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

Document Type : Original Research

Authors
Eli Veiga Junior 1
Sidnei Alves de Araújo 1
Alessandro Melo Deana 2
1 Informatics and Knowledge Management Post-Graduation Program, Nove de Julho University (UNINOVE), Vergueiro Street 235/249, São Paulo 01504-001, Brazil.
2 Informatics and Knowledge Management Post-Graduation Program, Nove de Julho University (UNINOVE), Vergueiro Street 235/249, São Paulo 01504-001, Brazil. 2 Biophotonics Applied to Health Sciences Graduate Program, Nove de Julho University (UNINOVE), Vergueiro Street 235/249, São Paulo 01504-001, Brazil.
10.48311/jast.2026.24094
Abstract
In their early stages, germination of bean 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 bio-speckle 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
Computer vision
Convolutional neural network
Laser speckle image
Subjects
1.       Ansari, M. Z., Da Silva, L. C., Da Silva, J. V. P. and Deana, A. M. 2016. Modelling Laser Speckle Photographs of Decayed Teeth by Applying a Digital Image Information Technique. Laser Phys., 26(9): 095602.
2.       Belan, P. A., de Macedo, R. A. G., Alves, W. A. L., Santana, J. C. C. And Araujo, S. A. 2020. Machine Vision System for Quality Inspection of Beans. Int. J. Adv. Manuf. Technol., 111: 3421-3435.
3.       Braga Jr, R. A., Rabelo, G. F., Granato, L. R., Santos, E. F., Machado, J. C., Arizaga, R. And Trivi, M. 2005. Detection of Fungi in Beans by the Laser Biospeckle Technique. Biosyst. Eng., 91(4): 465-469.
4.       Bravo, D. T., Lima, G. A., Alves, W. A. L., Colombo, V. P., Djogbenou, L., Pamboukian, S. V. D. and de Araujo, S. A. 2021. Automatic Detection of Potential Mosquito Breeding Sites from Aerial Images Acquired by Unmanned Aerial Vehicles. Comput. Environ. Urban Syst., 90: 101692.
5.       Briers, J. D. and Webster, S. 1996. Laser Speckle Contrast Analysis (LASCA): A Nonscanning, Full-Field Technique for Monitoring Capillary Blood Flow. J. Biomed. Opt., 1(2): 174-179.
6.       Contado, J. L., de Faria Silva, C. And Júnior, R. A. B. 2020. Biospeckle Laser to Monitor the Germination of Angico-Vermelho Seeds. Theor. Appl. Eng., 4(4): 1-9.
7.       Deana, A. M., Jesus, S. H. C., Koshoji, N. H., Bussadori, S. K. and Oliveira, M. T. 2013. Detection of Early Carious Lesions Using Contrast Enhancement with Coherent Light Scattering (Speckle Imaging). Laser Phys., 23(7): 075607.
8.        EMBRAPA. 2008. Manual de Classificação do Feijão Instrução Normativa n° 12, de 28 de Março de 2008. Disponível em: .
9.       Gavinho, L. G., Araujo, S. A., Bussadori, S. K., Silva, J. V. and Deana, A. M. 2018. Detection of White Spot Lesions by Segmenting Laser Speckle Images Using Computer Vision Methods. Laser Med. Sci., 33: 1565-1571.
10.    Goodman, J. W. 1975. Statistical Properties of Laser Speckle Patterns. In: “Laser Speckle and Related Phenomena”. Springer, Heidelberg, Berlin.
11.    Koshoji, N. H., Bussadori, S. K., Bortoletto, C. C., Prates, R. A., Oliveira, M. T. And Deana, A. M. 2015. Laser Speckle Imaging: a Novel Method for Detecting Dental Erosion. PloS One, 10(2): e0118429.
12.    Koshoji, N. H., Prates, R. A., Bussadori, S. K., Bortoletto, C. C., de Miranda Junior, W. G., Librantz, A. F., Leal C. R., Oliveira, M. T. and Deana, A. M. 2016. Relationship between Analysis of Laser Speckle Image and Knoop Hardness on Softening Enamel. Photodiagnosis Photodyn. Ther., 15: 139-42.
13.    Kurokawa e Silva, G., Aguiar, R. H., Oliveira, R. A. D. and Fabbro, I. M. D. 2020. Indirect Determination of Moisture Using Biospeckle Technique. Rev. Ciênc. Agron., 51(1): 1-5.
14.    Maaten, L. V. D. and Hinton, G. 2008. Visualizing Data Using t-SNE. J. Mach. Learn. Res., 9: 2579-2605.
15.     MAPA. 2018. Ministério da Agricultura Pecuária e Abastecimento. Disponível em: , Acesso em: 04 Maio 2018.
16.    Olivan, S. R. G., Deana, A. M., Pinto, M. M., Sfalcin, R. A., Fernandes, K. P. S., Mesquita-Ferrari, R. A., Prates, R. A. And Bussadori, S. K. 2017. Diagnosis of Occlusal Caries Lesions in Deciduous Molars by Coherent Light Scattering Pattern Speckle. Photodiagnosis Photodyn. Ther., 18: 221-225.
17.    Peixoto, L. S., Silva, G. M., Fujii, A. K., Parisi, J. J. D., Aguiar, R. H. and Fracarolli, J. A. 2018. Maize Seeds Submitted to Thermotherapy and Analyzed by Dynamic Speckle. J.  Agric. Sci. Technol. B, 8(2): 115-121.
18.    Rabelo, G. F., Enes, A. M., Junior, R. A. B. and Dal Fabbro, I. M. 2011. Frequency Response of Biospeckle Laser Images of Bean Seeds Contaminated by Fungi. Biosyst. Eng., 110(3): 297-301.
19.    Shorten, C. and Khoshgoftaar, T. M. 2019. A Survey on Image Data Augmentation for Deep Learning. J. Big Data, 6(1): 1-48.
20.    Silva, G. M., Peixoto, L. S., Fujii, A. K., Parisi, J. J. D., Aguiar, R. H. and  Fracarolli, J. A. 2018. Evaluation of Maize Seeds Treated with Trichodermil® through Biospeckle. J. Agric. Sci. Technol. B, 8(2): 175-187.
21.    Silva, J. V. P. D., Sfalcin, R. A., Andrianarijaona, V. M., Gavinho, L. G., Salviatto, L. T. C., Bussadori, S. K. and Deana, A. M. 2020. Detection of Carious Lesion by Laser Speckle Analysis Using the First Order Moment. Res. Soc. Dev., 9(12): 1-15.
22.    Singh, P., Chatterjee, A., Bhatia, V. and Prakash, S. 2020. Application of Laser Biospeckle Analysis for Assessment of Seed Priming Treatments. Comput. Electron. Agric., 169: 105212.
23.    Singh, P., Chatterjee, A., Bhatia, V., and Prakash, S. 2018. Viability Assessment of Kidney Bean Seed (Phaseolus vulgaris sp.) Using Robust Biospeckle Indexing Technique. In Workshop on Computational Models of Natural Argument. Springer, Singapore, PP. 189-195.
24.    Thakur, P. S., Chatterjee, A., Rajput, L. S., Rana, S., Bhatia, V. and Prakash, S. 2022. Laser Biospeckle Technique for Characterizing the Impact of Temperature and Initial Moisture Content on Seed Germination. Opt. Laser Eng., 153: 106999.
25.    Vargas-Canales, J. M., Brambila-Paz, J. D. J., Pérez-Cerecedo, V., Rojas-Rojas, M. M., López-Reyna, M. D. C. and Omaña-Silvestre, J. M. 2022. Trends in Science, Technology, and Innovation in the Agri-Food Sector. Tapuya Lat. Am. Sci. Technol. Soc., 5(1): 2115829.
26.    Xia, Y., Xu, Y., Li, J., Zhang, C. and Fan, S. 2019. Recent Advances in Emerging Techniques for Non-Destructive Detection of Seed Viability: A Review. Artif. Intell. Agric., 1: 35-47.
 
Journal of Agricultural Science and Technology
Volume 28, Issue 3
May and June 2026
Pages 679-698