Laboratoire de Génie Informatique et d’Automatique de l’Artois

Pauline MINARY

Ph.D. student
(Position when this person departed from the LGI2A)
Member of the research themes:
Evidential joint calibration of binary SVM classifiers
Soft Computing, pp 4655-4671, Vol. 23, No. 13, juillet 2019
Face pixel detection using evidential calibration and fusion
International Journal of Approximate Reasoning, pp 202-215, Vol. 91, décembre 2017
Calibration évidentielle conjointe de classifieurs SVM binaires fondée sur la régression logistique
Actes des 26e rencontres Francophones sur la Logique Floue et ses Applications, LFA 2017, pp 39-46, (Prix ex aequo du meilleur papier doctorant), Amiens, France, Cepadues, octobre 2017
Evidential joint calibration of binary SVM classifiers using logistic regression
Proceedings of the 11th International Conference on Scalable Uncertainty Management, SUM 2017, pp 405-411, Volume 10564 of Lecture Notes in Computer Science, Granada, Spain, S. Moral, O. Pivert, D. Sánchez and N. Marín (Eds.), Springer, octobre 2017
An Evidential Pixel-Based Face Blurring Approach
4th International Conference on Belief Functions, BELIEF 2016, pp 222-230, LNAI 9861 (co-best student paper award), Prague, Czech Republic, J. Vejnarová and V. Kratochvil (Eds.), Springer, septembre 2016
International conference with review committee
A fusion method for blurring faces on platforms using belief functions
11th World Congress on Railway Research, Milan, Italie, juin 2016

Author of the Ph.D. thesis "Evidential calibration and fusion of multiple classifiers: application to face blurring"

2014 - 2017

To ensure safely trains departures, especially in a high-density environment, the SNCF offers the driver of the train a camera system allowing him/her to see all of his train within monitors displaying images of the platform.

To allow the SNCF to use these videos for other purposes, such as studying for example moving users in a station, it is necessary to respect the right of publicity and then to blur people faces on images.

The objective of this thesis is then to realize a robust face detection system in order to blur faces. This system will in particular be confronted to uncontrolled conditions (weather, exterior, interior, ...) in which operate the cameras.