Accurate decoding of data pages in an amplitude- and phase-modulated signal beam detected by the single-shot transport of intensity equation method with convolutional neural network-based classifiers

Abstract

We propose an accurate method for the classification and decoding of data pages in complex-amplitude-modulated signal beams detected via the transport of the intensity equation (TIE) method using simple classifiers with a convolutional neural network (CNN) for holographic data storage (HDS). The classifiers allow a single-shot TIE method using two cameras to detect the complex-amplitude-modulated signal beam in HDS. Although the phase distribution detected using the single-shot TIE method tends to be superimposed with strong phase noise, we demonstrate experimentally that the CNN-based classifiers can classify/decode data pages in the complex-amplitude-modulated signal beam accurately without phase noise removal.