Convolutional Neural Networks to Identify Plant Nutrient Deficiencies
Keywords:
Nutrient deficiency leaf, image analysis, machine learning, CNN, ANN, DenseNet121.Abstract
A brand-new image processing technique is suggested for determining nutritional shortages in plants based on their leaves. The suggested solution begins by dividing the input leaf picture into manageable chunks. Second, a group of convolutional neural networks are given each block of leaf pixels (CNNs). The CNNs are used to determine whether a block is displaying any symptoms of the related nutritional shortage. Each CNN is uniquely trained for a distinct nutrient shortfall. The results from all CNNs are then combined using a winner-take-all method to get a single response for the block. Finally, a multi-layer perceptron is used to combine all of the replies into one to create a final response for the entire leaf. On a group of black gramme (Vigna mungo) plants cultivated in nutrient-controlled conditions, the suggested method's validity was tested. Study subjects included a set of plants with full nutritional profiles as well as five different forms of deficits, including Ca, Fe, K, Mg, and N shortages. For the purpose of the experiment, 3,000 photographs of leaves were gathered as a dataset. The suggested technology is superior to trained humans in identifying nutritional deficiencies, according to experimental data. Nutrients in the soil are vital for plants to survive. In some circumstances, such as when there is a lack of nitrogen or phosphorus in the environment, the plant can transfer these nutrients from old tissue to new tissue. This study aimed to examine how various nutritional shortages affected development over a four-week period. Over the course of the experiment, it was found that deficiencies in nitrogen, phosphorus, and all other nutrients significantly affected the ability of plants to grow. Comparing the nitrogen- and phosphorus-deficient treatments with the full nutritional treatment revealed notable variations in standard chlorophyll levels as well. These findings suggested that nutrient mobility cannot entirely compensate for an environmental nutrient shortfall; rather, it can only support the plant's attempt to survive the deficiency.
References
- A. Camargo and J.S. Smith, “An image-processing based algorithm to automatically identify plant disease visual symptoms,” Biosystems Engineering, vol.102, pp.9–21, January 2009.
- J.S. Cope, D. Corney, J.Y. Clark, P. Remagnino, and P. Wilkin, “Plant species identification using digital morphometrics: A review,” Expert Systems with Applications, vol.39, pp.7562–7573, June 2012.
- J. Garcia and A. Barbedo, “Using digital image processing for counting whiteflies on soybean leaves,” Journal of Asia-Pacific Entomology, vol.17, pp.685–694, December 2014.
- A. Gongal, S. Amatya, M. Karkee, Q. Zhang, and K. Lewis, “Sensors and systems for fruit detection and localization: A review,” Computers and Electronics in Agriculture, vol.116, pp.8–19, August 2015.
- I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
- J. Hemming and T. Rath, “Computer-vision-based weed identification under field conditions using controlled lighting,” Journal of Agricultural Engineering Research, vol.78, no.3, pp.233–243, March 2001
- S. Ji-Yong, Z. Xiao-Bo, Z. Jie-Wen, W. Kai-Liang, C. Zheng-Wei et al., “Nondestructive diagnostic of nitrogen deficiency by cucumber leaf chlorophyll distribution map based on near infrared hyperspectral imaging,” Scientia Horticulturae, vol.138, pp.190–197, May 2012.
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Proceedings of 25th Advances in Neural Information Processing Systems (NIPS 2012), pp. 1097–1105,2012.
- C. Leksomboon, Plant Disease and Diagnosis, Kasetsart University Press, 2011 (in Thai).
- P. Li, S.H. Lee, and H.Y. Hsu “Review on fruit harvesting method for potential use of automatic fruit harvesting systems,” Procedia Engineering, vol.23, pp.351–366, 2011.
- T. Liu, W. Chen, W. Wu, C. Sun, W. Guo, and X. Zhu, “Detection of aphids in wheat fields using a computer vision technique,” Biosystems Engineering, vol.141, pp.82–93, January 2016.
- P. Noinongyao, U. Watchareeruetai, P. Khantiviriya, C. Wattanapaiboonsuk, and S. Duangsrisai, “Separation of abnormal regions on black gram leaves using image analysis,” Proceedings of the 2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE 2017), 2017.
- L.M. Romualdo, P.H.C. Luz, F.F.S. Devechio, M.A. Marin, A.M.G. Zu´niga, O.M. Bruno, and V.R. Herling, “Use of artificial vision tech- ˜ niques for diagnostic of nitrogen nutritional status in maize plants,” Computers and Electronics in Agriculture, vol.104, pp.63–70, June 2014.
- S. Sankaran, A. Mishra, R. Ehsani, and C. Davis, “A review of advanced techniques for detecting plant diseases,” Computers and Electronics in Agriculture, vol.72, pp.1–13, June 2010.
- Y. Song, C.A. Glasbey, G.W. Horgan, G. Polder, J.A., Deleman, G.W.A.M. van der Heijden, “Automatic fruit recognition and counting from multiple images,” Biosystems Engineering, vol.118, pp.203–215, February 2014.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.