inPHASENet: convolutional neural network for high space-bandwidth product single-fringe-pattern phase imaging

Maria Cywińska; Krzysztof Patorski; Maciej Trusiak

doi:10.1117/12.3007913

13 March 2024 inPHASENet: convolutional neural network for high space-bandwidth product single-fringe-pattern phase imaging

Maria Cywińska, Krzysztof Patorski, Maciej Trusiak

Author Affiliations +

Proceedings Volume PC12852, Quantitative Phase Imaging X; PC128521O (2024) https://doi.org/10.1117/12.3007913
Event: SPIE BiOS, 2024, San Francisco, California, United States

Conference Poster

Abstract

Quantitative phase imaging is the representative of state-of-the-art marker-free full-field optical metrology techniques. The inPhaseNet is a phase demodulation algorithmic solution, where convolutional neural network was used for the quadrature function (input fringe pattern shifted in phase by π/2) retrieval. Having both neural network input and output data phase function is calculated via arctangent function. Since phase demodulation consists a very important part in a measurement process its algorithm imposes one of the main limitations of the entire QPI unit. Phase decoding results are favorably compared with reference algorithms, i.e., classical Variational Hilbert Quantitative Phase Imaging, the Hilbert-Huang and Fourier transforms.

Citation Download Citation

Maria Cywińska, Krzysztof Patorski, and Maciej Trusiak "inPHASENet: convolutional neural network for high space-bandwidth product single-fringe-pattern phase imaging", Proc. SPIE PC12852, Quantitative Phase Imaging X, PC128521O (13 March 2024); https://doi.org/10.1117/12.3007913

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