Section: New Results

Computer Vision and Deep Learning applied to Facial analysis in the invisible spectra

Participants : David Anghelone, Antitza Dantcheva.

The goal of our work is to analyze faces, as well as recognize events in the invisible spectra. In the last few years, face analysis has been a highly active area and has attracted a lot of interest from the scientific community. Limitations encountered in the visible spectrum such as illumination-restriction have the ability to be overcome in the infrared spectrum. We explored the state-of-the-Art of facial analysis in the invisible spectrum including low energy infrared waves, as well as ultraviolet waves. In this context we have captured images in each spectra and intend to process the data. We aim at designing a model, which extracts biometric features. The key challenges are the processing of contours, shape, etc. This subject is within the framework of the national project SafeCity: Security of Smart Cities.