[INPp1-2] Registrable Lensless Face Recognition System based on Deep Learning
Lensless imaging, Convolutional Neural Network, Face Recognition, Deep Learning
We proposed a lensless recognition system associated with deep learning paradigm. An amplitude-modulated mask is applied as an element for optical encryption. Then, ResNet-50 architecture was trained to learn a well-structured representation space for the visual recognition task. Over 90% sensitivity and 98% specificity with 10 classes proved the concept.