Hu Li Moments for Low Resolution Thermal Face Recognition
Naser Zaeri · 2018
In this paper, we present a new technique for low resolution face recognition using Hu Li moment invariants. The new technique can handle the issue of low resolution images very efficiently by the virtue of thermal face characteristics. The new technique will be tested on a new database comprising of images of different expressions, and were taken within different time-lapse. Experiments have resulted to almost consistent recognition rates. The proposed technique offers outstanding discriminability and performs efficiently, with an average recognition rate of ~94% over the various resolutions.