Abstract
In the food and agricultural industries, it is crucial to identify and to choose correct sunflower seeds that meet specific requirements. Deep learning and computer vision methods can help identify sunflower seeds. In this study, a computer vision system was proposed, trained, and tested to identify four varieties of sunflower seeds using deep learning methodology and a regular color camera. Image acquisition was carried out under controlled illumination conditions. An image segmentation procedure was employed to reduce the workload in obtaining training images required for training deep convolutional neural network models. Three deep learning architectures, namely AlexNet, GoogleNet, and ResNet, were investigated for identifying sunflower seeds in this study. Different solver types were also evaluated to determine the best deep learning model in terms of both accuracy and training time. About 4800 sunflower seeds were inspected individually for training and testing. The highest classification accuracy (95%) was succeeded with the GoogleNet algorithm.
Similar content being viewed by others
References
FAO, Food and agriculture organization of the United Nations. https://www.fao.org/faostat/en/#data/QC. Accessed 23 Oct 2019.
F.M. Anjum, M. Nadeem, M.I. Khan, S. Hussain, Br. Food. J. 114(4), 544–552 (2012)
A. Zehra, Z.A. Sahito, W. Tong, L. Tang, Y. Hamid, Q. Wang, X. Cao, M.B. Khan, B. Hussain, S.A. Jatoi, Z. He, Ecotoxicol. Environ. Saf. 187, 109857 (2020)
P. Casadebaig, E. Mestries, P. Debaeke, Eur. J. Agron 81, 92–105 (2016)
L. Byczynski, Advantages & Disadvantages of Various Types of Sunflowers (Johnny's Selected Seeds, 2020) https://www.johnnyseeds.com/growers-library/flowers/library-flowers-choose-sunflowers.html. Accessed 7 Oct 2020
J. Paliwal, N.S. Shashidhar, D.S. Jayas, Trans. ASAE 42, 1921–1924 (1999)
K. Kiliç, I.H. Boyaci, H. Köksel, I. Küsmenoglu, J. Food Eng. 78(3), 897–904 (2007)
F. Avila, M. Mora, C. Fredes, Comput. Electron. Agric. 101, 76–83 (2014)
P. Zapotoczny, Int. J. Food Prop. 17, 139–151 (2014)
M.P. Arakeri, B. Lakshmana, Procedia Comput. Sci. 79, 426–433 (2016)
K.L. Tu, L.J. Li, L.M. Yang, J.H. Wang, Q. Sun, J. Integr. Agric. 17(9), 1999–2006 (2018)
A. Krizhevsky, I. Sutskever, G.E. Hinton, Adv. Neural Inform. Process. Syst. 25(2), 1097–1105 (2012)
D. Rong, L. Xie, Y. Ying, Comput. Electron. Agric. 162, 1001–1010 (2019)
K. Yanai, Y. Kawano, ICMEW (2015). https://doi.org/10.1109/ICMEW.2015.7169816
A. Tatsuma, M. Aono, IEICE Trans. Inf. Syst. E99D(6), 1711–1715 (2016)
L. Bossard, M. Guillaumin, L. Van-Gool, Lecture Notes in Computer Science, 1st edn. (Springer, Cham, 2014), pp. 446–461
C. Ni, D. Wang, R. Vinson, M. Holmes, Y. Tao, Biosyst. Eng. 178, 131–144 (2019)
P. Nie, J. Zhang, X. Feng, C. Yu, Y. He, Sens. Actuators B 296, 126630 (2019)
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Proc. CVPR IEEE (2015). https://doi.org/10.1109/CVPR.2015.7298594
K. He, X. Zhang, S. Ren, J. Sun, Proc. CVPR IEEE (2016). https://doi.org/10.1109/CVPR.2016.90
A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, P. Martinez-Gonzalez, J. Garcia-Rodriguez, Appl. Soft. Comput. 70, 41–65 (2018)
M.D. Zeiler, ADADELTA: An Adaptive Learning Rate Method.
J. Yu, S.M. Sharpe, A.W. Schumann, N.S. Boyd, Eur. J. Agron. 104, 78–84 (2019)
S. Sigtia, S. Dixon, IEEE Trans. Multimedia (2014). https://doi.org/10.1109/ICASSP.2014.6854949
M.K. Uçar, M. Nour, H. Sindi, K. Polat, Math. Probl. Eng (2020). https://doi.org/10.1155/2020/2836236
J. Makhoul, F. Kubala, R. Schwartz, R. Weischedel, in Proceedings of DARPA Broadcast News Workshop, 1st edn. (Morgan Kaufmann Pub, Burlington, 1999), pp. 249–252
D.M.W. Powers, J. Mach. Learn. Technol. 2, 37–63 (2011)
Acknowledgements
The author is grateful to Prof. Dr. Mehmet Sincik, a researcher in the Dept. of Field Crops, Agriculture Faculty, Bursa Uludag University, for kindly providing the seeds of Helianthus annulus L.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kurtulmuş, F. Identification of sunflower seeds with deep convolutional neural networks. Food Measure 15, 1024–1033 (2021). https://doi.org/10.1007/s11694-020-00707-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11694-020-00707-7