Presentation
20 May 2022 Multispectral image reconstruction with neural networks for minimally invasive 3D lensless fiber endoscopy using a diffuser
Tom Glosemeyer, Yazhi Zheng, Julian Lich, Robert Kuschmierz, Jürgen Czarske
Author Affiliations +
Abstract
Endoscopy through coherent fiber bundles plays a significant role in industrial and medical imaging. By using a diffractive optical element in form of a diffuser on the distal side, the information of the measurement volume is encoded as 2D speckle patterns on the camera. This allows minimally invasive single-shot 3D imaging through a flexible low-cost endoscope with a diameter of less than 1 mm. Neural networks are employed to get fast image reconstructions from the speckle patterns with high quality. Moreover, multispectral speckle coding is used to increase the amount of transferred information and thus improving imaging capabilities.
Conference Presentation
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tom Glosemeyer, Yazhi Zheng, Julian Lich, Robert Kuschmierz, and Jürgen Czarske "Multispectral image reconstruction with neural networks for minimally invasive 3D lensless fiber endoscopy using a diffuser", Proc. SPIE PC12136, Unconventional Optical Imaging III, PC121360A (20 May 2022); https://doi.org/10.1117/12.2621196
Advertisement
Advertisement
KEYWORDS
Diffusers

Endoscopy

Neural networks

Image restoration

3D image processing

Multispectral imaging

3D metrology

Back to Top