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.

Recent advances in multispectral imaging-based technology have provided useful information on seed health in order to optimize the quality control process. In this study, we verified the efficiency of multispectral imaging (MSI) combined with statistical models to assess the cowpea seed health and differentiate seeds carrying different fungal species. Seeds were artificially inoculated with Fusarium pallidoroseum, Rhizoctonia solani and Aspergillus sp. Multispectral images were acquired at 19 wavelengths (365 to 970 nm) from inoculated seeds and freeze-killed ‘incubated’ seeds. Statistical models based on linear discriminant analysis (LDA) were developed using reflectance, color and texture features of the seed images. Results demonstrated that the LDA-based models were efficient in detecting and identifying different species of fungi in cowpea seeds. The model showed above 92% accuracy before incubation and 99% after incubation, indicating that the MSI technique in combination with statistical models can be a useful tool for evaluating the health status of cowpea seeds. Our findings can be a guide for the development of in-depth studies with more cultivars and fungal species, isolated and in association, for the successful application of MSI in the routine health inspection of cowpea seeds and other important legumes.

Among grain-producing species, soybean is one of the most important commodities, with increasing demand for production in coming years. Evaluation of soybean seed quality is fundamental for ensuring maximum germination and yield potential. Therefore, effective methods are necessary for examining different properties associated with physical-chemical, physiological, and seed-health changes that affect seed quality. This review focuses on the fundamental principles and on the application of techniques of radiographic imaging, magnetic resonance imaging, multispectral imagining, chlorophyll fluorescence imaging, and infrared thermography to evaluate changes related to loss of soybean seed quality, such as mechanical injury, injury caused by insects, embryonic malformation, and incomplete maturation. Computerized seedling image analysis is also presented for evaluation of seed lot vigor. The examples presented here show the potential of these image analysis techniques for identifying different types of injuries and increasing the efficiency of in-house quality control programs in soybean seed production companies.

Image analysis techniques are expanding in agriculture and, for being fast, simple, and not destroying samples, they are interesting alternatives in the detection of immature rice seeds. Therefore, the aim of this study was to evaluate the quality of rice seeds using X-ray, multispectral and chlorophyll fluorescence image analysis techniques. Initially, with the seeds identified and numbered, radiographic images were obtained to determine the free space (area between the endosperm + embryo and the glumes). Subsequently, with the same seeds used in the X-ray, multispectral and chlorophyll fluorescence images were acquired, and then the computerized seedling analysis was performed with the SVIS® software. It was concluded that rice seeds that do not germinate or originate abnormal seedlings have free space equal to or greater than 18.68%, higher reflectance in the spectral bands with wavelength from 590 nm to 780 nm (41.46% to 64.21%, respectively) and in the band of 970 nm (75.65%), in addition to having chlorophyll fluorescence values equal to or greater than 40.58 and 112.92 at excitation/emission energies of 630/700 nm and 645/700 nm, respectively.

Technologies that increase safety and efficiency, while facilitating and streamlining the work of seed analysts, are increasingly required by the seed industry. X-ray image analysis is a technique that has been used in the analysis of grain and seeds because it is fast, accurate and non-destructive. The traditional method to verify the presence of insect damage in seeds involves manual cutting of the seeds, which endangers the safety of the analyst and is time-consuming and repetitive work that leads to visual fatigue. The objective of this study was to compared the efficiency of radiographic analysis with and without contrast in the determination of infestation by Sitophilus zeamais Motschulsky (Coleoptera: Curculionidae), at different stages of development, in maize seeds, compared to the traditional method required by seed legislation, which consists of cutting and visual evaluation. Seeds were evaluated regarding the presence of eggs/oviposition signs, larvae, pupae, adult insects, insect damage in five infestation periods (5, 18, 33 and 35 days after infestation), while evaluating the total number of seeds infested, comparing the three methods. For characterization of the oviposition stage, the use of contrast was best at all times of infestation. For the larval stage, there was no difference between the evaluation methods; however, at 18 days, larger infestations were observed by the traditional method. At 5 days, the identification of pupae was better by the traditional method and radiography without contrast, while for the identification of adult insects the best method was the use of radiography without contrast. The characterization of the level of infestation with maize weevil damage was best verified using contrast radiography. Radiographic analysis is efficient in the detection of damage caused by S. zeamais in maize seeds. This method of radiographic analysis (with or without contrast) is thus an auxiliary tool to assess the damage and presence of S. zeamais in maize seeds.