Innovations in seafood freshness quality: Non-destructive detection of freshness in Litopenaeus vannamei using the YOLO-shrimp model.

The relationship between freshness changes and visual images of Litopenaeus vannamei was established based on Sensory Evaluation, Total Volatile Base Nitrogen (TVB-N), Total Viable Count (TVC), and Gray Value during storage at 4 °C. A non-destructive detection system using the advanced YOLO(You Only Look Once)-Shrimp model was developed to evaluate shrimp freshness. The results revealed a gradual increase in freshness indices over time, with the gray value showing strong positive correlations with TVB-N and TVC (0.88 and 0.81). The advanced YOLO-Shrimp model demonstrated notable performance enhancements over the YOLOv8 model, as evidenced by a precision increase of 5.07 %, a recall improvement of 1.58 %, a 3.25 % rise in the F1 score, and a 2.84 % elevation in mAP50. This innovative approach offers substantial potential for enhancing food safety and quality control in the seafood industry.

Fast detection of moisture content and freshness for loquats using optical fiber spectroscopy.

Detection of the moisture content (MC) and freshness for loquats is crucial for achieving optimal taste and economic efficiency. Traditional methods for evaluating the MC and freshness of loquats have disadvantages such as destructive sampling and time-consuming. To investigate the feasibility of rapid and non-destructive detection of the MC and freshness for loquats, optical fiber spectroscopy in the range of 200-1000 nm was used in this study. The full spectra were pre-processed using standard normal variate method, and then, the effective wavelengths were selected using competitive adaptive weighting sampling (CARS) and random frog algorithms. Based on the selected effective wavelengths, prediction models for MC were developed using partial least squares regression (PLSR), multiple linear regression, extreme learning machine, and back-propagation neural network. Furthermore, freshness level discrimination models were established using simplified k nearest neighbor, support vector machine (SVM), and partial least squares discriminant analysis. Regarding the prediction models, the CARS-PLSR model performed relatively better than the other models for predicting the MC, with R 2 P and RPD values of 0.84 and 2.51, respectively. Additionally, the CARS-SVM model obtained superior discrimination performance, with 100% accuracy for both calibration and prediction sets. The results demonstrated that optical fiber spectroscopy technology is an effective tool to fast detect the MC and freshness for loquats.

Rapid Detection of Tannin Content in Wine Grapes Using Hyperspectral Technology.

Wine grape quality is influenced by the variety and growing environment, and the quality of the grapes has a significant impact on the quality of the wine. Tannins are a crucial indicator of wine grape quality, and, therefore, rapid and non-destructive methods for detecting tannin content are necessary. This study collected spectral data of Pinot Noir and Chardonnay using a geophysical spectrometer, with a focus on the 500-1800 nm spectrum. The spectra were preprocessed using Savitzky-Golay (SG), first-order differential (1D), standard normal transform (SNV), and their respective combinations. Characteristic bands were extracted through correlation analysis (PCC). Models such as partial least squares (PLS), support vector machine (SVM), random forest (RF), and one-dimensional neural network (1DCNN) were used to model tannin content. The study found that preprocessing the raw spectra improved the models' predictive capacity. The SVM-RF model was the most effective in predicting grape tannin content, with a test set R2 of 0.78, an RMSE of 0.31, and an RE of 10.71%. These results provide a theoretical basis for non-destructive testing of wine grape tannin content.

Non-destructive detection of egg white and yolk morphology transformation and salt content of salted duck eggs in salting by hyperspectral imaging.

Salt content is a crucial indicator of the maturity and internal quality of salted duck eggs (SDEs) during the pickling process. However, there is currently no valid and rapid method available for accurately detecting salt content. In the present study, we utilized hyperspectral imaging to no-destructively determine the salt content in egg yolks, egg whites, and whole eggs during the curing period. Firstly, principal component analysis was applied to explain the characteristics of egg yolk and white morphology transformation of SDEs with different maturities during curing. Secondly, sensitive spectral factors representative of changes in the salt content of SDEs were extracted by three spectral transformations (Savitzky-Golay SG, continuum removal CR, and first-order derivation FD) and three approaches of selecting characteristic wavelengths (successive projection algorithm SPA, uninformative variables elimination UVE and competitive adaptive reweighting sampling algorithm CARS). The results of the PLSR model suggested that the optimal models for predicting salt content in egg yolks, whites, and whole eggs were SG-UVE-PLSR (predicted coefficient of determination Rp2=0.912, predicted standard deviation SEp=0.151, residual prediction deviation RPD = 3.371), CR-CARS-PLSR (Rp2=0.873, SEp=0.862, RPD = 2.806), and CR-UVE-PLSR (Rp2=0.877, SEp=0.680, RPD = 2.851), respectively. Eventually, the optimal prediction model for the salt content of the whole egg was employed to a pixel spectral matrix to calculate the salt content values of pixel points on the hyperspectral image of SDEs. Additionally, pseudo-color techniques were employed to visualize the spatial distribution of predicted salt content. This work will provide a theoretical foundation for rapidly detecting maturity and enabling high-throughput quality sorting of SDEs.

Correcting correlation quality of portable X-ray fluorescence to better map heavy metal contamination by spatial co-kriging interpolation.

High-precision mapping based on portable X-ray fluorescence (PXRF) data is currently being studied extensively; however, owing to poor correlation with soil metal concentration, the original PXRF data directly used for co-kriging interpolation (CKI) cannot accurately map contaminated sites with heterogeneous concentrations. Therefore, this study selected a landfill-contaminated site for research, explored the best correlation mode between PXRF variants and actual heavy metal concentration, analyzed the impact of improving the correlation model on the CKI of the spatial distribution of heavy metals, and explored the most appropriate CKI mode and point density. The results showed the following: (1) After nonlinear transformation, the correlation model between PXRF and the actual concentration was significantly improved, and the correlation coefficients of five heavy metals increased from 0.214-0.232 to 0.936-0.986. (2) The introduction of corrected PXRF data significantly improves the accuracy of CKI. Compared with the original PXRF co-kriging interpolation (OP-CKI), the ME of the corrected PXRF co-kriging interpolation (CP-CKI) for Zn, Pb, and Cu decreased by 78.2 %, 45.5 %, and 65.3 %, respectively. In terms of the spatial distribution of heavy metal pollutant concentrations, CP-CKI effectively improved the influence of local anomalous high-value points on the interpolation accuracy. (3) When the sample density measured by inductively coupled plasma mass spectrometry (ICP-MS) was less than 4 boreholes/hm2, CKI accuracy decreased significantly, indicating that the sample density should not be less than a certain threshold during CKI. (4) When the sample density measured by PXRF exceeded 7 boreholes/hm2, the mean error and root mean square error of CKI continued to decrease, suggesting that the introduction of enough sample density measured by PXRF can effectively improve the accuracy of CKI.

Integrating spectral and image information for prediction of cottonseed vitality.

Cotton plays a significant role in people's lives, and cottonseeds serve as a vital assurance for successful cotton cultivation and production. Premium-quality cottonseeds can significantly enhance the germination rate of cottonseeds, resulting in increased cotton yields. The vitality of cottonseeds is a crucial metric that reflects the quality of the seeds. However, currently, the industry lacks a non-destructive method to directly assess cottonseed vitality without compromising the integrity of the seeds. To address this challenge, this study employed a hyperspectral imaging acquisition system to gather hyperspectral data on cottonseeds. This system enables the simultaneous collection of hyperspectral data from 25 cottonseeds. This study extracted spectral and image information from the hyperspectral data of cottonseeds to predict their vitality. SG, SNV, and MSC methods were utilized to preprocess the spectral data of cottonseeds. Following this preprocessing step, feature wavelength points of the cottonseeds were extracted using SPA and CARS algorithms. Subsequently, GLCM was employed to extract texture features from images corresponding to these feature wavelength points, including attributes such as Contrast, Correlation, Energy, and Entropy. Finally, the vitality of cottonseeds was predicted using PLSR, SVR, and a self-built 1D-CNN model. For spectral data analysis, the 1D-CNN model constructed after MSC+CARS preprocessing demonstrated the highest performance, achieving a test set correlation coefficient of 0.9214 and an RMSE of 0.7017. For image data analysis, the 1D-CNN model constructed after SG+CARS preprocessing outperformed the others, yielding a test set correlation coefficient of 0.8032 and an RMSE of 0.9683. In the case of fused spectral and image data, the 1D-CNN model built after SG+SPA preprocessing displayed the best performance, attaining a test set correlation coefficient of 0.9427 and an RMSE of 0.6872. These findings highlight the effectiveness of the 1D-CNN model and the fusion of spectral and image features for cottonseed vitality prediction. This research contributes significantly to the development of automated detection devices for assessing cottonseed vitality.

Non-destructive detection of protein content in mulberry leaves by using hyperspectral imaging.

Protein content is one of the most important indicators for assessing the quality of mulberry leaves. This work is carried out for the rapid and non-destructive detection of protein content of mulberry leaves using hyperspectral imaging (HSI) (Specim FX10 and FX17, Spectral Imaging Ltd., Oulu, Finland). The spectral range of the HSI acquisition system and data processing methods (pretreatment, feature extraction, and modeling) is compared. Hyperspectral images of three spectral ranges in 400-1,000 nm (Spectral Range I), 900-1,700 nm (Spectral Range II), and 400-1,700 nm (Spectral Range III) were considered. With standard normal variate (SNV), Savitzky-Golay first-order derivation, and multiplicative scatter correction used to preprocess the spectral data, and successive projections algorithm (SPA), competitive adaptive reweighted sampling, and random frog used to extract the characteristic wavelengths, regression models are constructed by using partial least square and least squares-support vector machine (LS-SVM). The protein content distribution of mulberry leaves is visualized based on the best model. The results show that the best results are obtained with the application of the model constructed by combining SNV with SPA and LS-SVM, showing an R 2 of up to 0.93, an RMSE of just 0.71 g/100 g, and an RPD of up to 3.83 based on the HSI acquisition system of 900-1700 nm. The protein content distribution map of mulberry leaves shows that the protein of healthy mulberry leaves distributes evenly among the mesophyll, with less protein content in the vein of the leaves. The above results show that rapid, non-destructive, and high-precision detection of protein content of mulberry leaves can be achieved by applying the SWIR HSI acquisition system combined with the SNV-SPA-LS-SVM algorithm.

Development of effective model for non-destructive detection of defective kiwifruit based on graded lines.

The accurate detection of external defects in kiwifruit is an important part of postharvest quality assessment. Previous studies have not considered the problems posed by the actual grading environment. In this study, we designed a novel approach based on improved Yolov5 to achieve real-time and efficient non-destructive detection of multiple defect categories in kiwifruit. First, a kiwifruit image acquisition device based on grading lines was developed to enhance the image acquisition. Subsequently, a kiwifruit dataset was constructed based on the external defect characteristics and a new data enhancement method was proposed to augment the kiwifruit samples. Thereafter, the SPD-Conv and DW-Conv modules were combined to improve Yolov5s, with EIOU as the loss calculation function. The results demonstrated that the improved model training loss value was 0.013 lower, the convergence was accelerated, the number of parameters was reduced, and the computational effort was increased. The detection accuracies of the samples in the test set, which included healthy, leaf-rubbing damaged, healed cuts or scarred, and sunburned samples, were 98.8%, 98.7%, 97.6%, and 95.9%, respectively, with an overall detection accuracy of 97.7%. The detection time was 8.0 ms, thereby meeting real-time sorting demands. The average detection accuracy and model size of SSD, Yolov5s, Yolov7, and Yolov5-Ours were compared. When the confidence threshold was 0.5, the detection accuracy of Yolov5-Ours was 10% and 6.4% higher than that of SSD and Yolov5s, respectively. In terms of the model size, Yolov5-Ours was approximately 6.5- and 4-fold smaller than SSD and Yolov7, respectively. Thus, Yolov5-Ours achieved the highest accuracy, adaptability, and robustness for the detection of all kiwifruit categories as well as a small volume and portability. These results can provide technical support for the non-destructive detection and grading of agricultural products in the future.

Terahertz Humidity Sensing Based on Surface-Modified Polymer Mesh Membranes with Photografting PEGMA Brush.

A simple and compact intensity-interrogated terahertz (THz) relative humidity (RH) sensing platform is successfully demonstrated in experiments on the basis of combining a porous polymer sensing membrane and a continuous THz electronic system. The RH-sensing membrane is fabricated by surface modification of a porous polymer substrate with hydrophilic and photosensitive copolymer brushes via a UV-induced graft-polymerization process. The intensity interrogation sensing scheme indicated that the power reduction of the 0.4 THz wave is dependent on the grafting density of the copolymer brushes and proportional to the RH percent levels in the humidity-controlled air-sealed chamber. This finding was verified by the water contact angle measurement. Based on the slope of the proportional relation, the best sensitivity of the hydrophilic surface-modified sensing membrane was demonstrated at 0.0423 mV/% RH at the copolymer brush density of 1.57 mg/mm3 grafted on the single side of the sensing membrane. The sensitivity corresponds to a detection limit of approximately 1% RH. The THz RH sensing membrane was proven to exhibit the advantages of low loss, low cost, flexibility, high sensitivity, high RH resolution, and a wide RH working range of 25-99%. Thus, it is a good candidate for novel applications of wearable electronics, water- or moisture-related industrial and bio-sensing.

An online automatic sorting system for defective Ginseng Radix et Rhizoma Rubra using deep learning.

Objective: To establish a deep-learning architecture based on faster region-based convolutional neural networks (Faster R-CNN) algorithm for detection and sorting of red ginseng (Ginseng Radix et Rhizoma Rubra) with internal defects automatically on an online X-ray machine vision system. Methods: A Faster R-CNN based classifier was trained with around 20 000 samples with mean average precision value (mAP) of 0.95. A traditional image processing method based on feedforward neural network (FNN) obtained a bad performance with the accuracy, recall and specificity of 69.0%, 68.0%, and 70.0%, respectively. Therefore, the Faster R-CNN model was saved to evaluate the model performance on the defective red ginseng online sorting system. Results: An independent set of 2 000 red ginsengs were used to validate the performance of the Faster R-CNN based online sorting system in three parallel tests, achieving accuracy of 95.8%, 95.2% and 96.2%, respectively. Conclusion: The overall results indicated that the proposed Faster R-CNN based classification model has great potential for non-destructive detection of red ginseng with internal defects.

Flexible Au@AgNRs/CMC/qPCR film with enhanced sensitivity, homogeneity and stability for in-situ extraction and SERS detection of thiabendazole on fruits.

In this study, a high-performance, stable and homogeneous Au@AgNRs/CMC/qPCR flexible film surface-enhanced Raman scattering (SERS) substrate was constructed by synergistically stabilizing and protecting bimetallic core-shell Au@Ag nanorods (Au@AgNRs) with carboxymethylcellulose (CMC) and fluorescent-quantitative-polymerase-chain-reaction (qPCR) film. The network structure of CMC immobilized and aligned Au@AgNRs through coordination of carboxyl groups with surface Ag atoms to provide intensive and stable 'hot spots', and the qPCR bilayer film performed as carrier and barrier to protect Au@AgNRs from oxidation, humidity and optical damage and improved the robustness and stability. The Au@AgNRs/CMC/qPCR film was used for in-situ extraction and SERS detection of thiabendazole on nectarine (0.24 ppm) and lemon (0.27 ppm) with low detection of limits. Furthermore, it retained 98.6% SERS performance after storage for 90 days under ambient conditions, revealing the great potential in promoting the commercialization of the SERS technique for sensitive contaminants sensing with simple fabrication procedures, homogeneity, reproducibility and long-term stability.

Non-Destructive Detection of Different Pesticide Residues on the Surface of Hami Melon Classification Based on tHBA-ELM Algorithm and SWIR Hyperspectral Imaging.

In the field of safety detection of fruits and vegetables, how to conduct non-destructive detection of pesticide residues is still a pressing problem to be solved. In response to the high cost and destructive nature of existing chemical detection methods, this study explored the potential of identifying different pesticide residues on Hami melon by short-wave infrared (SWIR) (spectral range of 1000-2500 nm) hyperspectral imaging (HSI) technology combined with machine learning. Firstly, the classification effects of classical classification models, namely extreme learning machine (ELM), support vector machine (SVM), and partial least squares discriminant analysis (PLS-DA) on pesticide residues on Hami melon were compared, ELM was selected as the benchmark model for subsequent optimization. Then, the effects of different preprocessing treatments on ELM were compared and analyzed to determine the most suitable spectral preprocessing treatment. The ELM model optimized by Honey Badger Algorithm (HBA) with adaptive t-distribution mutation strategy (tHBA-ELM) was proposed to improve the detection accuracy for the detection of pesticide residues on Hami melon. The primitive HBA algorithm was optimized by using adaptive t-distribution, which improved the structure of the population and increased the convergence speed. Compared the classification results of tHBA-ELM with HBA-ELM and ELM model optimized by genetic algorithm (GA-ELM), the tHBA-ELM model can accurately identify whether there were pesticide residues and different types of pesticides. The accuracy, precision, sensitivity, and F1-score of the test set was 93.50%, 93.73%, 93.50%, and 0.9355, respectively. Metaheuristic optimization algorithms can improve the classification performance of classical machine learning classification models. Among all the models, the performance of tHBA-ELM was satisfactory. The results indicated that SWIR-HSI coupled with tHBA-ELM can be used for the non-destructive detection of pesticide residues on Hami melon, which provided the theoretical basis and technical reference for the detection of pesticide residues in other fruits and vegetables.

Deep Learning Network of Amomum villosum Quality Classification and Origin Identification Based on X-ray Technology.

A machine vision system based on a convolutional neural network (CNN) was proposed to sort Amomum villosum using X-ray non-destructive testing technology in this study. The Amomum villosum fruit network (AFNet) algorithm was developed to identify the internal structure for quality classification and origin identification in this manuscript. This network model is composed of experimental features of Amomum villosum. In this study, we adopted a binary classification method twice consecutive to identify the origin and quality of Amomum villosum. The results show that the accuracy, precision, and specificity of the AFNet for quality classification were 96.33%, 96.27%, and 100.0%, respectively, achieving higher accuracy than traditional CNN under the condition of faster operation speed. In addition, the model can also achieve an accuracy of 90.60% for the identification of places of origin. The accuracy of multi-category classification performed later with the consistent network structure is lower than that of the cascaded CNNs solution. With this intelligent feature recognition model, the internal structure information of Amomum villosum can be determined based on X-ray technology. Its application will play a positive role to improve industrial production efficiency.

Detecting different pesticide residues on Hami melon surface using hyperspectral imaging combined with 1D-CNN and information fusion.

Efficient, rapid, and non-destructive detection of pesticide residues in fruits and vegetables is essential for food safety. The visible/near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral imaging (HSI) systems were used to detect different types of pesticide residues on the surface of Hami melon. Taking four pesticides commonly used in Hami melon as the object, the effectiveness of single-band spectral range and information fusion in the classification of different pesticides was compared. The results showed that the classification effect of pesticide residues was better by using the spectral range after information fusion. Then, a custom multi-branch one-dimensional convolutional neural network (1D-CNN) model with the attention mechanism was proposed and compared with the traditional machine learning classification model K-nearest neighbor (KNN) algorithm and random forest (RF). The traditional machine learning classification model accuracy of both models was over 80.00%. However, the classification results using the proposed 1D-CNN were more satisfactory. After the full spectrum data was fused, it was input into the 1D-CNN model, and its accuracy, precision, recall, and F1-score value were 94.00%, 94.06%, 94.00%, and 0.9396, respectively. This study showed that both VNIR and SWIR hyperspectral imaging combined with a classification model could non-destructively detect different pesticide residues on the surface of Hami melon. The classification result using the SWIR spectrum was better than that using the VNIR spectrum, and the classification result using the information fusion spectrum was better than that using SWIR. This study can provide a valuable reference for the non-destructive detection of pesticide residues on the surface of other large, thick-skinned fruits.

Influence of maturity on bruise detection of peach by structured multispectral imaging.

Peaches are easily bruising during all stages of postharvest handling, maturity can affect the characteristics and detection of bruising, which is directly related to the quality and shelf life of peach. The main objective of this research was to investigate the effect of maturity on the early detection of postharvest bruising in peach based on structured multispectral imaging (S-MSI) system. The S-MSI data was measured for bruised peaches, followed by microstructural (CLSM), and biochemical (oxidative browning-related enzyme activities, gene expression, and phenolic compound metabolism) measurements. As the maturity increases, the external impact stress could further induce the accumulation of phenolics through the phenylpropane pathway and pulp oxidative browning, resulting in more pronounced external damage; and the spectral reflectance value of bruised peach was getting smaller, and the spectral waveform gradually flattened out. Three characteristic bands of 781, 824, 867 nm were selected from structured spectra (669-955 nm) related to bruising. The watershed algorithm was adopted for bruise detection, the detection rates for bruised peaches based on three maturity levels (S1-S3) were 91-92%, 90.71-97.43%, and 97.14-99.86%, respectively. This research demonstrated that S-MSI system coupled with watershed algorithm, can enhance our capability of detecting the early bruised peaches of different maturity levels.

Quantitative Measurements of DP in Cellulose Paper Based on Terahertz Spectroscopy.

The power transformer is vital to the reliability of the power grid which is most commonly insulated with Kraft paper and immersed in mineral oil, among which the aged state of the paper is mainly correlated to the operating life of the transformer. Degree of polymerization (DP) is a direct parameter to assess the aged condition of insulating paper, but existing DP measurement by viscosity methods are destructive and complicated. In this paper, terahertz time-domain spectroscopy (THz-TDS) was introduced to reach rapid, non-destructive detection of the DP of insulating paper. The absorption spectra of insulating paper show that characteristic peak regions at 1.8 and 2.23 THz both exhibit a log-linear quantitative relationship with DP, and their universalities are confirmed by conducting the above relationship on different types of insulating paper. Fourier transform infrared spectroscopy (FTIR) analysis and molecular dynamics modeling further revealed that 1.8 and 2.23 THz were favorably associated with the growth of water-cellulose hydrogen bond strength and amorphous cellulose, respectively. This paper demonstrates the viability of applying THz-TDS to the non-destructive detection of DP in insulating paper and assigned the vibration modes of the characteristic absorption peaks.

Non-Destructive Detection of Meat Quality Based on Multiple Spectral Dimension Reduction Methods by Near-Infrared Spectroscopy.

The potential of four dimension reduction methods for near-infrared spectroscopy was investigated, in terms of predicting the protein, fat, and moisture contents in lamb meat. With visible/near-infrared spectroscopy at 400-1050 nm and 900-1700 nm, respectively, calibration models using partial least squares regression (PLSR) or multiple linear regression (MLR) between spectra and quality parameters were established and compared. The MLR prediction models for all three quality parameters based on the wavelengths selected by stepwise regression achieved the best results in the spectral region of 400-1050 nm. As for the spectral region of 900-1700 nm, the PLSR prediction model based on the raw spectra or high-correlation spectra achieved better results. The results of this study indicate that sampling interval shortening and of peak-to-trough jump features are worthy of further study, due to their great potential in explaining the quality parameters.

Non-destructive Detection of Fatty Acid Content of Camellia Seed Based on Hyperspectral.

As a unique traditional vegetable oil in China, camellia seed oil has very high edible value. Camellia seed kernel is mainly composed of fatty acids, which not only determines the oil yield of camellia seed, but also exert an important impact on the storage performance of camellia seed. In order to quickly and accurately determine the fatty acid content of camellia seed, this paper took camellia seed as the research object, used hyperspectral technology to determine the fatty acid content of camellia seed, and establishes a spectral model. 8 pretreatment methods, such as Savitzky-Golay smoothing, normalization, baseline correction, multivariate scattering correction, standard normal variable transformation, detrending algorithm, first derivative and second derivative, were adopted in this paper. The spectral prediction model of fatty acid content in camellia seed was established by combining 4 modeling methods: principal components regression (PCR), partial least square regression (PLSR), back propagation neural network (BP), radial basis function neural network (RBF). The optimal prediction model was selected by comparing the coefficient of determination (R2) and root mean square error (RMSE) of various models. The results showed that the spectral sensitive bands with high correlation coefficients (r) were 410-420 nm, 450-460 nm, 490-510 nm, 545-580 nm, 845-870 nm and 905-925 nm, respectively. The r obtained by MSC pretreatment of spectral data was the largest. The data obtained by 8 different pretreatment methods combined with RBF neural network model was the best, in which the average value of coefficient of determination (RC2) in the calibration set was 0.8654, and the root mean square error of calibration (RMSEC) was 0.0777; the average value of coefficient of determination (RP2) and root mean square error of prediction (RMSEP) in the prediction set model were 0.8437 and 0.0827, respectively. It could be seen that the best accuracy could be achieved by MSC pretreatment combined with RBF neural network modeling. This paper can provide reference for rapid nondestructive detection of fatty acid content in camellia seed by hyperspectral technology.

An online automatic sorting system for defective Ginseng Radix et Rhizoma Rubra using deep learning / 中草药·英文版

OBJECTIVE@#To establish a deep-learning architecture based on faster region-based convolutional neural networks (Faster R-CNN) algorithm for detection and sorting of red ginseng (Ginseng Radix et Rhizoma Rubra) with internal defects automatically on an online X-ray machine vision system.@*METHODS@#A Faster R-CNN based classifier was trained with around 20 000 samples with mean average precision value (mAP) of 0.95. A traditional image processing method based on feedforward neural network (FNN) obtained a bad performance with the accuracy, recall and specificity of 69.0%, 68.0%, and 70.0%, respectively. Therefore, the Faster R-CNN model was saved to evaluate the model performance on the defective red ginseng online sorting system.@*RESULTS@#An independent set of 2 000 red ginsengs were used to validate the performance of the Faster R-CNN based online sorting system in three parallel tests, achieving accuracy of 95.8%, 95.2% and 96.2%, respectively.@*CONCLUSION@#The overall results indicated that the proposed Faster R-CNN based classification model has great potential for non-destructive detection of red ginseng with internal defects.

Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition.

Food non-destructive detection technology (NDDT) is a powerful impetus to the development of food safety and quality. One of the essential tasks of food quality regulation is the non-destructive detection of the food's nutrient content. However, existing food nutrient NDDT performs poorly in terms of efficiency and accuracy, which hinders their widespread application in daily meals. Therefore, this paper proposed an end-to-end food nutrition non-destructive detection method, named Swin-Nutrition, which combined deep learning and NDDT to evaluate the nutrient content of food. The method aimed to fully capture the feature information from the food images and thus accurately estimate the nutrient content. Swin-Nutrition resorted to Swin Transformer, the feature fusion module (FFM), and the nutrient prediction module to evaluate nutrient content. In particular, Swin Transformer acted as the backbone network for feature extraction of food images, and FFM was used to obtain the discriminative feature representation to improve the accuracy of prediction. The experimental results on the Nutrition5k dataset demonstrated the effectiveness and efficiency of our proposed method. Specifically, the mean value of the percentage mean absolute error (PMAE) for calories, mass, fat, carbohydrate, and protein were only 15.3%, 12.5%, 22.1%, 20.8%, and 15.4%, respectively. We hope that our simple and effective method will provide a solid foundation for the research of food NDDT.