Abstract

The imaging process of terahertz in-line digital holography is susceptible to environmental interference, and it is difficult to obtain high-quality images and image segmentation results. The challenge can be better handled by using the region of interest (ROI) condition to improve the image quality of the object region and reduce the interference of peripheral noise. In this paper, for two-dimensional 2.52 THz in-line digital holography, a method to add a variety of real backgrounds in the simulation scene is proposed, and through this method, a sufficient amount of close-to-real-scene images are produced to train the YOLOv5 model. The object ROI is extracted by the YOLOv5 model (YOLOv5-ROI). Based on the region, a new, to the best of our knowledge, support-domain-constrained phase retrieval algorithm (YOLOv5-ROI-SPRA) and an image segmentation method combined with the Otsu method (YOLOv5-ROI-Otsu) are proposed, respectively. The better results show that the expected purpose is achieved.

© 2023 Optica Publishing Group

Support-domain constrained phase retrieval algorithms in terahertz in-line digital holography reconstruction of a nonisolated amplitude object

Jiaqi Hu, Qi Li, and Yi Zhou
Appl. Opt. 55(2) 379-386 (2016)

A visual defect detection for optics lens based on the YOLOv5 -C3CA-SPPF network model

Haiyang Tang, Shan Liang, Dan Yao, and Yongjie Qiao
Opt. Express 31(2) 2628-2643 (2023)

Research on object-plane constraints and hologram expansion in phase retrieval algorithms for continuous-wave terahertz inline digital holography reconstruction

Jiaqi Hu, Qi Li, and Shanshan Cui
Appl. Opt. 53(30) 7112-7119 (2014)

Deep learning based coherence holography reconstruction of 3D objects

Quang Trieu and George Nehmetallah
Appl. Opt. 63(7) B1-B15 (2024)

Field recovery from digital inline holographic images of composite propellant combustion base on denoising diffusion model

Geng Xu, Bingning Jin, Siying Yang, and Peijin Liu
Opt. Express 31(23) 38216-38227 (2023)