Fig. 16: All-optical image classification using a diffractive optical network under spatially incoherent illumination.
From: Universal linear intensity transformations using spatially incoherent diffractive processors
a A K = 5 phase-only diffractive network trained to perform all-optical classification of handwritten digits under spatially incoherent illumination. b Confusion matrix generated by blind testing of the resulting diffractive network on 10,000 MNIST test images, evaluated using Nφ,te = 20,000. The overall blind testing accuracy of the network on the MNIST test set was 95.04%. For the phase profiles of the trained diffractive network layers, see Supplementary Fig. S4
