Hinting Pipeline and Multivariate Regression CNN for Maize Kernel Counting on the Ear (2306.06553v1)
Abstract: Maize is a highly nutritional cereal widely used for human and animal consumption and also as raw material by the biofuels industries. This highlights the importance of precisely quantifying the corn grain productivity in season, helping the commercialization process, operationalization, and critical decision-making. Considering the manual labor cost of counting maize kernels, we propose in this work a novel preprocessing pipeline named hinting that guides the attention of the model to the center of the corn kernels and enables a deep learning model to deliver better performance, given a picture of one side of the corn ear. Also, we propose a multivariate CNN regressor that outperforms single regression results. Experiments indicated that the proposed approach excels the current manual estimates, obtaining MAE of 34.4 and R2 of 0.74 against 35.38 and 0.72 for the manual estimate, respectively.
- T. Shah, K. Prasad, and P. Kumar, “Maize – a potential source of human nutrition and health: A review,” Cogent-Food and Agriculture, vol. 2, pp. 1–9, 2016.
- S. Khaki, H. Pham, Y. Han, A. Kuhl, W. Kent, and L. Wang, “Convolutional neural networks for image-based corn kernel detection and counting,” MDPI Sensors, vol. 20, no. 9, p. 2721, 2020.
- X. Li, B. Dai, H. Sun, and W. Li, “Corn classification system based on computer vision,” MDPI Symmetry, vol. 11, no. 4, p. 591, 2019.
- A. D. Severini, L. Borrás, and A. G. Cirilo, “Counting maize kernels through digital image analysis,” Crop Science, vol. 51, no. 6, pp. 2796–2800, 2011.
- Y. Zhang, W. Wu, and G. Wang, “Separation of corn seeds images based on threshold changed gradually,” Transactions of the Chinese Society of Agricultural Engineering, vol. 27, no. 7, pp. 200–204, 2011.
- N. D. Miller, N. J. Haase, J. Lee, S. M. Kaeppler, N. de Leon, and E. P. Spalding, “A robust, high-throughput method for computing maize ear, cob, and kernel attributes automatically from images,” The Plant Journal, vol. 89, no. 1, pp. 169 – 178, 2017.
- T. E. Grift, W. Zhao, M. A. Momin, Y. Zhang, and M. O. Bohn, “Semi-automated, machine vision based maize kernel counting on the ear,” Elsevier Biosystems Engineering, vol. 164, pp. 171–180, 2017.
- S. Khaki, H. Pham, Y. Han, A. Kuhl, W. Kent, and L. Wang, “Deepcorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation,” Elsevier Knowledge-Based Systems, vol. 218, p. 106874, 2021.
- A. M. Reza, “Realization of the contrast limited adaptive histogram equalization (clahe) for real-time image enhancement,” J. VLSI Signal Process. Syst., vol. 38, no. 1, p. 35–44, Aug. 2004.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 770–778.
- C. Alvares, J. Stape, P. Sentelhas, J. Gonçalves, and G. Sparovek, “Köppen’s climate classification map for brazil,” Stuttgart Meteorologische Zeitschrift, vol. 22, no. 6, pp. 711–728, 2013.
- D. Kingma and J. Ba, “Adam: A method for stochastic optimization,” International Conference on Learning Representations, 2014.
- H. B. Mann and D. R. Whitney, “On a test of whether one of two random variables is stochastically larger than the other,” JSTOR - The Annals of Mathematical Statistics, pp. 50–60, 1947.
- A. Vargha and H. D. Delaney, “The kruskal-wallis test and stochastic homogeneity,” Journal of Educational and Behavioral Statistics, vol. 23, no. 2, pp. 170–192, 1998.
- K. Simonyan, A. Vedaldi, and A. Zisserman, “Deep inside convolutional networks: Visualising image classification models and saliency maps,” arXiv preprint arXiv:1312.6034, 2013.