Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android

Qiang Yao; Bin Lyu; Chao Su; Bo Li

doi:doi:10.11648/j.sd.20221005.20

| Peer-Reviewed

Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android

Qiang Yao, Bin Lyu, Chao Su, Bo Li

Published in Science Discovery (Volume 10, Issue 5)

Received: 16 September 2022 Accepted: 20 October 2022 Published: 24 October 2022

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Nitrogen nutrition diagnosis is one of the key technologies to achieve high quality and high yield in rice. It is time-consuming and laborious to use traditional diagnosis methods of rice nitrogen nutrition. Rapid and intelligent diagnosis of rice nitrogen nutrition can be realized by using smart phones and image recognition technology. In order to use mobile equipment to carry out nitrogen nutrition diagnosis in rice anytime and anywhere, and providing suggestions and prescriptions for fertilization management, by migrating the deep learning model to the Android environment, the rice nitrogen nutrition diagnosis system based on Android has been developed according to the established deep learning model of rice nitrogen nutrition recognition based on TensorFlow. The diagnosis results of the developed system have been verified and analyzed using the collected image data. At first, comparative analysis was conducted on various nitrogen nutrition diagnosis methods for rice, and then, image processing technology, image recognition technology, the configuration of development environment, system design and implementation, verification and analysis of diagnosis results have been emphatically introduced. The techniques and development methods used in the experiments are feasible and reproducible. The results of rice nitrogen nutrition recognition using the Android-based rice nitrogen nutrition diagnosis system were the same as the validation results of the original model.

Published in	Science Discovery (Volume 10, Issue 5)
DOI	10.11648/j.sd.20221005.20
Page(s)	340-346
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

TensorFlow, TensorFlow Lite, Android, Deep Learning, Rice, Nitrogen Nutrition Diagnosis

References

[1]	孙棋. 基于数字图像处理技术的水稻氮素营养诊断研究[D]. 杭州: 浙江大学, 2008: 1-3.
[2]	杨红云, 罗建军, 万颖等. 计算机视觉技术在水稻氮素营养诊断中应用的研究进展 [J]. 中国农学通报, 2020, 36 (16): 149-155.
[3]	曹彦圣, 付子轼, 孙会峰等. 施氮水平对水稻氮肥利用率和径流负荷的影响 [J]. 土壤, 2016, 48 (5): 868-872.
[4]	李岚涛, 张萌, 任涛等. 应用数字图像技术进行水稻氮素营养诊断 [J]. 植物营养与肥料学报, 2015, 21 (1): 259-268.
[5]	吴刚, 彭要奇, 周广奇等. 基于多光谱成像和卷积神经网络的玉米作物营养状况识别方法研究 [J]. 智慧农业 (中英文), 2020, 2 (01): 111-120.
[6]	兰宁. 基于Android平台的图像识别设计方法与实现 [J]. 电子技术与软件工程, 2021, (19): 61-64.
[7]	郑姣, 刘立波. 基于Android的水稻病害图像识别系统设计与应用 [J]. 计算机工程与科学, 2015, 37 (07): 1366-1371.
[8]	杨红云, 周琼, 杨珺等. 水稻氮素营养诊断方法研究进展 [J]. 中国稻米, 2020, 26 (02): 5-8+13.
[9]	姚强, 粟超, 李波等. 深度学习方法在水稻氮素营养诊断中的应用初探 [J]. 南方农业, 2021, 15 (31): 125-129.
[10]	CARTER G A, KNAPP A K. Leaf optical properties in higher plants: Linking spectral characteristics to stress and chlorophyll concentration [J]. Am J Bot, 2001, 88 (4): 677-684.
[11]	罗建军. 基于计算机视觉技术与高光谱技术的水稻氮素营养诊断研究[D]. 南昌: 江西农业大学, 2015: 17-19.
[12]	黄喜梅, 毕建杰, 张楠等. 计算机视觉技术在农业上的应用 [J]. 农业科学与技术, 2017, 18 (11): 2158-2162.
[13]	张浩, 胡昊, 陈义等. 水稻叶片氮素及籽粒蛋白质含量的高光谱估测模型 [J]. 核农学报, 2012, 26 (1): 135-140.
[14]	吴子龙. 基于Android移动终端的烟草病虫害图像智能识别系统研究[D]. 昆明: 云南农业大学, 2015: 17-19.
[15]	刘鹏, 庄卫东. 图像识别技术在农业中的应用浅析 [J]. 现代化农业, 2021, (12): 20-21.

Cite This Article

Plain Text BibTeX RIS

APA Style

Qiang Yao, Bin Lyu, Chao Su, Bo Li. (2022). Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Science Discovery, 10(5), 340-346. https://doi.org/10.11648/j.sd.20221005.20

Copy | Download

ACS Style

Qiang Yao; Bin Lyu; Chao Su; Bo Li. Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Sci. Discov. 2022, 10(5), 340-346. doi: 10.11648/j.sd.20221005.20

Copy | Download

AMA Style

Qiang Yao, Bin Lyu, Chao Su, Bo Li. Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Sci Discov. 2022;10(5):340-346. doi: 10.11648/j.sd.20221005.20

Copy | Download

@article{10.11648/j.sd.20221005.20,
  author = {Qiang Yao and Bin Lyu and Chao Su and Bo Li},
  title = {Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android},
  journal = {Science Discovery},
  volume = {10},
  number = {5},
  pages = {340-346},
  doi = {10.11648/j.sd.20221005.20},
  url = {https://doi.org/10.11648/j.sd.20221005.20},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221005.20},
  abstract = {Nitrogen nutrition diagnosis is one of the key technologies to achieve high quality and high yield in rice. It is time-consuming and laborious to use traditional diagnosis methods of rice nitrogen nutrition. Rapid and intelligent diagnosis of rice nitrogen nutrition can be realized by using smart phones and image recognition technology. In order to use mobile equipment to carry out nitrogen nutrition diagnosis in rice anytime and anywhere, and providing suggestions and prescriptions for fertilization management, by migrating the deep learning model to the Android environment, the rice nitrogen nutrition diagnosis system based on Android has been developed according to the established deep learning model of rice nitrogen nutrition recognition based on TensorFlow. The diagnosis results of the developed system have been verified and analyzed using the collected image data. At first, comparative analysis was conducted on various nitrogen nutrition diagnosis methods for rice, and then, image processing technology, image recognition technology, the configuration of development environment, system design and implementation, verification and analysis of diagnosis results have been emphatically introduced. The techniques and development methods used in the experiments are feasible and reproducible. The results of rice nitrogen nutrition recognition using the Android-based rice nitrogen nutrition diagnosis system were the same as the validation results of the original model.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android
AU  - Qiang Yao
AU  - Bin Lyu
AU  - Chao Su
AU  - Bo Li
Y1  - 2022/10/24
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221005.20
DO  - 10.11648/j.sd.20221005.20
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 340
EP  - 346
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221005.20
AB  - Nitrogen nutrition diagnosis is one of the key technologies to achieve high quality and high yield in rice. It is time-consuming and laborious to use traditional diagnosis methods of rice nitrogen nutrition. Rapid and intelligent diagnosis of rice nitrogen nutrition can be realized by using smart phones and image recognition technology. In order to use mobile equipment to carry out nitrogen nutrition diagnosis in rice anytime and anywhere, and providing suggestions and prescriptions for fertilization management, by migrating the deep learning model to the Android environment, the rice nitrogen nutrition diagnosis system based on Android has been developed according to the established deep learning model of rice nitrogen nutrition recognition based on TensorFlow. The diagnosis results of the developed system have been verified and analyzed using the collected image data. At first, comparative analysis was conducted on various nitrogen nutrition diagnosis methods for rice, and then, image processing technology, image recognition technology, the configuration of development environment, system design and implementation, verification and analysis of diagnosis results have been emphatically introduced. The techniques and development methods used in the experiments are feasible and reproducible. The results of rice nitrogen nutrition recognition using the Android-based rice nitrogen nutrition diagnosis system were the same as the validation results of the original model.
VL  - 10
IS  - 5
ER  -

Copy | Download

Author Information

Qiang Yao

Institute of Agricultural Science and Technology Information, Chongqing Academy of Agricultural Sciences, Chongqing, China
Bin Lyu

Institute of Agricultural Science and Technology Information, Chongqing Academy of Agricultural Sciences, Chongqing, China
Chao Su

Institute of Agricultural Science and Technology Information, Chongqing Academy of Agricultural Sciences, Chongqing, China
Bo Li

Institute of Agricultural Science and Technology Information, Chongqing Academy of Agricultural Sciences, Chongqing, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Qiang Yao, Bin Lyu, Chao Su, Bo Li. (2022). Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Science Discovery, 10(5), 340-346. https://doi.org/10.11648/j.sd.20221005.20

Copy | Download

ACS Style

Qiang Yao; Bin Lyu; Chao Su; Bo Li. Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Sci. Discov. 2022, 10(5), 340-346. doi: 10.11648/j.sd.20221005.20

Copy | Download

AMA Style

Qiang Yao, Bin Lyu, Chao Su, Bo Li. Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android. Sci Discov. 2022;10(5):340-346. doi: 10.11648/j.sd.20221005.20

Copy | Download

@article{10.11648/j.sd.20221005.20,
  author = {Qiang Yao and Bin Lyu and Chao Su and Bo Li},
  title = {Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android},
  journal = {Science Discovery},
  volume = {10},
  number = {5},
  pages = {340-346},
  doi = {10.11648/j.sd.20221005.20},
  url = {https://doi.org/10.11648/j.sd.20221005.20},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221005.20},
  abstract = {Nitrogen nutrition diagnosis is one of the key technologies to achieve high quality and high yield in rice. It is time-consuming and laborious to use traditional diagnosis methods of rice nitrogen nutrition. Rapid and intelligent diagnosis of rice nitrogen nutrition can be realized by using smart phones and image recognition technology. In order to use mobile equipment to carry out nitrogen nutrition diagnosis in rice anytime and anywhere, and providing suggestions and prescriptions for fertilization management, by migrating the deep learning model to the Android environment, the rice nitrogen nutrition diagnosis system based on Android has been developed according to the established deep learning model of rice nitrogen nutrition recognition based on TensorFlow. The diagnosis results of the developed system have been verified and analyzed using the collected image data. At first, comparative analysis was conducted on various nitrogen nutrition diagnosis methods for rice, and then, image processing technology, image recognition technology, the configuration of development environment, system design and implementation, verification and analysis of diagnosis results have been emphatically introduced. The techniques and development methods used in the experiments are feasible and reproducible. The results of rice nitrogen nutrition recognition using the Android-based rice nitrogen nutrition diagnosis system were the same as the validation results of the original model.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Research on Rice Nitrogen Nutrition Diagnosis System Based on Deep Learning Model and Android
AU  - Qiang Yao
AU  - Bin Lyu
AU  - Chao Su
AU  - Bo Li
Y1  - 2022/10/24
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221005.20
DO  - 10.11648/j.sd.20221005.20
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 340
EP  - 346
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221005.20
AB  - Nitrogen nutrition diagnosis is one of the key technologies to achieve high quality and high yield in rice. It is time-consuming and laborious to use traditional diagnosis methods of rice nitrogen nutrition. Rapid and intelligent diagnosis of rice nitrogen nutrition can be realized by using smart phones and image recognition technology. In order to use mobile equipment to carry out nitrogen nutrition diagnosis in rice anytime and anywhere, and providing suggestions and prescriptions for fertilization management, by migrating the deep learning model to the Android environment, the rice nitrogen nutrition diagnosis system based on Android has been developed according to the established deep learning model of rice nitrogen nutrition recognition based on TensorFlow. The diagnosis results of the developed system have been verified and analyzed using the collected image data. At first, comparative analysis was conducted on various nitrogen nutrition diagnosis methods for rice, and then, image processing technology, image recognition technology, the configuration of development environment, system design and implementation, verification and analysis of diagnosis results have been emphatically introduced. The techniques and development methods used in the experiments are feasible and reproducible. The results of rice nitrogen nutrition recognition using the Android-based rice nitrogen nutrition diagnosis system were the same as the validation results of the original model.
VL  - 10
IS  - 5
ER  -

Copy | Download