The mr-MDA: An Invariant to Shifting, Scaling, and Rotating Variance for 3D Object Recognition Using Diffractive Deep Neural Network

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 20; p. 7754
• Main Authors: Zhou, Liang, Shi, Jiashuo, Zhang, Xinyu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 12.10.2022; MDPI
• Subjects: Classification; computer vision; Datasets; Deep learning; diffractive neural network; Fourier transforms; Light; Neural networks; Neural Networks, Computer; Neurons; Pattern Recognition, Visual; Propagation; Random variables; Recognition, Psychology; Visual Perception; diffractive neural network; deep learning; computer vision
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22207754

The diffractive deep neural network (D2NN) can efficiently accomplish 2D object recognition based on rapid optical manipulation. Moreover, the multiple-view D2NN array (MDA) possesses the obvious advantage of being able to effectively achieve 3D object classification. At present, 3D target recognition should be performed in a high-speed and dynamic way. It should be invariant to the typical shifting, scaling, and rotating variance of targets in relatively complicated circumstances, which remains a shortcoming of optical neural network architectures. In order to efficiently recognize 3D targets based on the developed D2NN, a more robust MDA (mr-MDA) is proposed in this paper. Through utilizing a new training strategy to tackle several random disturbances introduced into the optical neural network system, a trained mr-MDA model constructed by us was numerically verified, demonstrating that the training strategy is able to dynamically recognize 3D objects in a relatively stable way.