Low Resolution Face Recognition Using Generative Adversarial Network (Gan) [post]

Howard Martin, Suharjito
2020 unpublished
Although face recognition system has achieved a very good performance in the past years, but Low Resolution Face Recognition (LRFR) is still challenging because low resolution image would decrease the accuracy. This research aimed to solved and get the best SR method to solved LRFR problem. YTF dataset used for fine tuning SR methods. While LFW dataset used for fine tuning and evaluating FaceNet model. The images would be increased using Res-Net GAN and RRDB GAN. Then the images would be
more » ... ges would be recognized using FaceNet. The images that had been increased by RRDB GAN reached the highest accuracy 98.96 %.
doi:10.21203/rs.3.rs-36971/v1 fatcat:qcfilidx7rfotnllzu5zphg5py