Invariant Classification of Holograms of Deformable Objects Based on Deep Learning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

2 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE 28th International Symposium on Industrial Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2392-2396
ISBN (Print)9781728136660
Publication statusPublished - Jun 2019

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2019-June
ISSN (Print)2163-5145

Conference

Title28th IEEE International Symposium on Industrial Electronics (ISIE 2019)
LocationPinnacle Hotel Harbourfront
PlaceCanada
CityVancouver
Period12 - 14 June 2019

Abstract

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%.

Research Area(s)

  • invariant hologram classification, deep learning, convolutional neural network

Citation Format(s)

Invariant Classification of Holograms of Deformable Objects Based on Deep Learning. / Lam, H.S.; Tsang, P.W.M.

Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2392-2396 8781149 (IEEE International Symposium on Industrial Electronics; Vol. 2019-June).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)