Transfer Learning-Based Image Recognition of Nitrogen and Potassium Nutrient Stress in Rice

doi:10.1016/j.rsci.2023.01.002

Rice Science ›› 2023, Vol. 30 ›› Issue (2): 100-103.DOI: 10.1016/j.rsci.2023.01.002

• Letter • Previous Articles Next Articles

Transfer Learning-Based Image Recognition of Nitrogen and Potassium Nutrient Stress in Rice

Chen Lisu¹^,³, Li Wei¹, Feng Daolun¹, Wu Huafeng², Wang Ke³()

¹College of Ocean Science and Engineering, Shanghai Maritime University, Shanghai 201306, China
²Merchant Marine College, Shanghai Maritime University, Shanghai 201306, China
³College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China

Received:2022-04-21 Accepted:2022-07-19 Online:2023-03-28 Published:2023-01-16
Contact: Wang Ke (kwang@zju.edu.cn)

1. Supplementaldata for 2022-0056.pdf(734KB)

Abstract

Chen Lisu, Li Wei, Feng Daolun, Wu Huafeng, Wang Ke. Transfer Learning-Based Image Recognition of Nitrogen and Potassium Nutrient Stress in Rice[J]. Rice Science, 2023, 30(2): 100-103.

Fig. 1. Analysis of nitrogen (N) and potassium (K) nutrient stress in rice leaves based on different models. A, Different degrees of nitrogen [the concentrations of N1 to N4 as 0, 28.6, 57.2 and 85.7 mg/L, respectively, with the concentration of K (K2SO4) as 89.3 mg/L] and potassium [the concentrations of K1 to K4 as 0, 22.3, 44.7 and 67.0 mg/L, respectively, with the concentration of N (NH4NO3) as 114.3 mg/L] nutrient stresses, as well as the control group [CK, with the concentrations of N (NH4NO3) as 114.3 mg/L and K (K2SO4) as 89.3 mg/L]. B, Accuracy, sensitivity, specificity and training time of different classification models for types and degrees of nutrient stress in rice leaves. EVI, EfficientNet-V3 Integration model. C and D, Accuracy and loss of training and validation of each model based on the identification of nutrient stress categories (C) and degrees (D) in rice leaves, with transfer learning (a and c) and without transfer learning (b and d).

References 17

[1]	Bai X D, Cao Z G, Zhao L D, Zhang J R, Lv C F, Li C N, Xie J D. 2018. Rice heading stage automatic observation by multi- classifier cascade based rice spike detection method. Agric For Meteorol, 259: 260-270.
[2]	Barbedo J G A. 2019. Detection of nutrition deficiencies in plants using proximal images and machine learning: A review. Comput Electron Agric, 162: 482-492.
[3]	Bhattarai U, Karkee M. 2022. A weakly-supervised approach for flower/fruit counting in apple orchards. Comput Ind, 138: 103635.
[4]	Chen J D, Chen J X, Zhang D F, Sun Y D, Nanehkaran Y A. 2020. Using deep transfer learning for image-based plant disease identification. Comput Electron Agric, 173: 105393.
[5]	Chen L S, Huang S H, Sun Y Y, Zhu E Y, Wang K. 2019. Rapid identification of potassium nutrition stress in rice based on machine vision and object-oriented segmentation. J Spectrosc, 2019: 4623545.
[6]	Ferentinos K P, Barda M, Damer D. 2019. An image-based deep learning model for Cannabis diseases, nutrient deficiencies and pests identification. In: Moura Oliveira P, Novais P, Reis L. Progress in Artificial Intelligence. Cham, Switzerland: Springer International Publishing: 134-145.
[7]	Ghosal S, Blystone D, Singh A K, Ganapathysubramanian B, Singh A, Sarkar S. 2018. An explainable deep machine vision framework for plant stress phenotyping. Proc Natl Acad Sci USA, 115(18): 4613-4618. PMID
[8]	Gui P H, Dang W J, Zhu F Y, Zhao Q J. 2021. Towards automatic field plant disease recognition. Comput Electron Agric, 191: 106523.
[9]	Jeyaraj P R, Asokan S P, Samuel Nadar E R.. 2022. Computer-assisted real-time rice variety learning using deep learning network. Rice Sci, 29(5): 489-498.
[10]	Krishnamoorthy N, Prasad L V N, Kumar C S P, Subedi B, Abraha H B, Sathishkumar V E. 2021. Rice leaf diseases prediction using deep neural networks with transfer learning. Environ Res, 198: 111275.
[11]	Liu J C, Wang M T, Bao L, Li X F. 2020. EfficientNet based recognition of maize diseases by leaf image classification. J Phys: Conf Ser, 1693(1): 012148.
[12]	Ma J Y, Chen T T, Lin J, Fu W M, Feng B H, Li G Y, Li H B, Li J C, Wu Z H, Tao L X, Fu G F. 2022. Functions of nitrogen, phosphorus and potassium in energy status and their influences on rice growth and development. Rice Sci, 29(2): 166-178.
[13]	Porikli F, Shan S G, Snoek C, Sukthankar R, Wang X G. 2018. Deep learning for visual understanding: Part 2. IEEE Signal Process Mag, 35(1): 17-19.
[14]	Saleem G, Akhtar M, Ahmed N, Qureshi W S. 2019. Automated analysis of visual leaf shape features for plant classification. Comput Electron Agric, 157: 270-280.
[15]	Sethy P K, Barpanda N K, Rath A K, Behera S K. 2020. Deep feature based rice leaf disease identification using support vector machine. Comput Electron Agric, 175: 105527.
[16]	Sun Y Y, Tong C, He S, Wang K, Chen L S. 2018. Identification of nitrogen, phosphorus, and potassium deficiencies based on temporal dynamics of leaf morphology and color. Sustainability, 10(3): 762.
[17]	Wäldchen J, Mäder P. 2018. Plant species identification using computer vision techniques: A systematic literature review. Arch Comput Methods Eng, 25(2): 507-543.

Transfer Learning-Based Image Recognition of Nitrogen and Potassium Nutrient Stress in Rice

RichHTML

PDF

Supplement

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 1

References 17

Related Articles 0

Recommended Articles

Metrics