Non-Invasive Detection of Early Germination in Beans Using Laser Speckle Temporal Analysis and Deep Learning

Articles in Press
Author
A. Deana
Uninove
Abstract
The visual quality control of bean grains is currently conducted manually and relies heavily on identifying surface-level defects to classify the product type. Among these defects, germinated grains pose a unique challenge: in their early stages, germination is not externally visible, requiring invasive methods such as physically breaking the seed for detection. This study proposes a non-invasive and automated approach that combines laser speckle imaging with deep learning to identify early-stage germinated defects in beans. Speckle images were captured under coherent laser illumination (λ = 633 nm) for samples subjected to germination periods of 0, 6, 12, and 24 hours. Two contrast analysis techniques were evaluated: Laser Speckle Spatial Contrast Analysis (LASCA) and the more advanced Laser Speckle Temporal Contrast Analysis (LASTCA), the latter using temporal intensity fluctuations across 120 video frames. From the resulting contrast maps, regions of interest (50×50 pixels) were extracted and used to train a Convolutional Neural Network (CNN) for binary classification. The proposed system achieved high performance, with an accuracy of 92.33% and sensitivity of 98.21%, successfully detecting germinated defects invisible to conventional inspection. By integrating temporal biospeckle analysis with deep learning, this method offers a scalable solution for intelligent, non-destructive grain inspection—addressing a critical gap in current computer vision systems and contributing to the advancement of Agribusiness 4.0.



Keywords

Subjects

[1] Vargas-Canales, J. M., Brambila-Paz, J. D. J., Pérez-Cerecedo, V., Rojas-Rojas, M. M., López-Reyna, M. D. C., & Omaña-Silvestre, J. M. (2022). Trends in science, technology, and innovation in the agri-food sector. Tapuya: Latin American Science, Technology and Society, 5(1), 2115829.
[2] EMBRAPA – Manual de Classificação do Feijão Instrução Normativa n° 12, de 28 de março de 2008. [s.l.: s.n.], 2012. Disponível em: <www.cnpaf.embrapa.br>.
[3] MAPA – Ministério da Agricultura Pecuária e Abastecimento. disponível em: <http://www.agricultura.gov.br/>, Acesso em: 04 maio 2018.
[4] Belan, P. A., de Macedo, R. A. G., Alves, W. A. L., Santana, J. C. C., & Araujo, S. A. (2020). Machine vision system for quality inspection of beans. The International Journal of Advanced Manufacturing Technology, 111, 3421-3435.
[5] Deana, A. M., Jesus, S. H. C., Koshoji, N. H., Bussadori, S. K., & Oliveira, M. T. (2013). Detection of early carious lesions using contrast enhancement with coherent light scattering (speckle imaging). Laser Physics, 23(7), 075607.
[6] Koshoji, N. H., Bussadori, S. K., Bortoletto, C. C., Prates, R. A., Oliveira, M. T., & Deana, A. M. (2015). Laser speckle imaging: a novel method for detecting dental erosion. PloS one, 10(2), e0118429.
[7] Olivan, S. R. G., Sfalcin, R. A., Fernandes, K. P. S., Ferrari, R. A. M., Horliana, A. C. R. T., Motta, L. J., ... & Bussadori, S. K. (2020). Preventive effect of remineralizing materials on dental erosion lesions by speckle technique: an in vitro analysis. Photodiagnosis and photodynamic therapy, 29, 101655.
[8] Ansari, M. Z., Da Silva, L. C., Da Silva, J. V. P., & Deana, A. M. (2016). Modelling laser speckle photographs of decayed teeth by applying a digital image information technique. Laser Physics, 26(9), 095602.
[9] Gavinho, L. G., Araujo, S. A., Bussadori, S. K., Silva, J. V., & Deana, A. M. (2018). Detection of white spot lesions by segmenting laser speckle images using computer vision methods. Lasers in Medical Science, 33, 1565-1571.
[10] Olivan, S. R. G., Deana, A. M., Pinto, M. M., Sfalcin, R. A., Fernandes, K. P. S., Mesquita-Ferrari, R. A., ... & Bussadori, S. K. (2017). Diagnosis of occlusal caries lesions in deciduous molars by coherent light scattering pattern speckle. Photodiagnosis and Photodynamic Therapy, 18, 221-225.
[11] Koshoji, N. H., Prates, R. A., Bussadori, S. K., Bortoletto, C. C., de Miranda Junior, W. G., Librantz, A. F., ... & Deana, A. M. (2016). Relationship between analysis of laser speckle image and Knoop hardness on softening enamel. Photodiagnosis and Photodynamic Therapy, 15, 139-142.
[12] Silva, J. V. P. D., Sfalcin, R. A., Andrianarijaona, V. M., Gavinho, L. G., Salviatto, L. T. C., Bussadori, S. K., & Deana, A. M. (2020). Detection of carious lesion by laser speckle analysis using the first order moment.
[13] Silva, G. M., Peixoto, L. S., Fujii, A. K., Parisi, J. J. D., Aguiar, R. H., & Fracarolli, J. A. (2018). Evaluation of maize seeds treated with Trichodermil® through biospeckle. Journal of Agricultural Science and Technology, 8, 175-187..
[14] Peixoto, L. S., Silva, G. M., Fujii, A. K., Parisi, J. J. D., Aguiar, R. H., & Fracarolli, J. A. (2018). Maize Seeds Submitted to Thermotherapy and Analyzed by Dynamic Speckle. Journal of Agricultural Science and Technology B, 8(2), 115-121.
[15] Xia, Y., Xu, Y., Li, J., Zhang, C., & Fan, S. (2019). Recent advances in emerging techniques for non-destructive detection of seed viability: A review. Artificial Intelligence in Agriculture, 1, 35-47.
[16] Singh, P., Chatterjee, A., Bhatia, V., & Prakash, S. (2020). Application of laser biospeckle analysis for assessment of seed priming treatments. Computers and electronics in agriculture, 169, 105212.
[17] Kurokawa e Silva, G., Aguiar, R. H., Oliveira, R. A. D., & Fabbro, I. M. D. (2020). Indirect determination of moisture using biospeckle technique. Revista Ciência Agronômica, 51.
[18] Contado, J. L., de Faria Silva, C., & Júnior, R. A. B. (2020). BIOSPECKLE LASER TO MONITOR THE GERMINATION OF ANGICO-VERMELHO SEEDS. Theoretical and Applied Engineering, 4(4), 1-9.
[19] Singh, P., Chatterjee, A., Bhatia, V., & Prakash, S. (2018, November). Viability Assessment of Kidney Bean Seed (Phaseolus Vulgaris sp.) Using Robust Biospeckle Indexing Technique. In Workshop on Computational Models of Natural Argument (pp. 189-195). Singapore: Springer Singapore.
[20] Thakur, P. S., Chatterjee, A., Rajput, L. S., Rana, S., Bhatia, V., & Prakash, S. (2022). Laser biospeckle technique for characterizing the impact of temperature and initial moisture content on seed germination. Optics and Lasers in Engineering, 153, 106999.
[21] Braga Jr, R. A., Rabelo, G. F., Granato, L. R., Santos, E. F., Machado, J. C., Arizaga, R. & Trivi, M. (2005). Detection of fungi in beans by the laser biospeckle technique. Biosystems engineering, 91(4), 465-469.
[22] Rabelo, G. F., Enes, A. M., Junior, R. A. B., & Dal Fabbro, I. M. (2011). Frequency response of biospeckle laser images of bean seeds contaminated by fungi. Biosystems engineering, 110(3), 297-301.
[23] Goodman, J. W. (1975). Statistical properties of laser speckle patterns. In Laser speckle and related phenomena (pp. 9-75). Berlin, Heidelberg: Springer Berlin Heidelberg.
[24] Briers, J. D., & Webster, S. (1996). Laser speckle contrast analysis (LASCA): a nonscanning, full-field technique for monitoring capillary blood flow. Journal of biomedical optics, 1(2), 174-179.
[25] Bravo, D. T., Lima, G. A., Alves, W. A. L., Colombo, V. P., Djogbenou, L., Pamboukian, S. V. D., & de Araujo, S. A. (2021). Automatic detection of potential mosquito breeding sites from aerial images acquired by unmanned aerial vehicles. Computers, Environment and Urban Systems, 90, 101692.
[26] Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1-48.
Journal of Agricultural Science and Technology

Articles in Press, Accepted Manuscript
Available Online from 16 September 2025