FACING

The main objectives of this project are to conduct exhaustive batteries of tests of tools created by INCM for the manipulation of images of people's faces for identification and travel documents. The challenges to be overcome include: (1) the processing of images from vision systems consisting of medium and medium-low quality and resolution cameras, namely current vision systems already in operation in enrollment portals and for which it is intended to increase the lifetime, maintaining or improving performance, including the removal of the background of the images, allowing an intelligent segmentation of the pixels relating to the photographed person (foreground) and pixels relating to the background (background); (2) analysis and verification of compliance with the requirements and recommendations of international organizations on the photographs of people contained in these documents; (3) facial recognition through comparison between feature vectors of faces stored in a Database and feature vectors of a person presented for authentication, either in the context of validation (1:1) or identification (1:n) and (4) proof of life to distinguish between the face of a living person and fraudulent objects or artifacts that intend to imitate a living person. The algorithms will be implemented by INCM, integrating technology and algorithms from ISR-UC. Exhaustive tests will be carried out to measure the defined KPIs, as a form of quality control of the algorithms.