Generative AI methods to model Printing-and-Digitalization process

Generative AI methods to model Printing-and-Digitalization process

Réf ABG-127858 Stage master 2 / Ingénieur Durée 6 mois Salaire net mensuel 4.35 euros per hour
10/01/2025
Université Lumière Lyon 2 Lieu de travail Lyon Auvergne-Rhône-Alpes France

Champs scientifiques:

• Informatique

Mots clés: Generative learning, image processing, printed documents

Date limite de candidature: 31/01/2025

Établissement recruteur

Founded in 1973, Université Lumière Lyon 2 welcomes nearly 30,000 students on its two campuses, ranging from undergraduate to doctoral level. As a university of literature, languages, and human and social sciences, it is comprised of 13 teaching units spread over four main areas of teaching and research.

With 33 laboratories and four research federations, Université Lumière Lyon 2 focuses on innovation, interdisciplinarity, partnership, and an international outlook. The university aims to enable communication between human and social sciences and hard sciences, addressing current societal and scientific challenges.

Université Lumière Lyon 2 has a strong focus on international cooperation and currently has agreements with 350 institutions worldwide. International students account for more than 15% of the overall student body.

Description

Context of the study:

Due to the development and broad availability of high-quality printing and scanning devices, the number of forged or counterfeited products and documents is dramatically increasing. Continuous research of new solutions to protect documents and valuable products is essential.

One promising solution is the use of security printing. When an electronic document is printed and scanned multiple times, a slightly different image is obtained each time due to the optical characteristics of the capture devices. This information loss can be used to identify the devices used for producing the document's hardcopy.

This internship is part of the ANR project TRUSTIT: Theoretical and practical study of physical object security in real-world use cases, aiming to explore the potential offered by deep learning methods in the context of secure printing from the verifier's point of view.

Description of the subject:

The generative neural networks (GANs) and probabilistic latent diffusion models have shown efficiency in data generation and style transfer. During this internship, we will work on learning a surrogate representation of the degradations added during the Printing-and-Digitalization (PD) process to printed documents. The main tasks of this internship are:

1. To learn a surrogate representation of one pair printer-scanner using the existing large dataset of L3iTextCopies.
2. To experiment with different architectures of GANs and probabilistic diffusion approaches to identify the best method for our task.
3. To compare the pseudo-synthetic samples with real printed documents using commonly used metrics such as Pearson correlation, Mean Square Error (MSE) distance, and Fréchet Inception Distance (FID) between the datasets.
4. To evaluate the possibility of fine-tuning the proposed models for unseen pairs of printer and scanner.
5. To create a public synthetic dataset of printed documents and, if possible, to publish the results in an international conference or scientific journal.

Place and allowance of internship:

The internship will be held in LIRIS (Laboratoire d’Informatique en Image et Systèmes d’information) laboratory, campus of Université Lumière Lyon 2, Bron. Internship allowance is 4.35 euros per hour.

Profil

• The candidate must currently be enrolled in a Master 2 program or in the final year of engineering school (corresponding to Bac+5 in France) in Computer Science.
• Programming languages: Python.
• Libraries for image analysis and processing: OpenCV, scikit-image (Python).
• Machine learning frameworks: scikit-learn, PyTorch.
• Scientific knowledge: signal processing, image analysis, machine learning, and deep learning.
• Knowledge of multimedia security will be considered a plus.
• Languages: French or English.

Prise de fonction

03/03/2025