Search

The food service industry must ensure that service facilities are free of foodborne pathogens hosted by organic residues and biofilms. Foodborne diseases put customers at risk and compromise the reputations of service providers. Fluorescence imaging, empowered by state-of-the-art artificial intelligence (AI) algorithms, can detect invisible residues. However, using AI requires large datasets that are most effective when collected from actual users, raising concerns about data privacy and possible leakage of sensitive information. In this study, we employed a decentralized privacy-preserving technology to address client data privacy issues. When federated learning (FL) is used, there is no need for data sharing across clients or data centralization on a server. We used FL and a new fluorescence imaging technology and applied two deep learning models, MobileNetv3 and DeepLabv3+, to identify and segment invisible residues on food preparation equipment and surfaces. We used FedML as our FL framework and Fedavg as the aggregation algorithm. The model achieved training and testing accuracies of 95.83% and 94.94% for classification between clean and contamination frames, respectively, and resulted in intersection over union (IoU) scores of 91.23% and 89.45% for training and testing, respectively, of segmentation of the contaminated areas. The results demonstrated that using federated learning combined with fluorescence imaging and deep learning algorithms can improve the performance of cleanliness auditing systems while assuring client data privacy.

Ginseng is a perennial herbaceous plant that has been widely consumed for medicinal and dietary purposes since ancient times. Ginseng plants require shade and cool temperatures for better growth; climate warming and rising heat waves have a negative impact on the plants’ productivity and yield quality. Since Republic of Korea’s temperature is increasing beyond normal expectations and is seriously threatening ginseng plants, an early-stage non-destructive diagnosis of stressed ginseng plants is essential before symptomatic manifestation to produce high-quality ginseng roots. This study demonstrated the potential of fluorescence hyperspectral imaging to achieve the early high-throughput detection and prediction of chlorophyll composition in four varieties of heat-stressed ginseng plants: Chunpoong, Jakyeong, Sunil, and Sunmyoung. Hyperspectral imaging data of 80 plants from these four varieties (temperature-sensitive and temperature-resistant) were acquired before and after exposing the plants to heat stress. Additionally, a SPAD-502 meter was used for the non-destructive measurement of the greenness level. In accordance, the mean spectral data of each leaf were extracted from the region of interest (ROI). Analysis of variance (ANOVA) was applied for the discrimination of heat-stressed plants, which was performed with 96% accuracy. Accordingly, the extracted spectral data were used to develop a partial least squares regression (PLSR) model combined with multiple preprocessing techniques for predicting greenness composition in ginseng plants that significantly correlates with chlorophyll concentration. The results obtained from PLSR analysis demonstrated higher determination coefficients of R2val = 0.90, and a root mean square error (RMSE) of 3.59%. Furthermore, five proposed bands (683 nm, 688 nm, 703 nm, 731 nm, and 745 nm) by stepwise regression (SR) were developed into a PLSR model, and the model coefficients were used to create a greenness-level concentration in images that showed differences between the control and heat-stressed plants for all varieties.

Ginseng is an important medicinal plant in Korea. The roots of the ginseng plant have medicinal properties; thus, it is very important to maintain the quality of ginseng roots. Root rot disease is a major disease that affects the quality of ginseng roots. It is important to predict this disease before it causes severe damage to the plants. Hence, there is a need for a non-destructive method to identify root rot disease in ginseng plants. In this paper, a method to identify the root rot disease by analyzing the RGB plant images using image processing and deep learning is proposed. Initially, plant segmentation is performed, and then the noise regions are removed in the plant images. These images are given as input to the proposed linear deep learning model to identify root rot disease in ginseng plants. Transfer learning models are also applied to these images. The performance of the proposed method is promising in identifying root rot disease.

Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to collect images in multiple wavelengths. This paper proposes a new methodology to support the design of a hypothesized system that uses three imaging modes—fluorescence, visible/near-infrared (VNIR) reflectance, and shortwave infrared (SWIR) reflectance—to capture narrow-band spectral data at only three to seven narrow wavelengths. Simulated annealing is applied to identify the optimal wavelengths for sparse spectral measurement with a cost function based on the accuracy provided by a weighted k-nearest neighbors (WKNN) classifier, a common and relatively robust machine learning classifier. Two separate classification approaches are presented, the first using a multi-layer perceptron (MLP) artificial neural network trained on sparse data from the three individual spectra and the second using a fusion of the data from all three spectra. The results are compared with those from four alternative classifiers based on common machine learning algorithms. To validate the proposed methodology, reflectance and fluorescence spectra in these three spectroscopic modes were collected from fish fillets and used to classify the fillets by species. Accuracies determined from the two classification approaches are compared with benchmark values derived by training the classifiers with the full resolution spectral data. The results of the single-layer classification study show accuracies ranging from ~68% for SWIR reflectance to ~90% for fluorescence with just seven wavelengths. The results of the fusion classification study show accuracies of about 95% with seven wavelengths and more than 90% even with just three wavelengths. Reducing the number of required wavelengths facilitates the creation of rapid and cost-effective spectral imaging systems that can be used for widespread analysis in food monitoring/food fraud, agricultural, and biomedical applications.

Excessive addition of food waste fertilizer to organic fertilizer (OF) is forbidden in the Republic of Korea because of high sodium chloride and capsaicin concentrations in Korean food. Thus, rapid and nondestructive evaluation techniques are required. The objective of this study is to quantitatively evaluate food-waste components (FWCs) using hyperspectral imaging (HSI) in the visible–near-infrared (Vis/NIR) region. A HSI system for evaluating fertilizer components and prediction algorithms based on partial least squares (PLS) analysis and least squares support vector machines (LS-SVM) are developed. PLS and LS-SVM preprocessing methods are employed and compared to select the optimal of two chemometrics methods. Finally, distribution maps visualized using the LS-SVM model are created to interpret the dynamic changes in the OF FWCs with increasing FWC concentration. The developed model quantitively evaluates the OF FWCs with a coefficient of determination of 0.83 between the predicted and actual values. The developed Vis/NIR HIS system and optimized model exhibit high potential for OF FWC discrimination and quantitative evaluation.

With increasing public demand for ready-to-eat fresh-cut food products, proper sanitation of food-processing equipment surfaces is essential to mitigate potential contamination of these products to ensure safe consumption. This study presents a sanitation monitoring technique using hyperspectral fluorescence images to detect fruit residues on food-processing equipment surfaces. An algorithm to detect residues on the surfaces of 2B-finished and #4-finished stainless-steel, both commonly used in food processing equipment, was developed. Honeydew, orange, apple, and watermelon were selected as representatives since they are mainly used as fresh-cut fruits. Hyperspectral fluorescence images were obtained for stainless steel sheets to which droplets of selected fruit juices at six concentrations were applied and allowed to dry. The most significant wavelengths for detecting juice at each concentration were selected through ANOVA analysis. Algorithms using a single waveband and using a ratio of two wavebands were developed for each sample and for all the samples combined. Results showed that detection accuracies were better for the samples with higher concentrations. The integrated algorithm had a detection accuracy of 100% and above 95%, respectively, for the original juice up to the 1:20 diluted samples and for the more dilute 1:50 to 1:100 samples, respectively. The results of this study establish that using hyperspectral imaging, even a small residual quantity that may exist on the surface of food processing equipment can be detected and that sanitation monitoring and management is possible.

Geographical origin discrimination of white rice is an important endeavor in preventing illegal distribution of white rice and regulating and standardizing food safety and quality assurance. The aim of this study was to develop a method for geographical origin discrimination between South Korean and Chinese rice using a hyperspectral fluorescence imaging technique and multivariate analysis. Hyperspectral fluorescence images of South Korean and Chinese rice samples were obtained in the wavelength range of 420 nm to 780 nm with intervals of 4.8 nm using 365 nm wavelength ultraviolet-A excitation light. Partial least squares discriminant analysis models were developed and applied to the acquired image to determine the geographical origins of the rice samples. In addition, various pre-processing techniques were applied to improve the discrimination accuracy. Accordingly, the pixel size of the hyperspectral image was determined. The results revealed that the optimum pixel size of the hyperspectral image that was above 7 mm × 7 mm showed a high discrimination accuracy. Moreover, the geographical origin discrimination model that applied the first-order derivative achieved a high discrimination accuracy of 98.89%. The results of this study showed that hyperspectral fluorescence imaging technology can be used to quickly and accurately discriminate the geographical origins of white rice.

The inspection of rice grain that may be infected by seedborne disease is important for ensuring uniform plant stands in production fields as well as preventing proliferation of some seedborne diseases. The goal of this study was to use a hyperspectral imaging (HSI) technique to find optimal wavelengths and develop a model for detecting discolored, diseased rice seed infected by bacterial panicle blight (Burkholderia glumae), a seedborne pathogen. For this purpose, the HSI data spanning the visible/near-infrared wavelength region between 400 and 1000 nm were collected for 500 sound and discolored rice seeds. For selecting optimal wavelengths to use for detecting diseased seed, a sequential forward selection (SFS) method combined with various spectral pretreatments was employed. To evaluate performance based on optimal wavelengths, support vector machine (SVM) and linear and quadratic discriminant analysis (LDA and QDA) models were developed for detection of discolored seeds. As a result, the violet and red regions of the visible spectrum were selected as key wavelengths reflecting the characteristics of the discolored rice seeds. When using only two or only three selected wavelengths, all of the classification methods achieved high classification accuracies over 90% for both the calibration and validation sample sets. The results of the study showed that only two to three wavelengths are needed to differentiate between discolored, diseased and sound rice, instead of using the entire HSI wavelength regions. This demonstrates the feasibility of developing a low cost multispectral imaging technology based on these selected wavelengths for non-destructive and high-throughput screening of diseased rice seed.