Classification of white maize defects with multispectral imaging

Multispectral imaging for distinguishing hybrid forest seeds of Corymbia spp. and Eucalyptus spp. from their progenitors

In the forest industry, interspecific hybridization, such as Eucalyptus urograndis (Eucalyptus grandis × Eucalyptus urophylla) and Corymbia maculata × Corymbia torelliana, has led to the development of high-performing F1 generations. The successful breeding of these hybrids relies on verifying progenitor origins and confirming post-crossing, but conventional genotype identification methods are resource-intensive and result in seed destruction. As an alternative, multispectral imaging analysis has emerged as an efficient and non-destructive tool for seed phenotyping. This approach has demonstrated success in various crop seeds. However, identifying seed species in the context of forest seeds presents unique challenges due to their natural phenotypic variability and the striking resemblance between different species. This study evaluates the efficacy of spectral imaging analysis in distinguishing hybrid seeds of E. urograndis and C. maculata × C. torelliana from their progenitors. Four experiments were conducted: one for Corymbia spp. seeds, one for each Eucalyptus spp. batch separately, and one for pooled batches. Multispectral images were acquired at 19 wavelengths within the spectral range of 365-970 nm. Classification models based on Linear Discriminant Analysis (LDA), Random Forest (RF), and Support Vector Machine (SVM) was created using reflectance and reflectance features, combined with color, shape, and texture features, as well as nCDA transformed features. The LDA algorithm, combining all features, provided the highest accuracy, reaching 98.15% for Corymbia spp., and 92.75%, 85.38, and 86.00 for Eucalyptus batch one, two, and pooled batches, respectively. The study demonstrated the effectiveness of multispectral imaging in distinguishing hybrid seeds of Eucalyptus and Corymbia species. The seeds' spectral signature played a key role in this differentiation. This technology holds great potential for non-invasively classifying forest seeds in breeding programs.

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.

Vigour testing for the rice seed with computer vision-based techniques

Rice is the staple food for approximately half of the world's population. Seed vigour has a crucial impact on the yield, which can be evaluated by germination rate, vigor index and etc. Existing seed vigour testing methods heavily rely on manual inspections that are destructive, time-consuming, and labor-intensive. To address the drawbacks of existing rice seed vigour testing, we proposed a multispectral image-based non-destructive seed germination testing approach. Specifically, we collected multispectral data in 19 wavebands for six rice varieties. Furthermore, we designed an end-to-end pipeline, denoted as MsiFormer (MisFormer cod3e will be available at https://github.com/LiaoYun0x0/MisFormer) by integrating a Yolo-based object detector (trained Yolo v5) and a vision transformer-based vigour testing model, which effectively improved the automation and efficiency of existing techniques. In order to objectively evaluate the performance of the proposed method in this paper, we conduct a comparison between MisFormer and other 3 deep learning methods. The results showed that, MisFormer performed much better with the accuracy of 94.17%, which was 2.5%-18.34% higher than the other 3 deep learning methods. Besides MsiFormer, possibilities of CIELab mediated image analysis of TTC (tetrazolium chloride) staining in rice seed viability and nCDA (normalized canonical discriminant analysis) in rice seed vigour were also discussed, where CIELab L* of TTC staining were negatively correlated with vigor index and germination rate, with Pearson's correlation coefficient of -0.9874, -0.9802 respectively, and CIELab A* of TTC staining were and positively correlated with vigor index and germination rate, with Pearson's correlation coefficient of 0.9624, 0.9544 respectively, and CIELab A* of nCDA had Pearson's correlation coefficient of -0.8866 and -0.9340 with vigor index and germination rate, respectively. Besides testing methods, vigour results within and among variety(ies) showed that, there were great variations among the 6 rice varieties, and mean coefficient of variation (CV) of vigor index of individual seed within a variety reached 64.87%, revealing the high risk of conventional methods in random sampling. Vigour variations had close relationship with wavelengths of 780 nm-970 nm, indicating their value in future research.

Nondestructive discrimination of analogous density foreign matter inside soy protein meat semi-finished products based on transmission hyperspectral imaging

Analogous density foreign matter (ADFM) embedded in soy protein meat semi-finished (SFSPM) is hidden by SFSPM and has similar acoustic impedance features to SFSPM, which makes non-destructive testing techniques such as computer vision (CV), reflectance spectroscopy and ultrasound imaging inappropriate for ADFM, which not only seriously affects the quality of soy protein meat (SPM) products but also increases the safety risk to consumers. In this study, to locate and separate ADFM by using transmission hyperspectral imaging (T-HSI) technique which is sensitive to chemical composition and highlight internal contours. The optimal discrimination model SVM + PCA + MSC + SPA was constructed using transmission spectral information with an accuracy of 95.00 %. The visualization results based on the optimal model showed clearer localization results than CV and ultrasound imaging. The study demonstrated that the advantages of T-HSI technology in detecting and locating ADFM inside SFSPM, which provides a basis for improving the production quality and safety of SPM.

Identification of Defective Maize Seeds Using Hyperspectral Imaging Combined with Deep Learning

Seed quality affects crop yield and the quality of agricultural products, and traditional identification methods are time-consuming, complex, and irreversibly destructive. This study aims to establish a fast, non-destructive, and effective approach for defect detection in maize seeds based on hyperspectral imaging (HSI) technology combined with deep learning. Raw spectra collected from maize seeds (200 each healthy and worm-eaten) were pre-processed using detrending (DE) and multiple scattering correction (MSC) to highlight the spectral differences between samples. A convolutional neural network architecture (CNN-FES) based on a feature selection mechanism was proposed according to the importance of wavelength in the target classification task. The results show that the subset of 24 feature wavelengths selected by the proposed CNN-FES can capture important feature information in the spectral data more effectively than the conventional successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) algorithms. In addition, a convolutional neural network architecture (CNN-ATM) based on an attentional classification mechanism was designed for one-dimensional spectral data classification and compared with three commonly used machine learning methods, linear discriminant analysis (LDA), random forest (RF), and support vector machine (SVM). The results show that the classification performance of the designed CNN-ATM on the full wavelength does not differ much from the above three methods, and the classification accuracy is above 90% on both the training and test sets. Meanwhile, the accuracy, sensitivity, and specificity of CNN-ATM based on feature wavelength modeling can reach up to 97.50%, 98.28%, and 96.77% at the highest, respectively. The study shows that hyperspectral imaging-based defect detection of maize seed is feasible and effective, and the proposed method has great potential for the processing and analysis of complex hyperspectral data.

Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning

Multispectral imaging (MSI) has become a new fast and non-destructive detection method in seed identification. Previous research has usually focused on single models in MSI data analysis, which always employed all features and increased the risk to efficiency and that of system cost. In this study, we developed a stacking ensemble learning (SEL) model for successfully identifying a single seed of sickle alfalfa (Medicago falcata), hybrid alfalfa (M. varia), and alfalfa (M. sativa). SEL adopted a three-layer structure, i.e., level 0 with principal component analysis (PCA), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) as models of dimensionality reduction and feature extraction (DRFE); level 1 with support vector machine (SVM), multiple logistic regression (MLR), generalized linear models with elastic net regularization (GLMNET), and eXtreme Gradient Boosting (XGBoost) as basic learners; and level 3 with XGBoost as meta-learner. We confirmed that the values of overall accuracy, kappa, precision, sensitivity, specificity, and sensitivity in the SEL model were all significantly higher than those in basic models alone, based on both spectral features and a combination of morphological and spectral features. Furthermore, we also developed a feature filtering process and successfully selected 5 optimal features out of 33 ones, which corresponded to the contents of chlorophyll, anthocyanin, fat, and moisture in seeds. Our SEL model in MSI data analysis provided a new way for seed identification, and the feature filter process potentially could be used widely for development of a low-cost and narrow-channel sensor.

As the number falls, alternatives to the Hagberg-Perten falling number method: A review

This review examines the application, limitations, and potential alternatives to the Hagberg-Perten falling number (FN) method used in the global wheat industry for detecting the risk of poor end-product quality mainly due to starch degradation by the enzyme α-amylase. By viscometry, the FN test indirectly detects the presence of α-amylase, the primary enzyme that digests starch. Elevated α-amylase results in low FN and damages wheat product quality resulting in cakes that fall, and sticky bread and noodles. Low FN can occur from preharvest sprouting (PHS) and late maturity α-amylase (LMA). Moist or rainy conditions before harvest cause PHS on the mother plant. Continuously cool or fluctuating temperatures during the grain filling stage cause LMA. Due to the expression of additional hydrolytic enzymes, PHS has a stronger negative impact than LMA. Wheat grain with low FN/high α-amylase results in serious losses for farmers, traders, millers, and bakers worldwide. Although blending of low FN grain with sound wheat may be used as a means of moving affected grain through the marketplace, care must be taken to avoid grain lots from falling below contract-specified FN. A large amount of sound wheat can be ruined if mixed with a small amount of sprouted wheat. The FN method is widely employed to detect α-amylase after harvest. However, it has several limitations, including sampling variability, high cost, labor intensiveness, the destructive nature of the test, and an inability to differentiate between LMA and PHS. Faster, cheaper, and more accurate alternatives could improve breeding for resistance to PHS and LMA and could preserve the value of wheat grain by avoiding inadvertent mixing of high- and low-FN grain by enabling testing at more stages of the value stream including at harvest, delivery, transport, storage, and milling. Alternatives to the FN method explored here include the Rapid Visco Analyzer, enzyme assays, immunoassays, near-infrared spectroscopy, and hyperspectral imaging.

Advances in optical phenotyping of cereal crops

Optical sensors and sensing-based phenotyping techniques have become mainstream approaches in high-throughput phenotyping for improving trait selection and genetic gains in crops. We review recent progress and contemporary applications of optical sensing-based phenotyping (OSP) techniques in cereal crops and highlight optical sensing principles for spectral response and sensor specifications. Further, we group phenotypic traits determined by OSP into four categories - morphological, biochemical, physiological, and performance traits - and illustrate appropriate sensors for each extraction. In addition to the current status, we discuss the challenges of OSP and provide possible solutions. We propose that optical sensing-based traits need to be explored further, and that standardization of the language of phenotyping and worldwide collaboration between phenotyping researchers and other fields need to be established.

Emerging nondestructive approaches for meat quality and safety evaluation-A review

Meat is one of the most consumed agro-products because it contains proteins, minerals, and essential vitamins, all of which play critical roles in the human diet and health. Meat is a perishable food product because of its high moisture content, and as such there are concerns about its quality, stability, and safety. There are two widely used methods for monitoring meat quality attributes: subjective sensory evaluation and chemical/instrumentation tests. However, these methods are labor-intensive, time-consuming, and destructive. To overcome the shortfalls of these conventional approaches, several researchers have developed fast and nondestructive techniques. Recently, electronic nose (e-nose), computer vision (CV), spectroscopy, hyperspectral imaging (HSI), and multispectral imaging (MSI) technologies have been explored as nondestructive methods in meat quality and safety evaluation. However, most of the studies on the application of these novel technologies are still in the preliminary stages and are carried out in isolation, often without comprehensive information on the most suitable approach. This lack of cohesive information on the strength and shortcomings of each technique could impact their application and commercialization for the detection of important meat attributes such as pH, marbling, or microbial spoilage. Here, we provide a comprehensive review of recent nondestructive technologies (e-nose, CV, spectroscopy, HSI, and MSI), as well as their applications and limitations in the detection and evaluation of meat quality and safety issues, such as contamination, adulteration, and quality classification. A discussion is also included on the challenges and future outlooks of the respective technologies and their various applications.

Multispectral and X-ray images for characterization of Jatropha curcas L. seed quality

BACKGROUND

The use of non-destructive methods with less human interference is of great interest in agricultural industry and crop breeding. Modern imaging technologies enable the automatic visualization of multi-parameter for characterization of biological samples, reducing subjectivity and optimizing the analysis process. Furthermore, the combination of two or more imaging techniques has contributed to discovering new physicochemical tools and interpreting datasets in real time.

RESULTS

We present a new method for automatic characterization of seed quality based on the combination of multispectral and X-ray imaging technologies. We proposed an approach using X-ray images to investigate internal tissues because seed surface profile can be negatively affected, but without reaching important internal regions of seeds. An oilseed plant (Jatropha curcas) was used as a model species, which also serves as a multi-purposed crop of economic importance worldwide. Our studies included the application of a normalized canonical discriminant analyses (nCDA) algorithm as a supervised transformation building method to obtain spatial and spectral patterns on different seedlots. We developed classification models using reflectance data and X-ray classes based on linear discriminant analysis (LDA). The classification models, individually or combined, showed high accuracy (> 0.96) using reflectance at 940 nm and X-ray data to predict quality traits such as normal seedlings, abnormal seedlings and dead seeds.

CONCLUSIONS

Multispectral and X-ray imaging have a strong relationship with seed physiological performance. Reflectance at 940 nm and X-ray data can efficiently predict seed quality attributes. These techniques can be alternative methods for rapid, efficient, sustainable and non-destructive characterization of seed quality in the future, overcoming the intrinsic subjectivity of the conventional seed quality analysis.

Cultivar Discrimination of Single Alfalfa (Medicago sativa L.) Seed via Multispectral Imaging Combined with Multivariate Analysis

Rapid and accurate discrimination of alfalfa cultivars is crucial for producers, consumers, and market regulators. However, the conventional routine of alfalfa cultivars discrimination is time-consuming and labor-intensive. In this study, the potential of a new method was evaluated that used multispectral imaging combined with object-wise multivariate image analysis to distinguish alfalfa cultivars with a single seed. Three multivariate analysis methods including principal component analysis (PCA), linear discrimination analysis (LDA), and support vector machines (SVM) were applied to distinguish seeds of 12 alfalfa cultivars based on their morphological and spectral traits. The results showed that the combination of morphological features and spectral data could provide an exceedingly concise process to classify alfalfa seeds of different cultivars with multivariate analysis, while it failed to make the classification with only seed morphological features. Seed classification accuracy of the testing sets was 91.53% for LDA, and 93.47% for SVM. Thus, multispectral imaging combined with multivariate analysis could provide a simple, robust and nondestructive method to distinguish alfalfa seed cultivars.

Detection of Drechslera avenae (Eidam) Sharif [Helminthosporium avenae (Eidam)] in Black Oat Seeds (Avena strigosa Schreb) Using Multispectral Imaging

Conventional methods for detecting seed-borne fungi are laborious and time-consuming, requiring specialized analysts for characterization of pathogenic fungi on seed. Multispectral imaging (MSI) combined with machine vision was used as an alternative method to detect Drechslera avenae (Eidam) Sharif [Helminthosporium avenae (Eidam)] in black oat seeds (Avena strigosa Schreb). The seeds were inoculated with Drechslera avenae (D. avenae) and then incubated for 24, 72 and 120 h. Multispectral images of non-infested and infested seeds were acquired at 19 wavelengths within the spectral range of 365 to 970 nm. A classification model based on linear discriminant analysis (LDA) was created using reflectance, color, and texture features of the seed images. The model developed showed high performance of MSI in detecting D. avenae in black oat seeds, particularly using color and texture features from seeds incubated for 120 h, with an accuracy of 0.86 in independent validation. The high precision of the classifier showed that the method using images captured in the Ultraviolet A region (365 nm) could be easily used to classify black oat seeds according to their health status, and results can be achieved more rapidly and effectively compared to conventional methods.

A Review of the Methodology of Analyzing Aflatoxin and Fumonisin in Single Corn Kernels and the Potential Impacts of These Methods on Food Security

Current detection methods for contamination of aflatoxin and fumonisin used in the corn industry are based on bulk level. However, literature demonstrates that contamination of these mycotoxins is highly skewed and bulk samples do not always represent accurately the overall contamination in a batch of corn. Single kernel analysis can provide an insightful level of analysis of the contamination of aflatoxin and fumonisin, as well as suggest a possible remediation to the skewness present in bulk detection. Current literature describes analytical methods capable of detecting aflatoxin and fumonisin at a single kernel level, such as liquid chromatography, fluorescence imaging, and reflectance imaging. These methods could provide tools to classify mycotoxin contaminated kernels and study potential co-occurrence of aflatoxin and fumonisin. Analysis at a single kernel level could provide a solution to the skewness present in mycotoxin contamination detection and offer improved remediation methods through sorting that could impact food security and management of food waste.

Non-destructive identification of single hard seed via multispectral imaging analysis in six legume species

BACKGROUND

Physical dormancy (hard seed) occurs in most species of Leguminosae family and has great consequences not only for ecological adaptation but also for agricultural practice of these species. A rapid, nondestructive and on-site screening method to detect hard seed within species is fundamental important for maintaining seed vigor and germplasm storage as well as understanding seed adaptation to various environment. In this study, the potential of multispectral imaging with object-wise multivariate image analysis was evaluated as a way to identify hard and soft seeds in Acacia seyal, Galega orientulis, Glycyrrhiza glabra, Medicago sativa, Melilotus officinalis, and Thermopsis lanceolata. Principal component analysis (PCA), linear discrimination analysis (LDA), and support vector machines (SVM) methods were applied to classify hard and soft seeds according to their morphological features and spectral traits.

RESULTS

The performance of discrimination model via multispectral imaging analysis was varied with species. For M. officinalis, M. sativa, and G. orientulis, an excellent classification could be achieved in an independent validation data set. LDA model had the best calibration and validation abilities with the accuracy up to 90% for M. sativa. SVM got excellent seed discrimination results with classification accuracy of 91.67% and 87.5% for M. officinalis and G. orientulis, respectively. However, both LDA and SVM model failed to discriminate hard and soft seeds in A. seyal, G. glabra, and T. lanceolate.

CONCLUSIONS

Multispectral imaging together with multivariate analysis could be a promising technique to identify single hard seed in some legume species with high efficiency. More legume species with physical dormancy need to be studied in future research to extend the use of multispectral imaging techniques.

Integrating Optical Imaging Tools for Rapid and Non-invasive Characterization of Seed Quality: Tomato (Solanum lycopersicum L.) and Carrot (Daucus carota L.) as Study Cases

Light-based methods are being further developed to meet the growing demands for food in the agricultural industry. Optical imaging is a rapid, non-destructive, and accurate technology that can produce consistent measurements of product quality compared to conventional techniques. In this research, a novel approach for seed quality prediction is presented. In the proposed approach two advanced optical imaging techniques based on chlorophyll fluorescence and chemometric-based multispectral imaging were employed. The chemometrics encompassed principal component analysis (PCA) and quadratic discrimination analysis (QDA). Among plants that are relevant as both crops and scientific models, tomato, and carrot were selected for the experiment. We compared the optical imaging techniques to the traditional analytical methods used for quality characterization of commercial seedlots. Results showed that chlorophyll fluorescence-based technology is feasible to discriminate cultivars and to identify seedlots with lower physiological potential. The exploratory analysis of multispectral imaging data using a non-supervised approach (two-component PCA) allowed the characterization of differences between carrot cultivars, but not for tomato cultivars. A Random Forest (RF) classifier based on Gini importance was applied to multispectral data and it revealed the most meaningful bandwidths from 19 wavelengths for seed quality characterization. In order to validate the RF model, we selected the five most important wavelengths to be applied in a QDA-based model, and the model reached high accuracy to classify lots with high-and low-vigor seeds, with a correct classification from 86 to 95% in tomato and from 88 to 97% in carrot for validation set. Further analysis showed that low quality seeds resulted in seedlings with altered photosynthetic capacity and chlorophyll content. In conclusion, both chlorophyll fluorescence and chemometrics-based multispectral imaging can be applied as reliable proxies of the physiological potential in tomato and carrot seeds. From the practical point of view, such techniques/methodologies can be potentially used for screening low quality seeds in food and agricultural industries.

Online Feature Selection for Robust Classification of the Microbiological Quality of Traditional Vanilla Cream by Means of Multispectral Imaging

The performance of an Unsupervised Online feature Selection (UOS) algorithm was investigated for the selection of training features of multispectral images acquired from a dairy product (vanilla cream) stored under isothermal conditions. The selected features were further used as input in a support vector machine (SVM) model with linear kernel for the determination of the microbiological quality of vanilla cream. Model training (n = 65) was based on two batches of cream samples provided directly by the manufacturer and stored at different isothermal conditions (4, 8, 12, and 15 °C), whereas model testing (n = 132) and validation (n = 48) were based on real life conditions by analyzing samples from different retail outlets as well as expired samples from the market. Qualitative analysis was performed for the discrimination of cream samples in two microbiological quality classes based on the values of total viable counts [TVC ≤ 2.0 log CFU/g (fresh samples) and TVC ≥ 6.0 log CFU/g (spoiled samples)]. Results exhibited good performance with an overall accuracy of classification for the two classes of 91.7% for model validation. Further on, the model was extended to include the samples in the TVC range 2-6 log CFU/g, using 1 log step to define the microbiological quality of classes in order to assess the potential of the model to estimate increasing microbial populations. Results demonstrated that high rates of correct classification could be obtained in the range of 2-5 log CFU/g, whereas the percentage of erroneous classification increased in the TVC class (5,6) that was close to the spoilage level of the product. Overall, the results of this study demonstrated that the UOS algorithm in tandem with spectral data acquired from multispectral imaging could be a promising method for real-time assessment of the microbiological quality of vanilla cream samples.

Classification of Processing Damage in Sugar Beet (Beta vulgaris) Seeds by Multispectral Image Analysis

The pericarp of monogerm sugar beet seed is rubbed off during processing in order to produce uniformly sized seeds ready for pelleting. This process can lead to mechanical damage, which may cause quality deterioration of the processed seeds. Identification of the mechanical damage and classification of the severity of the injury is important and currently time consuming, as visual inspections by trained analysts are used. This study aimed to find alternative seed quality assessment methods by evaluating a machine vision technique for the classification of five damage types in monogerm sugar beet seeds. Multispectral imaging (MSI) was employed using the VideometerLab3 instrument and instrument software. Statistical analysis of MSI-derived data produced a model, which had an average of 82% accuracy in classification of 200 seeds in the five damage classes. The first class contained seeds with the potential to produce good seedlings and the model was designed to put more limitations on seeds to be classified in this group. The classification accuracy of class one to five was 59, 100, 77, 77 and 89%, respectively. Based on the results we conclude that MSI-based classification of mechanical damage in sugar beet seeds is a potential tool for future seed quality assessment.

Advanced Techniques for Hyperspectral Imaging in the Food Industry: Principles and Recent Applications

Hyperspectral imaging (HSI) is a technology integrating optical sensing technologies of imaging, spectroscopy, and chemometrics. The sensor of HSI can obtain both spatial and spectral information simultaneously. Therefore, the chemical and physical information of food products can be monitored in a rapid, nondestructive, and noncontact manner. There are numerous reports and papers and much research dealing with the applications of HSI in food in recent years. This review introduces the principle of HSI technology, summarizes its recent applications in food, and pinpoints future trends.

Recent Applications of Multispectral Imaging in Seed Phenotyping and Quality Monitoring-An Overview

As a synergistic integration between spectroscopy and imaging technologies, spectral imaging modalities have been emerged to tackle quality evaluation dilemmas by proposing different designs with effective and practical applications in food and agriculture. With the advantage of acquiring spatio-spectral data across a wide range of the electromagnetic spectrum, the state-of-the-art multispectral imaging in tandem with different multivariate chemometric analysis scenarios has been successfully implemented not only for food quality and safety control purposes, but also in dealing with critical research challenges in seed science and technology. This paper will shed some light on the fundamental configuration of the systems and give a birds-eye view of all recent approaches in the acquisition, processing and reproduction of multispectral images for various applications in seed quality assessment and seed phenotyping issues. This review article continues from where earlier review papers stopped but it only focused on fully-operated multispectral imaging systems for quality assessment of different sorts of seeds. Thence, the review comprehensively highlights research attempts devoted to real implementations of only fully-operated multispectral imaging systems and does not consider those ones that just utilized some key wavelengths extracted from hyperspectral data analyses without building independent multispectral imaging systems. This makes this article the first attempt in briefing all published papers in multispectral imaging applications in seed phenotyping and quality monitoring by providing some examples and research results in characterizing physicochemical quality traits, predicting physiological parameters, detection of defect, pest infestation and seed health.

Utilization of computer vision and multispectral imaging techniques for classification of cowpea (Vigna unguiculata) seeds

BACKGROUND

The traditional methods for evaluating seeds are usually performed through destructive sampling followed by physical, physiological, biochemical and molecular determinations. Whilst proven to be effective, these approaches can be criticized as being destructive, time consuming, labor intensive and requiring experienced seed analysts. Thus, the objective of this study was to investigate the potential of computer vision and multispectral imaging systems supported with multivariate analysis for high-throughput classification of cowpea (Vigna unguiculata) seeds. An automated computer-vision germination system was utilized for uninterrupted monitoring of seeds during imbibition and germination to identify different categories of all individual seeds. By using spectral signatures of single cowpea seeds extracted from multispectral images, different multivariate analysis models based on linear discriminant analysis (LDA) were developed for classifying the seeds into different categories according to ageing, viability, seedling condition and speed of germination.

RESULTS

The results revealed that the LDA models had good accuracy in distinguishing 'Aged' and 'Non-aged' seeds with an overall correct classification (OCC) of 97.51, 96.76 and 97%, 'Germinated' and 'Non-germinated' seeds with OCC of 81.80, 79.05 and 81.0%, 'Early germinated', 'Medium germinated' and 'Dead' seeds with OCC of 77.21, 74.93 and 68.00% and among seeds that give 'Normal' and 'Abnormal' seedlings with OCC of 68.08, 64.34 and 62.00% in training, cross-validation and independent validation data sets, respectively. Image processing routines were also developed to exploit the full power of the multispectral imaging system in visualizing the difference among seed categories by applying the discriminant model in a pixel-wise manner.

CONCLUSION

The results demonstrated the capability of the multispectral imaging system in the ultraviolet, visible and shortwave near infrared range to provide the required information necessary for the discrimination of individual cowpea seeds to different classes. Considering the short time of image acquisition and limited sample preparation, this stat-of-the art multispectral imaging method and chemometric analysis in classifying seeds could be a valuable tool for on-line classification protocols in cost-effective real-time sorting and grading processes as it provides not only morphological and physical features but also chemical information for the seeds being examined. Implementing image processing algorithms specific for seed quality assessment along with the declining cost and increasing power of computer hardware is very efficient to make the development of such computer-integrated systems more attractive in automatic inspection of seed quality.