Abstract
Common bean (Phaseolus vulgaris L.) is an essential grain legume for human consumption, as it is a low-cost source of dietary proteins. New bean varieties are created through genetic improvements to guarantee food security in marginal areas. They have to adapt to drought stress conditions and be resistant to different diseases. Bean quality assessments are qualitative and usually performed through visual inspection, making them subjective, laborious, time-consuming, and error-prone. In this paper, we propose an automatic bean classification system for supporting bean quality evaluation during seed breeding. Our system incorporates a protocol for bean image acquisition, a method for segmenting bean seeds using a combination of thresholding and watershed methods, and a classification method based on supervised learning with phenotype features. We validated our proposed system using 600 images of 6 bean varieties with variations regarding colour, shape, size, and reflectance. Our experimental results showed that our proposal outperformed a state-of-the-art approach based on artificial neural networks (accuracy, 98.5% vs 87.3%). Therefore, the proposed system seems suitable for classifying beans during seed breeding.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
A. Nasirahmadi, N. Behroozi-Khazaei, Identification of bean varieties according to color features using artificial neural network. Spanish J Agric Res 11, 670–677 (2013)
O. Voysest, Mejoramiento genético del frijol (Phaseolus vulgaris L.): legado de variedades de América Latina, 1930–1999 (2000).
J. Arias, T. Rengifo, M. Jaramillo, Manual técnico: buenas prácticas agrícolas (BPA) en la producción de frijol voluble, 1st edn. (Print Ltda, La selva, Medellín, Colombia, 2007)
K. Kılıç, İ.H. Boyacı, H. Köksel, İ. Küsmenoğlu, A classification system for beans using computer vision system and artificial neural networks. J. Food Eng. 78, 897–904 (2007)
G. Venora, O. Grillo, C. Ravalli, R. Cremonini, Tuscany beans landraces, on-line identification from seeds inspection by image analysis and linear discriminant analysis. Agrochimica 51(4-5), 254–268 (2007)
G. Venora, O. Grillo, C. Ravalli, R. Cremonini, Identification of italian lanraces of bean (phaseolus vulgarisl.) using an image analysis system. Scientia Horticulturae 121(4), 410–418 (2009)
K. Murat, A. Ilker, Multiclass classification of dry beans using computer vision and machine learning techniques. Comput. Electron. Agric. 174, 105507 (2020)
S.A. De Araújo, J.H. Pessota, H.Y. Kim, Beans quality inspection using correlation-based granulometry. Eng. Appl. Artif. Intel. 40, 84–94 (2015)
P.A. Belan, S. Araújo, W.A.L. Alves, An intelligent vision-based system applied to visual quality inspection of beans. In: International Conference Image Analysis and Recog-nition, pp. 801–809, Springer (2016).
Beucher, S., Lantuéjoul, C.: Use of Watersheds in Contour Detection, (1979).
N. Otsu, A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)
M. Garcia, M. Trujillo, D. Chaves, Global and local features for bean image classification. In: 7th Latin American Conference on Networked and Electronic Media (LACNEM 2017), pp. 1–6, (2017).
A. Criminisi, J. Shotton. Decision forests for computer vision and medical image analysis. Springer Science & Business Media, Berlin (2013) https://doi.org/10.1007%2F978-1-4471-4929-3
F. Tang, H. Lu, T. Sun, X. Jiang, Efficient image classification using sparse coding and random forest. In: 2012 5th International Congress on Image and Signal Processing, pp. 781–785 (2012).
D.M. Powers, Evaluation: from precision, recall and f-measure to ROC, informedness, markedness and correlation. J. Mach. Learn. Technol. 2, 37–63 (2011)
Acknowledgements
We would like to thank the bean inspectors from the CIAT for detailing the bean inspection process and helping with image acquisition.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Garcia, M., Chaves, D., Trujillo, M. (2022). An Automatic Bean Classification System Based on Visual Features to Assist the Seed Breeding Process. In: Johri, P., Diván, M.J., Khanam, R., Marciszack, M., Will, A. (eds) Trends and Advancements of Image Processing and Its Applications. EAI/Springer Innovations in Communication and Computing. Springer, Cham. https://doi.org/10.1007/978-3-030-75945-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-75945-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75944-5
Online ISBN: 978-3-030-75945-2
eBook Packages: EngineeringEngineering (R0)