‹ Back to the directory

Petr Dokladal

Petr Dokladal

Researcher Scientist

Center · STIM

Topic(s)
Additive Manufacturing, Medical Image Analysis, Nuclear

Biography

Petr Dokladal is a researcher specializing in image processing, computer vision, and machine learning as applied to materials science and industry. His work focuses on developing advanced methods for the analysis and optimization of microstructures, particularly in composite materials, renewable energy, and critical systems such as energy materials. His expertise includes the use of deep generative models, such as generative adversarial networks (GANs) and diffusion models, for the design and interpretation of complex microstructures, as well as the integration of physics-informed techniques for modeling and segmentation. Petr Dokladal has also contributed to industrial challenges, such as the automated inspection of components in remanufacturing or the detection of anomalies in additive manufacturing processes, by combining robust and generalizable approaches. His research addresses cross-cutting issues, such as the energy efficiency of high-performance computing (HPC) systems and resource optimization in critical infrastructure.

Publication(s)

Teaching

Image Analysis: From Theory to Practice

Lecturer

The course includes a theoretical presentation on image filtering and segmentation tools in the morning and tutorials in the afternoon. Binary, grayscale, and color images, as well as 2- and 3-dimensional images, are covered. Examples drawn from a wide variety of real-world applications illustrate the capabilities of the tools presented.

PhD supervision

  • 2023 Characterization of energetic material damage at the microstructural scale ROBIN Camille
  • 2023 Dynamic and morphological characterization of the electrochemical environment in lithium-ion batteries during charge cycles BOTTENMULLER Antoine
  • 2022 Deep learning approaches for the analysis and optimization of fiberglass-reinforced polymer matrix composites BASSO DELLA MEA Guilherme
  • 2022 High-performance, energy-efficient artificial intelligence: from measurement and modeling to multi-objective scheduling NANA TCHAKOUTE Roblex
  • 2017 Unsupervised vision methods based on image perception information BAZAN Eric
  • 2017 Experimental and numerical study of the sensitivity of energetic compositions: influence of the microstructure and role of damage KAESHAMMER Elodie
  • 2015 Automatic segmentation optimization of fragmented granular materials CHABARDES Théodore-Flavien
  • 2015 Image segmentation problems and contribution to mathematical morphology ALAIS Robin