New phase unwrapping approach in digital holographic microscopy with deep learning
- Title
- New phase unwrapping approach in digital holographic microscopy with deep learning
- Author(s)
- Seunghyeon Hwang
- DGIST Authors
- Hwang, Seunghyeon ; Moon, Inkyu ; Park, Sanghyun
- Advisor
- 문인규
- Co-Advisor(s)
- Sanghyun Park
- Issued Date
- 2020
- Awarded Date
- 2020-02
- Type
- Thesis
- Description
- Digital holography microscopy, Phase unwrapping, Deep learning, Generative adversarial network.
- Table Of Contents
-
Ⅰ. INTRODUCTION 1
1.1 Introduction 1
1.2 Related works 5
Ⅱ. Digital holographic microscopy 6
2.1 Label-free off-axis digital holographic imaging 6
Ⅲ. Method 9
3.1 Generation of dataset 9
3.2 Model Architecture 11
3.3 Objective function 13
3.4 Implementation Details 13
Ⅳ. Results 14
4.1 Experimental results 14
4.2 Performance of model for cells of the same and different type as training data 14
4.3 Performance of wrapped phase images with unfocused cells 15
4.4 Unwrapping time with QG, LS, TIE and the proposed model 17
Ⅴ. DISCUSSION AND CONCLUSION 18
5.1 Conclusion 18
Ⅵ. Acknowledgment 18
- URI
-
http://dgist.dcollection.net/common/orgView/200000285033
http://hdl.handle.net/20.500.11750/11976
- Degree
- Master
- Department
- Robotics Engineering
- Publisher
- DGIST
- Related Researcher
-
-
Moon, Inkyu
- Research Interests 지능형 영상시스템; AI기반 영상분석; AI기반 암호시스템; Intelligent Imaging Systems; AI-based Image Analysis; AI-based Cryptosystems & Cryptanalysis
-
- Files in This Item:
-
There are no files associated with this item.
- Appears in Collections:
- Department of Robotics and Mechatronics Engineering Theses Master
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.