- Site: Paris
- Group: image processing and pattern recognition
- Axis: software and performance
Short Bio
I received the Ing. diploma from Ecole Pour l’Informatique et les Techniques Avancées (EPITA) in 2011, specialized in Imaging and Scientific Computing. I then received the M.Sc. in Applied Mathematics for Computer Vision and Machine Learning with honors from Ecole Normale Supérieure de Cachan in 2012 and a Phd from Université Paris-Est in 2015.
I’m currently an assistant professor with the EPITA Research Laboratory (LRE)
My interests are twofold:
- Image Processing and Statistical Learning. I have some affinities with Mathematical Morphology approaches to solve imaging problems.
- Efficient programming and algorithmic optimization. I am a skilled C++ programmer interested in exploiting the new C++ features to get both efficient, readable and easy-to-write programs.
| Contact information | |
|---|---|
| edwin1.carlinet@epita.fr | |
| Tel | +33 1 53 14 59 44 |
Research
Research interest
My research interests lie in the fields of mathematical morphology - notably the use of hierarchical representations, and the efficient implementation of Math. Morphology operators, high performance computing, with applications in document image processing (astrometry).
I am also the lead developer of Pylene, an image processing library implementing generic and efficient mathematical morphology related algorithms.
Examples of on-going projects include:
- The SoDuCo project where image processing expertise of the LRE is used to extract massively data from XIX’ trade directories of Paris. This is a joint work with the LASTIG (université Gustave Eiffel, IGN-ENSG), the EHESS, and the Archives Nationales)
- The fast implementation of mathematical morphology-related algorithms on massevely parallel architectures (join-work with the ALSOC team from LIP6 - Sorbonne Université).
Publications
Supervision
I currently supervise the PhD work of:
- B. Esteban (since Nov. 2020). Modern and efficient implementations of Mathematical Morphology algorithms for image processing and noise estimation. Joint supervision with Didier Verna and Guillaume Tochon
Former Phd students:
- Michaël Roynard, Generic programming in modern C++ for Image Processing (joint supervision with Thierry Géraud)
Former RDI Student:
- Guillaume Thomas (RDI-2023), Post-OCR correction of documents (with J. Chazalon)
- Philippe Bernet (RDI-2023), Kalman Filter implementation for robust line detection (with J. Chazalon)
- Quentin Kaci (RDI-2022), Fast implementation of the quasi flat-zone hierarchy
- Nicolas Blin (RDI-2022), Implementation of the Max-Tree algorithm on massively parallel architectures
- Yassine Damiri (PCR-2024), Parallel implementation of the Tree of Shapes
- Victor Simonin (PCR-2023), Fast implementation of hierarchies of segmentation
- Virgile Hirtz (PCR-2021), *Generioc image processing in C++"
- Célian Gossec (RDI-2021), Static/dynamic bridge in C++
Teaching
I am teaching the following courses at EPITA:
- Parallel programming (12H) (ING1 level - third year of undergrad studies)
- Data compression (12H) (ING1 level - third year of undergrad studies)
- C++ (8H) (ING1 level - third year of undergrad studies)
- Algorithmics (24H) (ING1 level - third year of undergrad studies)
- GPU programming (12H) (ING2 level - fourth year of undergrad studies)
I am a teaching assistant for:
- Théorie des Langages Rationnel (10H) (SPE - for second year of undergrad studies)
I am teaching the following courses at Sup’Biotech
- Computer programming - Bioinformatics (third year of undergrad studies)