3D deformation measurement in digital holographic interferometry using a multitask deep learning architecture

Vengala, KS and Paluru, N and Gorthi, RKSS (2022) 3D deformation measurement in digital holographic interferometry using a multitask deep learning architecture. In: Journal of the Optical Society of America A: Optics and Image Science, and Vision, 39 (1). pp. 167-176.

PDF jou_opt_soc_ame_a_39-01_167-176_2022.pdf - Published Version Restricted to Registered users only Download (22MB) | Request a copy

Abstract

The extraction of absolute phase from an interference pattern is a key step for 3D deformation measurement in digital holographic interferometry (DHI) and is an ill-posed problem. Estimating the absolute unwrapped phase becomes even more challenging when the obtained wrapped phase from the interference pattern is noisy. In this paper, we propose a novel multitask deep learning approach for phase reconstruction and 3D deformation measurement in DHI, referred to asTriNet, that has the capability to learn and performtwo parallel tasks fromthe input image. The proposed TriNet has a pyramidal encoder-two-decoder framework for multi-scale information fusion. To our knowledge,TriNet is the first multitask approach to accomplish simultaneous denoising and phase unwrapping of the wrapped phase from the interference fringes in a single step for absolute phase reconstruction. The proposed architecture is more elegant than recent multitask learning methods such as Y-Net and state-of-the-art segmentation approaches such asUNet++. Further, performing denoising and phase unwrapping simultaneously enables deformation measurement from the highly noisy wrapped phase of DHI data. The simulations and experimental comparisons demonstrate the efficacy of the proposed approach in absolute phase reconstruction and 3D deformation measurement with respect to the existing conventional methods and state-of-the-art deep learning methods. © 2021 Optica Publishing Group.

Item Type:	Journal Article
Publication:	Journal of the Optical Society of America A: Optics and Image Science, and Vision
Publisher:	The Optical Society
Additional Information:	The copyright for this article belongs to The Optical Society.
Keywords:	Deep learning; E-learning; Holographic interferometry; Image reconstruction, 3D deformation measurements; Absolute phase; De-noising; Digital holographic interferometry; Interference patterns; Learning architectures; Phase reconstruction; Phase-unwrapping; State of the art; Wrapped phase, Deformation
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	07 Jan 2022 07:01
Last Modified:	07 Jan 2022 07:01
URI:	http://eprints.iisc.ac.in/id/eprint/70920

Actions (login required)

View Item