Imagens de Raios X e YOLOv8 para Avaliação Automatizada, Precisa e Não Destrutiva da Qualidade de Sementes Braquiária (Urochloa brizantha)

• Rafael Capelo Domingues UFC
• Gabriel Vasconcelos Fruet UFC
• Haynna Fernandes Abud UFC
• Danielo G. Gomes UFC

DOI: https://doi.org/10.5753/sbiagro.2023.26555

Abstract

Seed quality is crucial in agriculture. Companies that produce seeds are concerned about finding rapid tests that accurately assess seed vigor, and the time it takes to conduct these tests is a limiting factor. Here we apply the YOLOv8 model to quickly, automatically, and non-destructively evaluate the physiological potential of seeds. The proposed method uses radiographic images of brachiaria seeds (Urochloa brizantha) to identify and classify them based on their physiological quality. The YOLOv8 network was trained with a dataset of seed images, and the results demonstrated high accuracy in identifying and classifying the seeds, with mAP50 and mAP50-95 metrics of 90.6% and 90.1%, respectively, for all classes.

References

Abud, H. F., Cicero, S. M., and Gomes Junior, F. G. (2018). Radiographic images and relationship of the internal morphology and physiological potential of broccoli seeds. Acta Scientiarum. Agronomy, 40(Acta Sci., Agron., 2018 40):e34950.

Bochkovskiy, A., Wang, C., and Liao, H. M. (2020). Yolov4: Optimal speed and accuracy of object detection. CoRR, abs/2004.10934.

de Freitas, M. N., Dias, M. A. N., Gomes-Junior, F. G., Abud, H. F., de Araújo, L. B., and de Moraes, T. F. (2021). Discrimination of urochloa seed genotypes through image analysis: Morphological features. Agronomy Journal, 113(6):4930–4944.

Jeromini, T. S., Martins, C. C., Pereira, F. E. C. B., and Gomes, F. G. (2019). The use of x-ray to evaluate brachiaria brizantha seeds quality during seed processing. Revista Ciência Agronômica, 50(Rev. Ciênc. Agron., 2019 50(3)):439–446.

Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLO by Ultralytics.

Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T., editors, Computer Vision – ECCV 2014, pages 740–755, Cham. Springer International Publishing.

Ramos, A. K. F., Medeiros, A. D. d., Pereira, M. D., Araújo, Y. F., Silva, L. J. d., and Alves, C. Z. (2022). Sars software for analysis of radiographic images of urochloa decumbens (stapf) rd webster seeds. Journal of Seed Science, 44:e202244045.

Silva, A., de Oliveira, L., Pereira da Silva, C., Tiago, C., Mendes, E., Ferreira, A., Safadi, T., and Carvalho, M. (2022). Seed quality of brachiaria brizantha by x-ray image analysis using a bayesian approach. Acta Scientiarum Agronomy, 44:2022.

Sudki, J. M., Fonseca de Oliveira, G. R., de Medeiros, A. D., Mastrangelo, T., Arthur, V., Amaral da Silva, E. A., and Mastrangelo, C. B. (2023). Fungal identification in peanuts seeds through multispectral images: Technological advances to enhance sanitary quality. Frontiers in Plant Science, 14.