|Table of Contents|

Research on Tea Disease Analysis Methods Based on OpenCV and Fuzzy Mathematics

《北方园艺》[ISSN:1001-0009/CN:23-1247/S]

Issue:
2024年4
Page:
145-153
Research Field:
Publishing date:

Info

Title:
Research on Tea Disease Analysis Methods Based on OpenCV and Fuzzy Mathematics
Author(s):
YE Rong1; HE Yun2; GAO Quan3; ZHANG Guangchuan3; SHAO Guoqi3; LI Tong3
(1.College of Food Science and Technology，Yunnan Agricultural University，Kunming,Yunnan 650051；2.Big Data College,Yunnan Agricultural University，Kunming,Yunnan 650051；3.Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province，Kunming，Yunnan 650051)
Keywords:
image processing; algorithm; tea; fuzzy mathematics
PACS:
S 571.1
DOI:
10.11937/bfyy.20232536
Abstract:
The image features of tea diseases are complex,diverse,and fuzzy，posing a threat to the health and population of tea.At present，there is a lack of corresponding disease degree evaluation system，and the weight of evaluation indicators cannot accurately reflect the current growth status of tea.OpenCV is a powerful image processing tool，and its image edge defect recognition algorithm can reduce the misdiagnosis rate of diseases and has good background noise processing effects.This study used OpenCV to train and analyze the proportion of tea lesions，and obtained qualitative evaluation results.At the same time，the importance of the four characteristic indicators,namely the size of tea lesions spot size，tea texture，tea color，and tea size was quantitatively evaluated by experts.The membership degree theory of fuzzy mathematics was introduced for comprehensive judgment，and a comprehensive expression for tea disease was established.Based on the appropriate evaluation weights，further determine the impact of different factors on the degree of tea disease.The practical application results indicated that the combination of OpenCV and fuzzy mathematics evaluation methods，through reliable and stable image recognition technology，can more scientifically and reasonably evaluate the degree of tea diseases，providing reference value for the healthy growth and quality assurance of tea.

References:

［1］刘威,袁丁,郭桂义,等.茶树炭疽病病原鉴定［J］.南方农业学报,2017,48(3):448-453.［2］DREW L.The growth of tea［J］.Nature,2019,566(7742):S2.［3］王聃,柴秀娟.机器学习在植物病害识别研究中的应用［J］.中国农机化学报,2019,40(9):171-180.［4］贾少鹏,高红菊,杭潇，等.基于深度学习的农作物病虫害图像识别技术研究进展［J］.农业机械学报,2019,50(S1)：313-317.［5］林彬彬,邱新法,何永健，等.茶树病害智能诊断识别算法研究［J］.江苏农业科学,2019,47(6)：85-91.［6］陈雪艳,李理,范晓静，等.基于神经网络和证据理论的农田虫害预测算法［J］.中国农机化学报,2019,40(2):151-156.［7］WANG X F，HUANG D S.A novel multi-layer level set method for image segmentation［J］.Journal of Universal Computer Science，2008，14:2428-2452.［8］YAO Q，GUAN Z X，ZHOU Y F，et al.Application of support vector machine for detecting rice diseases using shape and color texture features［C］.Hong Kong：International Conference on Engineering Computation，2009.［9］张艳,王林茂,程志友,等.基于多尺度特征拼接的小样本茶叶病害分类［J］.安徽大学学报(自然科学版),2022,46(5):58-63.［10］鲁恒,付萧,贺一楠，等.基于迁移学习的无人机影像耕地信息提取方法［J］.农业机械学报,2015,46(12):274-279,284.［11］张云,许江淳,王志伟，等.基于机器视觉的棉花异性纤维检测技术优化研究［J］.中国农机化学报,2018,39(9):61-65.［12］孙道宗,刘欢,刘锦源,等.基于改进YOLOv4模型的茶叶病害识别［J］.西北农林科技大学学报(自然科学版),2023(9):145-154.［13］刘自强,周紫英.茶叶图像特征提取及其应用研究进展［J］.绿色科技,2021,23(16):207-209.［14］张金炎,曹成茂,李文宝，等.基于多特征融合的茶叶鲜叶等级识别的方法研究［J］.安徽农业大学学报,2021,48(3):480-487.［15］刘自强,周铁军,傅冬和，等.基于颜色和形状的鲜茶叶图像特征提取及在茶树品种识别中的应用［J］.江苏农业科学,2021,49(12):168-172.［16］LINS R D，BERNARDINO R，BARBOZA R S，et al.Using paper texture for choosing a suitable algorithm for scanned document image binarization［J］.Journal of Imaging，2022,8(10):272.［17］李先锋,徐森,花义明.基于OpenCV计算机视觉的海事视频船舶火灾烟雾检测技术［J］.舰船科学技术,2021,43(22):202-204.［18］姚俊光,余冰纯,林景峰,等.基于OpenCV的龙眼图像合理通道选择研究［J］.现代计算机,2019(26):31-35.［19］LIU Q G，LI S Q，XIONG J J，et al.WpmDecolor：Weighted projection maximumsolver for contrast-preserving decolorization［J］.The Visual Computer，2019,35(2):205-221.［20］卢红阳,刘且根,熊娇娇,等.基于最大加权投影求解的彩色图像灰度化对比度保留算法［J］.自动化学报，2017，43(5)：843-854.［21］ZHANG K，ZUO W M，CHEN Y J，et al.Beyond a Gaussian denoiser：Residual learning of deep CNN for image denoising［J］.IEEE Transactions on Image Processing,2017,26(7)：3142-3155.［22］TIAN C W，XU Y，LI Z Y，et al.Attention-guided CNN for image denoising［J］.Neural Networks,2020,124:117-129.［23］TIAN C W，XU Y,ZUO W M，et al.Designing and training of a dual CNN for image denoising［J］.Knowledge-Based Systems,2021,226:106949.［24］郭恒意,贾振堂.结合残差密集块的卷积神经网络图像去噪方法［J］.计算机工程与设计，2020,41(7):1998-2003.［25］吴广义,袁卓群,梁艳梅.基于深度学习的视网膜OCT图像无监督去噪方法［J/OL］.光学学报，(2023-05-05)［2023-07-04］.https://kns.cnki.net/kcms2/article/abstract?v=18Spvz_s8r EUIC2WxzccIKy9qQQqlmsEI5eTpax5a1VNo4XBFsf4EHhevsi2_x0CT4emtqA7k_-M9V3923A725BgSqKlgue5dM1uPyC_0fDWCb R2nrUb8JHHRY1AePMrbmM82yUhT4Y=&uniplatform=NZKPT&language=CHS.［26］贾洪信,周喜华,刘素纯.基于模糊数学综合评价法优化平菇肉松制作工艺［J］.北方园艺,2018(24):118-124.［27］刘全凤,王译萱,齐立学，等.模糊综合评价法评估盐渍化潮土区温室番茄减量施氮效益［J］.北方园艺,2018(16):150-154.

Memo

Memo:
-
Last Update: 2024-03-15