Abstract
Due to countless orthogonal eigenstates, light beams with orbital angular momentum(OAM) have a large potential information capacity. Recently, deep learning has been extensively applied in recognition of OAM mode. However, previous deep learning methods require a constant distance between laser and receiver. The accuracy will drop quickly if the distance of testing set deviates from the training set. Previous deep learning methods also have difficulty distinguishing OAM modes with positive and negative topological charges. In order to further exploit the huge potential of the countless dimension of state space, we proposed multidimensional information assisted deep learning flexible recognition (MIADLFR) method to make use of both intensity and angular spectrum information for the first time to achieve recognition of OAM modes unlimited by the sign of TC and distance with high accuracy. Also, MIADLFR can reduce the computational complexity significantly and requires much smaller training set.
Highlights
S INCE Allen et al [1] recognized that vortex beam with phase structure exp(ilφ) carries OAM l per photon, where l is topological charge(TC) vortex beam has been extensively investigated in optical manipulation [2], imaging [3], optical communication [4]
M is the size of testing set; N is the total number of TC in training set; yc(i) is a binary indicator which takes value 1 if and only if the actual TC of the ith sample of testing set is c. p(ci) is the probability of the TC of the ith sample to be c which is predicted by multidimensional feature fusion convolutional neural network (MFFCNN)
We proposed multidimensional information assisted deep learning flexible recognition (MIADLFR) method realize flexible recognition of OAM modes
Summary
S INCE Allen et al [1] recognized that vortex beam with phase structure exp(ilφ) carries OAM l per photon, where l is topological charge(TC) vortex beam has been extensively investigated in optical manipulation [2], imaging [3], optical communication [4]. Berkhout et al [8] demonstrated a very successful method for measuring the orbital angular momentum states of light based on log-polar transformation With this method we can get angular spectrum of vortex beam using two static optical elements. Because LG light with the same absolute value of TC with opposite sign share quite similar intensity profile which is all the information sent into CNN, there is no deep learning method realizing sorting LG light with positive and negative TC efficiently. These two drawbacks can severly block the practical application of light with orbital angular momentum. Fully connected layers process these two dimensions features and gives prediction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
