GLOW-DL: Generalized light-optimized workflow with deep learning for contamination detection using fluorescence imaging in variable conditions

Authors: ALIEE, MAHSA - North Dakota State University; GORJI, HAMED - Safetyspect Inc; VASEFI, FARTASH - Safetyspect Inc; YAGGI, KAYLEE - Safetyspect Inc; Qin, Jianwei; Baek, Insuck; Kim, Moon; Chan, Diane; JOHNSON, MICHAEL - Collaborator; DOWNS, ZACHARY - Collaborator; MARATEB, HAMID - Safetyspect Inc; TAVAKOLIAN, KOUHYAR - North Dakota State University; LIANG, BO - North Dakota State University

Submitted to: Journal of Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/11/2025
Publication Date: 5/5/2025
Citation: Aliee, M., Gorji, H.T., Vasefi, F., Yaggi, K., Qin, J., Baek, I., Kim, M.S., Chan, D.E., Johnson, M., Downs, Z., Marateb, H.R., Tavakolian, K., Liang, B. 2025. GLOW-DL: Generalized light-optimized workflow with deep learning for contamination detection using fluorescence imaging in variable conditions . Journal of Biosystems Engineering. 50:240-254. https://doi.org/10.1007/s42853-025-00262-3.
DOI: https://doi.org/10.1007/s42853-025-00262-3

Interpretive Summary: Surface contamination in the food service industry can pose food safety risks for consumers. Traditional inspection methods, such as visual inspection, often cannot consistently detect various types of contaminants, especially those invisible to the naked eye. This study aimed to improve a contamination sanitization inspection (CSI) handheld fluorescence imaging device, which was commercialized based on an ARS patented technology, for detecting surface contamination under different ambient light conditions. Based on imaging experiments for olive oil and peanut butter residues on a dark gray plastic cutting board under both low and high ambient light conditions, we optimized key imaging parameters for the CSI device and developed a new background subtraction method that significantly improved fluorescence image contrast of the residues for detecting the contaminants. Results of this study can help enhance the accuracy and reliability of the CSI device for surface contamination detection, which would benefit the food service industry and regulatory agencies in reducing the food safety risks for consumers.

Technical Abstract: Purpose: This study aims to improve fluorescence imaging techniques for detecting surface contamination under various ambient light conditions. The major challenge addressed is the interference from ambient light, which diminishes fluorescence contrast and hinders accurate contaminant detection. Methods and Results: We optimized key imaging parameters, including exposure time, synchronization of pulsed LEDs with camera exposure, and background subtraction. A noise-aware training approach was also applied using the YOLOv8 deep learning model to increase the model’s robustness to real-world noise. Results demonstrated that LED pulse synchronization enhanced image quality by reducing the impact of ambient light and increasing the signal-to-noise ratio by 25%. Extending exposure times from 3 to 21 ms increased fluorescence intensity by 35%, although it introduced a risk of motion blur. A refined background subtraction method significantly improved contrast, with up to a 30% enhancement, particularly under high ambient light levels, while maintaining controlled noise levels that were consistently lower in higher light conditions. Including Gaussian, Poisson, and stripe noise in training datasets substantially increased detection precision from 62.2 to 71.8% in low-noise environments and maintained precision at 60.8% in high-noise conditions. Conclusion: The study confirms that optimized exposure settings, synchronized pulsed illumination, and noise-aware train-ing substantially enhance the accuracy and reliability of fluorescence imaging for contamination detection. These strategies collectively offer a robust solution for improving contamination monitoring in environments with variable and challenging lighting, broadening the practical applications of fluorescence imaging.