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

With the fast development of deep learning, its performance in image classification and object recognition has presented dramatic improvements. These promising results could also be applied to better understand speckle patterns in scattering media imaging. In this paper, a multimode fiber is used as the scattering media, and 4000 face and nonface original images are transmitted generating speckle patterns. A SpeckleNet is proposed and trained with these 3600 speckle patterns based on a convolutional neural network, and its output layer is activated for a support vector machine (SVM) classifier. The binary classification accuracy of the proposed CNN-architecture SpeckleNet for face and nonface speckle patterns classification tested on another 400 speckle patterns is about 96%, which has been improved compared with the accuracy of the pure SVM method. The promising results confirm that the combination with deep learning could lead to lower optical and computation costs in optical sensing and contribute to practical applications in optics.