Laser & Optoelectronics Progress, Volume. 62, Issue 5, 0530001(2025)
Deep Learning-Based Disordered-Dispersion Miniature Spectrometer
Conventional spectrometers are typically large, costly, and constrained by a trade-off between spectral measurement range and spectral resolution. This paper proposes a disorder-dispersion miniature spectrometer based on deep learning. In the proposed spectrometer, mass-producible frosted glass is utilized as the spectral encoding device, significantly reducing the manufacturing cost. Further, the spectrometer employs an on-chip detection scheme that does not include any optical components. The distance between the ground glass and detector is only 2 mm, remarkably reducing the device size. Additionally, considering the accuracy and speed of spectral reconstruction, this paper presents a deep learning-based spectral reconstruction method. Experimental results indicate that the proposed spectrometer has a spectral resolution of 1.4 nm and spectral detection range of 420?700 nm. Even in noisy environments, the root-mean-square error between the reconstructed and actual spectra is 1.38×10-3, and the reconstruction time for a single spectrum is as low as 16 μs.
Get Citation
Copy Citation Text
Jiajia Wang, Qianqian Mo, Tao Yang. Deep Learning-Based Disordered-Dispersion Miniature Spectrometer[J]. Laser & Optoelectronics Progress, 2025, 62(5): 0530001
Category: Spectroscopy
Received: May. 20, 2024
Accepted: Jun. 27, 2024
Published Online: Feb. 21, 2025
The Author Email:
CSTR:32186.14.LOP241318