Non-Destructive Identification of Naturally Aged Alfalfa Seeds via Multispectral Imaging Analysis

Deep machine learning identified fish flesh using multispectral imaging

Food fraud is widespread in the aquatic food market, hence fast and non-destructive methods of identification of fish flesh are needed. In this study, multispectral imaging (MSI) was used to screen flesh slices from 20 edible fish species commonly found in the sea around Yantai, China, by combining identification based on the mitochondrial COI gene. We found that nCDA images transformed from MSI data showed significant differences in flesh splices of the 20 fish species. We then employed eight models to compare their prediction performances based on the hold-out method with 70% training and 30% test sets. Convolutional neural network (CNN), quadratic discriminant analysis (QDA), support vector machine (SVM), and linear discriminant analysis (LDA) models perform well on cross-validation and test data. CNN and QDA achieved more than 99% accuracy on the test set. By extracting the CNN features for optimization, a very high degree of separation was obtained for all species. Furthermore, based on the Gini index in RF, 11 bands were selected as key classification features for CNN, and an accuracy of 98% was achieved. Our study developed a successful pipeline for employing machine learning models (especially CNN) on MSI identification of fish flesh, and provided a convenient and non-destructive method to determine the marketing of fish flesh in the future.

Nondestructive Detection of Sunflower Seed Vigor and Moisture Content Based on Hyperspectral Imaging and Chemometrics

Sunflower is an important crop, and the vitality and moisture content of sunflower seeds have an important influence on the sunflower's planting and yield. By employing hyperspectral technology, the spectral characteristics of sunflower seeds within the wavelength range of 384-1034 nm were carefully analyzed with the aim of achieving effective prediction of seed vitality and moisture content. Firstly, the original hyperspectral data were subjected to preprocessing techniques such as Savitzky-Golay smoothing, standard normal variable correction (SNV), and multiplicative scatter correction (MSC) to effectively reduce noise interference, ensuring the accuracy and reliability of the data. Subsequently, principal component analysis (PCA), extreme gradient boosting (XGBoost), and stacked autoencoders (SAE) were utilized to extract key feature bands, enhancing the interpretability and predictive performance of the data. During the modeling phase, random forests (RFs) and LightGBM algorithms were separately employed to construct classification models for seed vitality and prediction models for moisture content. The experimental results demonstrated that the SG-SAE-LightGBM model exhibited outstanding performance in the classification task of sunflower seed vitality, achieving an accuracy rate of 98.65%. Meanwhile, the SNV-XGBoost-LightGBM model showed remarkable achievement in moisture content prediction, with a coefficient of determination (R2) of 0.9715 and root mean square error (RMSE) of 0.8349. In conclusion, this study confirms that the fusion of hyperspectral technology and multivariate data analysis algorithms enables the accurate and rapid assessment of sunflower seed vitality and moisture content, providing robust tools and theoretical support for seed quality evaluation and agricultural production practices. Furthermore, this research not only expands the application of hyperspectral technology in unraveling the intrinsic vitality characteristics of sunflower seeds but also possesses significant theoretical and practical value.

Integrating optical imaging techniques for a novel approach to evaluate Siberian wild rye seed maturity

Advances in optical imaging technology using rapid and non-destructive methods have led to improvements in the efficiency of seed quality detection. Accurately timing the harvest is crucial for maximizing the yield of higher-quality Siberian wild rye seeds by minimizing excessive shattering during harvesting. This research applied integrated optical imaging techniques and machine learning algorithms to develop different models for classifying Siberian wild rye seeds based on different maturity stages and grain positions. The multi-source fusion of morphological, multispectral, and autofluorescence data provided more comprehensive information but also increases the performance requirements of the equipment. Therefore, we employed three filtering algorithms, namely minimal joint mutual information maximization (JMIM), information gain, and Gini impurity, and set up two control methods (feature union and no-filtering) to assess the impact of retaining only 20% of the features on the model performance. Both JMIM and information gain revealed autofluorescence and morphological features (CIELab A, CIELab B, hue and saturation), with these two filtering algorithms showing shorter run times. Furthermore, a strong correlation was observed between shoot length and morphological and autofluorescence spectral features. Machine learning models based on linear discriminant analysis (LDA), random forests (RF) and support vector machines (SVM) showed high performance (>0.78 accuracies) in classifying seeds at different maturity stages. Furthermore, it was found that there was considerable variation in the different grain positions at the maturity stage, and the K-means approach was used to improve the model performance by 5.8%-9.24%. In conclusion, our study demonstrated that feature filtering algorithms combined with machine learning algorithms offer high performance and low cost in identifying seed maturity stages and that the application of k-means techniques for inconsistent maturity improves classification accuracy. Therefore, this technique could be employed classification of seed maturity and superior physiological quality for Siberian wild rye seeds.

Non-Destructive Testing of Alfalfa Seed Vigor Based on Multispectral Imaging Technology

Seed vigor is an important index to evaluate seed quality in plant species. How to evaluate seed vigor quickly and accurately has always been a serious problem in the seed research field. As a new physical testing method, multispectral technology has many advantages such as high sensitivity and accuracy, nondestructive and rapid application having advantageous prospects in seed quality evaluation. In this study, the morphological and spectral information of 19 wavelengths (365, 405, 430, 450, 470, 490, 515, 540, 570, 590, 630, 645, 660, 690, 780, 850, 880, 940, 970 nm) of alfalfa seeds with different level of maturity and different harvest periods (years), representing different vigor levels and age of seed, were collected by using multispectral imaging. Five multivariate analysis methods including principal component analysis (PCA), linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF) and normalized canonical discriminant analysis (nCDA) were used to distinguish and predict their vigor. The results showed that LDA model had the best effect, with an average accuracy of 92.9% for seed samples of different maturity and 97.8% for seed samples of different harvest years, and the average sensitivity, specificity and precision of LDA model could reach more than 90%. The average accuracy of nCDA in identifying dead seeds with no vigor reached 93.3%. In identifying the seeds with high vigor and predicting the germination percentage of alfalfa seeds, it could reach 95.7%. In summary, the use of Multispectral Imaging and multivariate analysis in this experiment can accurately evaluate and predict the seed vigor, seed viability and seed germination percentages of alfalfa, providing important technical methods and ideas for rapid non-destructive testing of seed quality.

An Approach Using Emerging Optical Technologies and Artificial Intelligence Brings New Markers to Evaluate Peanut Seed Quality

Seeds of high physiological quality are defined by their superior germination capacity and uniform seedling establishment. Here, it was investigated whether multispectral images combined with machine learning models can efficiently categorize the quality of peanut seedlots. The seed quality from seven lots was assessed traditionally (seed weight, water content, germination, and vigor) and by multispectral images (area, length, width, brightness, chlorophyll fluorescence, anthocyanin, and reflectance: 365 to 970 nm). Seedlings from the seeds of each lot were evaluated for their photosynthetic capacity (fluorescence and chlorophyll index, F₀, F_m, and F_v/F_m) and stress indices (anthocyanin and NDVI). Artificial intelligence features (QDA method) applied to the data extracted from the seed images categorized lots with high and low quality. Higher levels of anthocyanin were found in the leaves of seedlings from low quality seeds. Therefore, this information is promising since the initial behavior of the seedlings reflected the quality of the seeds. The existence of new markers that effectively screen peanut seed quality was confirmed. The combination of physical properties (area, length, width, and coat brightness), pigments (chlorophyll fluorescence and anthocyanin), and light reflectance (660, 690, and 780 nm), is highly efficient to identify peanut seedlots with superior quality (98% accuracy).