No abstract

Non-destructive and high performance analyses are highly desirable and important for assessing the quality of forest seeds. The aim of this study was to relate parameters obtained from semi-automated analysis of radiographs of Leucaena leucocephala seeds to their physiological potential by means of multivariate analysis. To do so, seeds from five lots collected from parent trees from the region of Viçosa, MG, Brazil, were used. The study was carried out through analysis of radiographic images of seeds, from which the percentage of damaged seeds (predation and fungi), and measurements of area, perimeter, circularity, relative density, and integrated density of the seeds were obtained. After the X-ray test, the seeds were tested for germination in order to assess variables related to seed physiological quality. Multivariate statistics were applied to the data generated, with use of principal component analysis (PCA). X-ray testing allowed visualization of details of the internal structure of seeds and differences regarding density of seed tissues. Semi-automated analysis of radiographic images of Leucaena leucocephala seeds provides information on seed physical characteristics and generates parameters related to seed physiological quality in a simple, fast, and inexpensive manner.

The need to optimize seed quality assessment using new, more accessible, and modern computational resources has led to the emergence of new tools. In this paper, we introduce SeedCalc, a new R software package developed to process germination and seedling length data. The functions included in SeedCalc allow fast and efficient data processing, offering greater reliability to the variables generated and facilitating statistical analysis itself since the data are already processed with the appropriate structure to be statistically analyzed in the R software. SeedCalc is available free of charge at https://CRAN.R-project.org/package=SeedCalc.

Optical sensors combined with machine learning algorithms have led to significant advances in seed science. These advances have facilitated the development of robust approaches, providing decision-making support in the seed industry related to the marketing of seed lots. In this study, a novel approach for seed quality classification is presented. We developed classifier models using Fourier transform near-infrared (FT-NIR) spectroscopy and X-ray imaging techniques to predict seed germination and vigor. A forage grass (Urochloa brizantha) was used as a model species. FT-NIR spectroscopy data and radiographic images were obtained from individual seeds, and the models were created based on the following algorithms: linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), naive Bayes (NB), and support vector machine with radial basis (SVM-r) kernel. In the germination prediction, the models individually reached an accuracy of 82% using FT-NIR data, and 90% using X-ray data. For seed vigor, the models achieved 61% and 68% accuracy using FT-NIR and X-ray data, respectively. Combining the FT-NIR and X-ray data, the performance of the classification model reached an accuracy of 85% to predict germination, and 62% for seed vigor. Overall, the models developed using both NIR spectra and X-ray imaging data in machine learning algorithms are efficient in quickly, non-destructively, and accurately identifying the capacity of seed to germinate. The use of X-ray data and the LDA algorithm showed great potential to be used as a viable alternative to assist in the quality classification of U. brizantha seeds.

Obtaining image-based information is a powerful approach to capture and quantify seed vigor data. However, commercial systems that facilitate the processing and acquisition of images are often cost prohibitive. This study aimed to evaluate the efficiency of the Seedling Analysis System (Sistema de Análise de Plântulas - SAPL®), in order to analyze the physiological potential of soybean seeds, in comparison with the information provided by vigor tests which are traditionally recommended for this species. Nine lots of soybean seeds were submitted to germination, germination speed, seedling emergence, cold test and electrical conductivity tests. In the SAPL® analyzes, seedlings of four and six days, counted from the beginning of the germination test, were evaluated, resulting in values for seedling length, growth, development uniformity, vigor index and corrected vigor index. The evaluated lots with emergence greater than 90 % showed a vigor index higher than 600 and 800, respectively in the fourth and sixth days. The indexes generated by SAPL®, except for the uniformity index, presented positive and high correlations with the traditional tests (> 0.80). SAPL® is efficient in identifying differences in the vigor of soybean seed lots.

RESUMOOs principais testes que avaliam a qualidade de sementes são destrutivos e exigem um tempo relativamente longo para serem concluídos. A análise de imagens de sementes por meio de raios X representa uma alternativa para este setor, sendo uma técnica reproduzível e rápida, permite maior agilidade e autonomia nas atividades dos sistemas de produção. O objetivo deste trabalho foi analisar a morfologia interna de sementes de moringa por meio de imagens radiografadas e compará-la aos testes de germinação e vigor. Foram utilizados quatro lotes de sementes, coletadas em árvores-matrizes na região de Macaíba -RN, posteriormente radiografadas e as imagens analisadas através do software ImageJ e, após a radiografia, submetidas aos testes de germinação, primeira contagem e índice de velocidade de germinação e comprimento e massa seca de plântulas. O delineamento experimental utilizado foi o inteiramente casualizado, com quatro repetições por lote e os resultados obtidos neste experimento para os testes de germinação e vigor foram comparados com o percentual de área livre no interior da semente. Os lotes 1, 2 e 4 tiveram melhor resultado para os testes de germinação e vigor e o lote 3 mostrou-se de qualidade inferior. Observou-se que quanto maior a área livre no interior das sementes, menor a qualidade dos lotes de moringa testados. A análise de imagens radiografadas de sementes de moringa, com o software ImageJ, permite a mensuração das áreas preenchidas e áreas livres no interior da semente assim como a associação entre estas e a germinação. Danos internos severos, malformação e grau de preenchimento detectados nos raios X podem ser associados à baixa germinação e à redução do comprimento de plântulas. Palavras-chave: germinação; imagens digitais; vigor; raios X. ABSTRACTThe main tests that assess the quality of seeds are destructive and require a relatively long time to complete. The analysis of seed images by X-ray is an alternative to this sector, with a reproducible and fast technique, which allows greater flexibility and autonomy to the activities of production systems. The aim of this study was to analyze the internal morphology of Moringa seeds by x-rayed images and to compare it to germination and vigor tests. Four seed lots were used, collected from trees matrixes in Macaíba region, RN state, and subsequently X-rayed and the images were analyzed using ImageJ software after the radiography, submitted to the germination test, first count, germination speed index and length and dry mass of seedlings. The experimental design was completely randomized, with four replicates per lot and the results obtained in this experiment for germination and vigor tests were compared with the free area percentage inside the seed. Lots 1, 2 and 4 had a better result for the germination and vigor tests and lot 3 proved to be of inferior quality. It was observed that the higher the open area inside the seeds was, the lower was the quality of the tested lots of Moringa. The x-rayed image analysis of Moringa seeds with the ImageJ so...

New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. the aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. in addition, we correlated the appearance of seeds to their physiological performance. images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. the appearance of soybean seeds is strongly correlated with their physiological performance.

In the agricultural industry, advances in optical imaging technologies based on rapid and non-destructive approaches have contributed to increase food production for the growing population. The present study employed autofluorescence-spectral imaging and machine learning algorithms to develop distinct models for classification of soybean seeds differing in physiological quality after artificial aging. Autofluorescence signals from the 365/400 nm excitation-emission combination (that exhibited a perfect correlation with the total phenols in the embryo) were efficiently able to segregate treatments. Furthermore, it was also possible to demonstrate a strong correlation between autofluorescence-spectral data and several quality indicators, such as early germination and seed tolerance to stressful conditions. The machine learning models developed based on artificial neural network, support vector machine or linear discriminant analysis showed high performance (0.99 accuracy) for classifying seeds with different quality levels. Taken together, our study shows that the physiological potential of soybean seeds is reduced accompanied by changes in the concentration and, probably in the structure of autofluorescent compounds. In addition, altering the autofluorescent properties in seeds impact the photosynthesis apparatus in seedlings. From the practical point of view, autofluorescence-based imaging can be used to check modifications in the optical properties of soybean seed tissues and to consistently discriminate high-and low-vigor seeds.