TY - GEN
T1 - Invariant Classification of Holograms of Deformable Objects Based on Deep Learning
AU - Lam, H.S.
AU - Tsang, P.W.M.
PY - 2019/6
Y1 - 2019/6
N2 - In this paper, we propose a method for invariant classification holograms of deformable objects. Our proposed method, which is referred to as the "deep learning invariant hologram classification" (DL-IHC), is comprising of an augmented holographic dataset generation stage, and a deep neural network that is implemented with a convolutional neural network (CNN). Experimental results show that our proposed method is capable of classifying holograms of handwritten numerals with high success rates of over 99%.
AB - In this paper, we propose a method for invariant classification holograms of deformable objects. Our proposed method, which is referred to as the "deep learning invariant hologram classification" (DL-IHC), is comprising of an augmented holographic dataset generation stage, and a deep neural network that is implemented with a convolutional neural network (CNN). Experimental results show that our proposed method is capable of classifying holograms of handwritten numerals with high success rates of over 99%.
KW - invariant hologram classification
KW - deep learning
KW - convolutional neural network
UR - http://www.scopus.com/inward/record.url?scp=85070640706&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85070640706&origin=recordpage
U2 - 10.1109/ISIE.2019.8781149
DO - 10.1109/ISIE.2019.8781149
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781728136660
T3 - IEEE International Symposium on Industrial Electronics
SP - 2392
EP - 2396
BT - Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics
PB - IEEE
T2 - 28th IEEE International Symposium on Industrial Electronics (ISIE 2019)
Y2 - 12 June 2019 through 14 June 2019
ER -