Fourier ptychography: effectiveness of image classification

Hongbo Zhang; Lin Wang; WenJing Zhou; ZhiJuan Hu; Peter W. M. Tsang; Ting-Chung Poon

doi:10.1117/12.2548097

16 October 2019 Fourier ptychography: effectiveness of image classification

Hongbo Zhang, Lin Wang, WenJing Zhou, ZhiJuan Hu, Peter W. M. Tsang, Ting-Chung Poon

Proceedings Volume 11205, Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019); 112050G (2019) https://doi.org/10.1117/12.2548097
Event: Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019), 2019, Phuket, Thailand

Abstract

In this research, we systematically investigated the image classification accuracy of Fourier Ptychography Microscopy (FPM). Multiple linear regression of image classification accuracy (dependent variable), PSNR and SSIM (independent variables) was performed. Notebly, results show that PSNR, SSIM, and image classification accuracy has a linear relationship. It is therefore feasible to predict the image classification accuracy only based on PSNR and SSIM. It is also found that image classification accuracy of the FPM is not universally significantly differed from the lower resolution image under the higher numerical aperture (NA) condition. The difference is yet much more pronounced under the lower NA condition.

Citation Download Citation

Hongbo Zhang, Lin Wang, WenJing Zhou, ZhiJuan Hu, Peter W. M. Tsang, and Ting-Chung Poon "Fourier ptychography: effectiveness of image classification", Proc. SPIE 11205, Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019), 112050G (16 October 2019); https://doi.org/10.1117/12.2548097

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