Litcius/Paper detail

Speckle-learned convolutional neural network for the recognition of intensity degenerate orbital angular momentum modes

Venugopal Raskatla, Purnesh Singh Badavath, Vijay Kumar

2023Optical Engineering21 citationsDOI

Abstract

Intensity degenerate orbital angular momentum (OAM) modes are impossible to recognize by direct visual inspection even using available machine learning techniques. We are reporting speckle-learned convolutional neural network (CNN) for the recognition of intensity degenerate Laguerre–Gaussian (LGp , l) modes, intensity degenerate LG superposition modes, and intensity degenerate perfect optical vortices. The CNN is trained on the simulated one-dimensional far-field intensity speckle patterns of the corresponding intensity degenerate OAM modes. The trained CNN recognizes intensity degenerate OAM modes with an accuracy >99 % . Speckle-learned CNNs are also capable of recognizing intensity degenerate OAM modes even under the presence of high Gaussian white noise and atmospheric turbulence with an accuracy >97 % .

Topics & Concepts

Speckle patternDegenerate energy levelsPhysicsIntensity (physics)Angular momentumConvolutional neural networkSuperposition principleOpticsArtificial intelligenceComputer sciencePattern recognition (psychology)Quantum mechanicsOrbital Angular Momentum in OpticsOptical Polarization and EllipsometryAdaptive optics and wavefront sensing