Missions

Within the framework of the recently funded ANR project AI-WOOD, researchers from the CEPAM, the i3S laboratory and the Centre INRIA d'Université Côte d'Azur are collaborating to the development of new machine/deep learning approaches aiming at performing the taxonomical identification (i.e. classification at the species, genus or family level) of wood and charcoal from microscopic 2D images. The project has a main interest from an archaeological point of view, the main idea being to train a classifier on a modern collection (about 6000 images for 120 species) and then use it to identify ancient charcoals. The anthracologists (i.e. the archaeologists specialized in the identification and analysis of ancient charcoal) actually perform this identification relying on comparative anatomy and based on anatomical features settled by the IAWA that they build manually through microscopic observation. Apart from being long and tedious, this identification routine is not entirely satisfying, (also) due to the anatomical proximity of some essences.
Hence, the aim of this project is to explore the potential of machine/deep learning to directly identify the taxon of a specimen from the microscopic image and possibly to boost the identification routine. Although some attempts in this direction have been made in the literature (Rosa da Silva et al., 2022; Silva et al., 2022) there is still considerable room for improvement.
A PhD student has set up a deep learning model enabling us to achieve an accuracy of around 80% on 4 classes for which we have sufficient data. The PhD student is working on several issues: image resolution, cross-section fusion, class hierarchies (family, genus, species) and the use of anthracologists' expert knowledge. The current database contains a large number of classes, but their coverage is highly variable: many classes contain data on very few individuals. The main focus of this engineering position will be the study of Few Shot Learning (FSL).

Activités

This position will involve different steps:
- state of the art of few shot learning,
- study and test of available codes with charcoal data,
- coding the non available algorithms (if needed),
- comparison of the different solutions,
- contribution to existing algorithms.

Compétences

Deep Learning, Image Processing, Python programming (pytorch, keras).
Deep learning for images. Pratice in programming using python deep learning libraries such as pytorch (mandatory), keras (optional).

Contexte de travail

This position is part of the ANR AI-WOOD project on charcoal classification from microscopic images.
This position is available within the SPARKS Pole of the i3S / UMR 7271 Laboratory in Sophia Antipolis. The Laboratory for Computer Science, Signals and Systems at Sophia Antipolis (i3S), created in 1989, conducts research in computer science. With a staff of nearly 300 members, including professors and researchers from the Université Côte d'Azur, CNRS and Inria researchers, administrative and technical staff, doctoral students and trainees, it is one of the largest public laboratories on the Côte d'Azur and was one of the first to be established in the Sophia Antipolis technology park.

Contraintes et risques

None