Hyperspectral Determination of Fluorescence Wavebands for Multispectral Imaging Detection of Multiple Animal Fecal Species Contaminations on Romaine Lettuce

Cho, Hyun-Jeong; Kim, Moon S.; Kim, Sung-Youn; Lee, Hoonsoo; Oh, Mirae; Chung, Soo Hyun

doi:10.1007/s11947-017-2032-y

Cited by 13 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such algorithms are prone to error because they are sensitive to ambient light intensity, and determining an appropriate thresholding level can be challenging. In real-world situations, the presence of other objects with similar pixel intensity in the background can also lead to false positives 18 , 20 , 37 , 38 .…”

Section: Methodsmentioning

confidence: 99%

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Gorji

Shahabi

Sharma

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

show abstract

Section: Methodsmentioning

confidence: 99%

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Gorji

Shahabi

Sharma

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Table 3 summarizes some important works on fecal contamination detection on horticultural products. Citrus Gómez-Sanchis et al (2008a Fluorescence Fecal contamination Apple Kim et al (2002Kim et al ( , 2005Kim et al ( , 2007Kim et al ( , 2008; Lefcourt et al (2003Lefcourt et al ( , 2006a Apple Kim et al (2001bKim et al ( , 2007Kim et al ( , 2008; Lefcout et al (2006b) Reflectance and transmittance Insect infestation Cucumber Lu and Ariana (2013) Recent efforts have been devoted to detecting fecal contamination on leafy greens using hyperspectral fluorescence imaging (Cho et al, 2018;Everard et al, 2016;Everard et al, 2014;Kang et al, 2011).…”

Section: Food Safety Inspectionmentioning

confidence: 99%

“…It was hence suggested to image leaves before the onset of leaf deterioration (Everard et al, 2016). Cho et al (2018) reported on the detection of four species of varied dilutions of animal feces on romaine lettuce (Cho et al, 2018), as illustrated in Figure 10. It was shown that species-specific detection after illumination with violet LED excitation light required different filters corresponding to the fluorescence emission wavelengths.…”

Section: Food Safety Inspectionmentioning

confidence: 99%

Hyperspectral imaging technology for quality and safety evaluation of horticultural products: A review and celebration of the past 20-year progress

Saeys

Kim

et al. 2020

Postharvest Biology and Technology

165

View full text Add to dashboard Cite

In the past 20 years, hyperspectral imaging has been widely investigated as an emerging, promising technology for evaluating quality and safety of horticultural products. This technology has originated from remote sensing and joins the domains of machine vision and point spectroscopy to provide superior image segmentation for the detection of defects and contaminations, and to map the chemical composition. Thanks to the advancements in instrumentation and data analysis in the past two decades, hyperspectral imaging technology has evolved into a powerful nondestructive inspection tool and the scope of applications in postharvest quality and safety evaluation has expanded tremendously. In this article, different imaging modes (reflectance, transmittance, fluorescence and Raman) and their combinations, and the potential for real-time acquisition of hyperspectral images at industry relevant speeds are first discussed in terms of their advantages and disadvantages. Next reviewed are different data processing/analysis methods and associated steps from data pre-processing over the spectral and spatial domains to the actual model building and performance evaluation. An overview is then given of hyperspectral imaging applications for external quality and defect evaluation, internal quality and maturity assessment, and food safety detection of 2 horticultural products. Finally, a brief discussion is presented on the challenges and opportunities in future development and application of hyperspectral imaging technology in food quality and safety evaluation of horticultural products.

show abstract

“…Currently, one of the tools assessed to detect fecal contamination in fresh produce in the growing fields is hyperspectral imaging. Cho et al evaluated this technique for the on-site detection of fecal contamination in romaine lettuce, with positive results [ 132 ]. Until more detailed and complete information on this topic becomes available, a conservative approach is likely to be taken by the competent authorities and by supply-chain stakeholders to avoid outbreaks and the subsequent consequences on public health and the agrifood sector [ 133 , 134 ].…”

Section: Approaches Strategies and Solutions To Solve Conflicts Between Fresh Produce Microbial Safety And Environmental Sustainabilitymentioning

confidence: 99%

Interactions between Microbial Food Safety and Environmental Sustainability in the Fresh Produce Supply Chain

López‐Gálvez

Gómez

Artés

et al. 2021

Foods

View full text Add to dashboard Cite

Improving the environmental sustainability of the food supply chain will help to achieve the United Nations Sustainable Development Goals (SDGs). This environmental sustainability is related to different SDGs, but mainly to SDG 2 (Zero Hunger), SDG 12 (Responsible Production and Consumption), SDG 13 (Climate Action), and SDG 15 (Life on Land). The strategies and measures used to improve this aspect of the food supply chain must remain in balance with other sustainability aspects (economic and social). In this framework, the interactions and possible conflicts between food supply chain safety and sustainability need to be assessed. Although priority must be given to safety aspects, food safety policies should be calibrated in order to avoid unnecessary deleterious effects on the environment. In the present review, a number of potential tensions and/or disagreements between the microbial safety and environmental sustainability of the fresh produce supply chain are identified and discussed. The addressed issues are spread throughout the food supply chain, from primary production to the end-of-life of the products, and also include the handling and processing industry, retailers, and consumers. Interactions of fresh produce microbial safety with topics such as food waste, supply chain structure, climate change, and use of resources have been covered. Finally, approaches and strategies that will prove useful to solve or mitigate the potential contradictions between fresh produce safety and sustainability are described and discussed. Upon analyzing the interplay between microbial safety and the environmental sustainability of the fresh produce supply chain, it becomes clear that decisions that are taken to ensure fresh produce safety must consider the possible effects on environmental, economic, and social sustainability aspects. To manage these interactions, a global approach considering the interconnections between human activities, animals, and the environment will be required.

show abstract

Hyperspectral Determination of Fluorescence Wavebands for Multispectral Imaging Detection of Multiple Animal Fecal Species Contaminations on Romaine Lettuce

Cited by 13 publications

References 33 publications

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses

Hyperspectral imaging technology for quality and safety evaluation of horticultural products: A review and celebration of the past 20-year progress

Interactions between Microbial Food Safety and Environmental Sustainability in the Fresh Produce Supply Chain

Contact Info

Product

Resources

About