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, Fm, and Fv/Fm) 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).

The sanitary quality of seed is essential in agriculture. This is because pathogenic fungi compromise seed physiological quality and prevent the formation of plants in the field, which causes losses to farmers. Multispectral images technologies coupled with machine learning algorithms can optimize the identification of healthy peanut seeds, greatly improving the sanitary quality. The objective was to verify whether multispectral images technologies and artificial intelligence tools are effective for discriminating pathogenic fungi in tropical peanut seeds. For this purpose, dry peanut seeds infected by fungi (A. flavus, A. niger, Penicillium sp., and Rhizopus sp.) were used to acquire images at different wavelengths (365 to 970 nm). Multispectral markers of peanut seed health quality were found. The incubation period of 216 h was the one that most contributed to discriminating healthy seeds from those containing fungi through multispectral images. Texture (Percent Run), color (CIELab L*) and reflectance (490 nm) were highly effective in discriminating the sanitary quality of peanut seeds. Machine learning algorithms (LDA, MLP, RF, and SVM) demonstrated high accuracy in autonomous detection of seed health status (90 to 100%). Thus, multispectral images coupled with machine learning algorithms are effective for screening peanut seeds with superior sanitary quality.

Os recentes avanços nas tecnologias de imagens ópticas têm contribuído para a análise rápida, precisa e não destrutiva no contexto da qualidade de sementes. Este trabalho teve como objetivo verificar a potencialidade de imagens de fluorescência de clorofila como um novo marcador para análise do potencial fisiológico de sementes de amendoim. Os sinais de fluorescência da clorofila a e b foram detectados nas combinações de excitação/emissão de 630/700 nm e 405/600 nm, respetivamente, utilizando sementes envelhecidas artificialmente por 0, 16, 24 e 48 horas. As imagens foram capturadas com o equipamento VideometerLab4 (Videometer A/S, Herlev, Dinamarca), software versão 5.4.6. Os dados foram comparados com os testes analíticos tradicionais utilizados para avaliação do desempenho fisiológico de sementes de amendoim, como testes de germinação, condutividade elétrica, emergência de plântulas e índice de emergência. Os resultados revelaram que a intensidade da fluorescência da clorofila a e b foi menor para as sementes de menor vigor. Portanto, o processo de deterioração das sementes de amendoim é acompanhado de quebra de moléculas de clorofila, e consequentemente, em alterações em propriedades fluorescentes das sementes. Do ponto de vista prático, a imagem de fluorescência de clorofila pode ser utilizada com sucesso para discriminar lotes de sementes de alto e baixo vigor, de forma rápida, precisa e não destrutiva.