Fourier Ptychography: Effectiveness of Image Classification

被引：2

作者：

Zhang, Hongbo ^{[1
]}

Wang, Lin ^{[2
]}

Zhou, WenJing ^{[3
]}

Hu, ZhiJuan ^{[4
]}

Tsang, Peter W. M. ^{[5
]}

Poon, Ting-Chung ^{[6
]}

机构：

[1] Virginia Mil Inst, Dept Comp & Informat Sci, Lexington, VA 24450 USA

[2] Nanjing Univ Sci & Technol, Sch Elect & Opt Engn, Nanjing, Jiangsu, Peoples R China

[3] Shanghai Univ, Dept Precis Mech Engn, Shanghai, Peoples R China

[4] Shanghai Normal Univ, Math & Sci Coll, Shanghai, Peoples R China

[5] City Univ Hongkong, Dept Eleectron Engn, Kowloon, 83 Tat Chee Ave, Hong Kong, Peoples R China

[6] Virginia Tech, Bradley Dept Elect & Comp Engn, Blacksburg, VA 24061 USA

来源：

SEVENTH INTERNATIONAL CONFERENCE ON OPTICAL AND PHOTONIC ENGINEERING (ICOPEN 2019) | 2019年 / 11205卷

关键词：

Fourier Ptychography; Image Classification; INTENSITY; TRANSPORT;

D O I：

10.1117/12.2548097

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

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.

引用

页数：8

共 19 条

[1]

[Anonymous], ARXIV180303434

[2] MRI Tumor Segmentation with Densely Connected 3D CNN [J].

Chen, Lele ;

Wu, Yue ;

DSouza, Adora M. ;

Abidin, Anas Z. ;

Wismueller, Axel ;

Xu, Chenliang .

MEDICAL IMAGING 2018: IMAGE PROCESSING, 2018, 10574

[3]

Goyal P., 2017, CoRR

[4] Fourier Ptychography for Brightfield, Phase, Darkfield, Reflective, Multi-Slice, and Fluorescence Imaging [J].

Guo, Kaikai ;

Dong, Siyuan ;

Zheng, Guoan .

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, 2016, 22 (04) :77-88

[5]

He K., 2016, CVPR, DOI [10.1109/CVPR.2016.90, DOI 10.1109/CVPR.2016.90]

[6] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[7]

Nguyen T., 2018, Imaging Systems and Applications, pJTh3A

[8] Single-shot quantitative phase microscopy based on color-multiplexed Fourier ptychography [J].

Sun, Jiasong ;

Chen, Qian ;

Zhang, Jialin ;

Fan, Yao ;

Zuo, Chao .

OPTICS LETTERS, 2018, 43 (14) :3365-3368

[9] High-speed Fourier ptychographic microscopy based on programmable annular illuminations [J].

Sun, Jiasong ;

Zuo, Chao ;

Zhang, Jialin ;

Fan, Yao ;

Chen, Qian .

SCIENTIFIC REPORTS, 2018, 8

[10] Deep learning approach to Fourier ptychographic microscopy [J].

Thanh Nguyen ;

Xue, Yujia ;

Li, Yunzhe ;

Tian, Lei ;

Nehmetallah, George .

OPTICS EXPRESS, 2018, 26 (20) :26470-26484

← 1 2 →