Toward a domain-specific heuristic knowledge based spectrum reconstruction method for multispectral camera with CMOS Fabry-Perot interferometer

Anna Zhao; Shuyang Liu; Chen Zhang; Tao Zhao; Xiaodong Jia

doi:10.1117/12.2505592

12 December 2018 Toward a domain-specific heuristic knowledge based spectrum reconstruction method for multispectral camera with CMOS Fabry-Perot interferometer

Anna Zhao, Shuyang Liu, Chen Zhang, Tao Zhao, Xiaodong Jia

Author Affiliations +

Proceedings Volume 10846, Optical Sensing and Imaging Technologies and Applications; 108462U (2018) https://doi.org/10.1117/12.2505592
Event: International Symposium on Optoelectronic Technology and Application 2018, 2018, Beijing, China

Abstract

Multispectral imaging technology is an advanced imaging method to acquire both spatial and spectral information in the image. Miniaturized spectral imaging system based on CMOS sensors integrated with Fabry-Perot interferometer makes it convenience for people to get the multispectral image outdoor because of the low-cost, high speed, especially compact size. However, the parasitic effects of the system makes the spectrum deviating from the ideal, applications for classification and recognition based on spectral information are limited. Hence, spectrum reconstruction method is applied to calibrate objects toward domain-specific with priori knowledge. And the experiment with test samples independent of the training data shows that, the MSE improves more than 20% compared with the raw data measured by the multispectral camera.

Citation Download Citation

Anna Zhao, Shuyang Liu, Chen Zhang, Tao Zhao, and Xiaodong Jia "Toward a domain-specific heuristic knowledge based spectrum reconstruction method for multispectral camera with CMOS Fabry-Perot interferometer ", Proc. SPIE 10846, Optical Sensing and Imaging Technologies and Applications, 108462U (12 December 2018); https://doi.org/10.1117/12.2505592

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