Bhatti David S, Lee Jioh, Kim Cheolsun, Choi Youngin, Yoon Hoon Hahn, Lee Heung-No
Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, 61005, Republic of Korea.
Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, Gwangju, 61005, Republic of Korea.
Sci Rep. 2025 Jul 1;15(1):21232. doi: 10.1038/s41598-025-06691-6.
Computational spectrometers hold significant potential for mobile applications, such as on-site detection and self-diagnosis, due to their compact size, fast operation time, high resolution, wide working range, and low-cost production. Although extensively studied, prior demonstrations have been confined to a few examples of straightforward spectra. This study demonstrates a deep learning (DL)-based single-shot computational spectrometer capable of recovering narrow and broad spectra using a multilayer thin-film filter array. Our device can measure spectral intensities of incident light by combining a filter array, fabricated using wafer-level stencil lithography, with a complementary metal-oxide-semiconductor (CMOS) image sensor through a simple attachment. All the intensities were extracted from a monochrome image captured with a single exposure. Our DL architecture, comprising a dense layer and a U-Net backbone with residual connections, was employed for spectrum reconstruction. The measured intensities were input into the DL architecture to reconstruct the spectra. We collected 3,223 spectra, encompassing both broad and narrow spectra, using color filters and a monochromator to train and evaluate the proposed model. We reconstructed 323 test spectra, achieving an average root mean squared error of 0.0288 over a wavelength range from 500 to 850 nm with a 1 nm spacing. Additionally, the proposed multilayer thin-film filters were validated through scanning electron microscope (SEM) analysis, which confirmed uniform layer deposition and a high fabrication yield. Our computational spectrometer boasts a compact design, a rapid measurement time, a high reconstruction accuracy, a broad spectral range, and CMOS compatibility, making it well-suited for commercialization.
由于其紧凑的尺寸、快速的操作时间、高分辨率、宽工作范围和低成本生产，计算光谱仪在移动应用（如现场检测和自我诊断）方面具有巨大潜力。尽管已经进行了广泛的研究，但先前的演示仅限于一些简单光谱的示例。本研究展示了一种基于深度学习（DL）的单次计算光谱仪，它能够使用多层薄膜滤波器阵列恢复窄光谱和宽光谱。我们的设备可以通过将使用晶圆级模板光刻制造的滤波器阵列与互补金属氧化物半导体（CMOS）图像传感器通过简单连接相结合，来测量入射光的光谱强度。所有强度均从单次曝光拍摄的单色图像中提取。我们采用了一种由密集层和带有残差连接的U-Net主干组成的深度学习架构进行光谱重建。将测量的强度输入到深度学习架构中以重建光谱。我们使用彩色滤光片和单色仪收集了3223个光谱，包括宽光谱和窄光谱，以训练和评估所提出的模型。我们重建了323个测试光谱，在500至850nm波长范围内，间隔为1nm，平均均方根误差为0.0288。此外，通过扫描电子显微镜（SEM）分析对所提出的多层薄膜滤波器进行了验证，这证实了均匀的层沉积和高制造良率。我们的计算光谱仪具有紧凑的设计、快速的测量时间、高重建精度、宽光谱范围和CMOS兼容性，非常适合商业化。
