Quality evaluation of speckle-noise-contaminated computer-generated holograms by using deep neural network

Kyosik Min; Jae-Hyeung Park

doi:10.1117/12.3000279

13 March 2024 Quality evaluation of speckle-noise-contaminated computer-generated holograms by using deep neural network

Kyosik Min, Jae-Hyeung Park

Author Affiliations +

Proceedings Volume 12910, Practical Holography XXXVIII: Displays, Materials, and Applications; 1291003 (2024) https://doi.org/10.1117/12.3000279
Event: SPIE OPTO, 2024, San Francisco, California, United States

Abstract

Computer-generated hologram (CGH) techniques have advanced in the field of display technology, capable of reproducing three-dimensional images. The reconstructed three-dimensional images of the CGHs, however, usually contain speckle noises due to random phase distribution applied in the CGH synthesis. The random distribution of the speckle noise makes the traditional metrics like peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM), which are generally used in image quality evaluation, become less reliable. In this paper, we propose a novel method to evaluate the speckled CGHs using a deep neural network.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Kyosik Min and Jae-Hyeung Park "Quality evaluation of speckle-noise-contaminated computer-generated holograms by using deep neural network", Proc. SPIE 12910, Practical Holography XXXVIII: Displays, Materials, and Applications, 1291003 (13 March 2024); https://doi.org/10.1117/12.3000279

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available