1007/s11554-015-0518-2
2018
Unsupervised Perception Model for UAVs Landing Target Detection and Recognition DOI : 10.1007/978-3-030-01449-0_20
2017
Function decomposition in main and lesser peaks DOI : 10.1007/978-3-319-57240-6_26
2017
A numerical approach for the mechanical analysis of superconducting rutherford-type cables using bimetallic description DOI : 10.1109/TASC.2017.2664803
2017
Automatic detection of cracks and delaminations in thermal images
2017
Morphological characterization of graphene plans stacking DOI : 10.1007/978-3-319-57240-6_35
2017
An affinity score for grains merging and touching grains separation DOI : 10.1007/978-3-319-57240-6_34
2017
Statistical threshold selection for path openings to detect cracks DOI : 10.1007/978-3-319-57240-6_30
2016
Geometry analysis of superconducting cables for the optimization of global performances DOI : 10.5220/0005667105400551
2016
A parallel, O(N) algorithm for unbiased, thin watershed DOI : 10.1109/ICIP.2016.7532823
2015
GPU implementation of linear morphological openings with arbitrary angle DOI : 10.1007/s11554-012-0248-7
2015
Ex vivo multiscale quantitation of skin biomechanics in wild-type and genetically-modified mice using multiphoton microscopy DOI : 10.1038/srep17635
2015
Real-time implementation of morphological filters with polygonal structuring elements DOI : 10.1007/s11554-012-0271-8
2014
Determination of collagen fiber orientation in histological slides using Mueller microscopy and validation by second harmonic generation imaging DOI : 10.1364/OE.22.022561
2014
Parsimonious path openings and closings DOI : 10.1109/TIP.2014.2303647
2014
Parallel implementation of sequential morphological filters DOI : 10.1007/s11554-011-0226-5
2013
Efficient geodesic attribute thinnings based on the barycentric diameter DOI : 10.1007/s10851-012-0374-7
2013
Automatic 3D segmentation of multiphoton images: A key step for the quantification of human skin DOI : 10.1111/srt.12019
2013
Filtering and segmentation of 3D angiographic data: Advances based on mathematical morphology DOI : 10.1016/j.media.2012.08.004
2012
In vivo multiphoton microscopy associated to 3D image processing for human skin characterization DOI : 10.1117/12.907410
2012
One-scan algorithm for arbitrarily oriented 1-D morphological opening and slope pattern spectrum DOI : 10.1109/ICIP.2012.6466813
2012
One-dimensional openings, granulometries and component trees in O(1) per pixel DOI : 10.1109/JSTSP.2012.2201694
2012
Efficient FPGA architecture for oriented 1-D opening and pattern spectrum DOI : 10.1109/ICIP.2012.6467203
2011
Linear openings in arbitrary orientation in O(1) per pixel DOI : 10.1109/ICASSP.2011.5946767
2011
Geodesic attributes thinnings and thickenings DOI : 10.1007/978-3-642-21569-8_18
2011
Region growing structuring elements and new operators based on their shape DOI : 10.2316/P.2011.759-018
2011
Morphological classification of particles recorded by the Timepix detector
2011
Fast streaming algorithm for 1-D morphological opening and closing on 2-D support DOI : 10.1007/978-3-642-21569-8_26
2011
Computationally efficient, one-pass algorithm for morphological filters DOI : 10.1016/j.jvcir.2011.03.005
2010
Pipeline architecture for compound morphological operators DOI : 10.1109/ICIP.2010.5653479
2010
Stream implementation of serial morphological filters with approximated polygons DOI : 10.1109/ICECS.2010.5724610
2009
Direction-adaptive grey-level morphology. Application to 3D vascular brain imaging DOI : 10.1109/ICIP.2009.5414356
2009
Spatially-variant morpho-hessian filter: Efficient implementation and application DOI : 10.1007/978-3-642-03613-2_13
2009
3-D Extraction of fibres from microtomographic images of fibre-reinforced composite materials DOI : 10.1007/978-3-642-03613-2_12
2009
Binary morphology with spatially variant structuring elements: Algorithm and architecture DOI : 10.1109/TIP.2008.2010108
2008
Grey-scale morphology with spatially-variant rectangles in linear time DOI : 10.1007/978-3-540-88458-3_61
2008
Grey-scale 1-D dilations with spatially-variant structuring elements in linear time
2008
Curvilinear morpho-Hessian filter DOI : 10.1109/ISBI.2008.4541170
2007
Frequency selective height-from-stereo reconstruction: Application to retinal oedemas detection
2005
Fast implementation of variational, contour-based object tracking
2005
Embedded real-time architecture for level-set-based active contours DOI : 10.1155/ASP.2005.2788
2004
Modelling of overlapping circular objects based on level set approach DOI : 10.1007/978-3-540-30125-7_52
2004
Contour-based object tracking with gradient-based contour attraction field
2004
Asynchronous multi-core architecture for level set methods
2003
Topologically controlled segmentation of 3D magnetic resonance images of the head by using morphological operators DOI : 10.1016/S0031-3203(03)00118-3
2003
A parallel architecture for curve-evolution partial differential equations DOI : 10.5566/ias.v22.p121-132
2003
A parallel algorithm for solving the Eikonal equation
2002
Prevention of hypoglycemia using risk assessment with a continuous glucose monitoring system DOI : 10.2337/diabetes.51.11.3263
2001
Segmentation of 3D head MR images using morphological reconstruction under constraints and automatic selection of markers
1999
Liver blood vessels extraction by a 3-D topological approach DOI : 10.1007/10704282_11

Enseignements

Analyse d'images : de la théorie à la pratique

Chargé d'enseignement

Le cours comprend une présentation théorique des outils de filtrage et de segmentation d'images le matin et des travaux dirigés l'après-midi. Les images binaires, à niveau de gris et couleur, ainsi que des images à 2, ou à 3 dimensions sont traitées. Des exemples tirés de la grande diversité d'applications réelles illustrent la capacité des outils présentés.

Direction(s) de thèse(s)

2023 Caractérisation de l'endommagement de matériaux énergétiques à l'échelle microstructurale ROBIN Camille
2023 Caractérisation dynamique et morphologique du milieu électrochimique des batteries Lithium-ion au cours des cycles de charge BOTTENMULLER Antoine
2022 Approches d’apprentissage profond pour l’analyse et l’optimisation de composites à matrice polymère renforcés par des fibres de verre BASSO DELLA MEA Guilherme
2022 intelligence artificielle haute-performance efficace en énergie : de la mesure et la modélisation à l'ordonnancement multi-objectifs NANA TCHAKOUTE Roblex
2017 Méthodes de vision non supervisée basées sur les informations de perception de l'image BAZAN Eric
2017 Etude expérimentale et numérique de la sensibilité de compositions énergétiques : influence de la microstructure et rôle de l'endommagement KAESHAMMER Elodie
2015 Optimisation de la segmentation automatique de matériaux granulaires fragmentés CHABARDES Théodore-Flavien
2015 Problèmes de segmentation d'images et contribution à la morphologie mathématique ALAIS Robin