Abstract

Advancements in optical, computing, and electronic technologies have enabled holograms of physical three-dimensional (3D) objects to be captured. The hologram can be displayed with a spatial light modulator to reconstruct a visible image. Although holography is an ideal solution for recording 3D images, a hologram comprises high-frequency fringe patterns that are almost impossible to recognize with traditional computer vision methods. Recently, it has been shown that holograms can be classified with deep learning based on convolution neural networks. However, the method can only achieve a high success classification rate if the image represented in the hologram is without speckle noise and occlusion. Minor occlusion of the image generally leads to a substantial drop in the success rate. This paper proposes a method known as ensemble deep-learning invariant occluded hologram classification to overcome this problem. The proposed new method attains over 95% accuracy in the classification of holograms of partially occluded handwritten numbers contaminated with speckle noise. To achieve the performance, a new augmentation scheme and a new enhanced ensemble structure are necessary. The new augmentation process includes occluded objects and simulates the worst-case scenario of speckle noise.

© 2022 Optica Publishing Group

Ensemble convolutional neural network for classifying holograms of deformable objects

H. H. Lam, P. W. M. Tsang, and T.-C. Poon
Opt. Express 27(23) 34050-34055 (2019)

Speckle-based deep learning approach for classification of orbital angular momentum modes

Venugopal Raskatla, B. P. Singh, Satyajeet Patil, Vijay Kumar, and R. P. Singh
J. Opt. Soc. Am. A 39(4) 759-765 (2022)

Deep learning speckle de-noising algorithms for coherent metrology: a review and a phase-shifted iterative scheme [Invited]

Silvio Montresor, Marie Tahon, and Pascal Picart
J. Opt. Soc. Am. A 39(2) A62-A78 (2022)

Deep learning-based object classification through multimode fiber via a CNN-architecture SpeckleNet

Ping Wang and Jianglei Di
Appl. Opt. 57(28) 8258-8263 (2018)

Speckle classification of a multimode fiber based on Inception V3

Zifei Li, Leihong Zhang, Zili Zhang, Runchu Xu, and Dawei Zhang
Appl. Opt. 61(29) 8850-8858 (2022)