[1]邹永杰,张永军,秦永彬,等.应用于番茄病虫害检测的HOG特征与LBP特征的结合[J].南京师范大学学报(工程技术版),2019,19(03):021.[doi:10.3969/j.issn.1672-1292.2019.03.004]
　Zou Yongjie,Zhang Yongjun,Qin Yongbin,et al.The Combination of HOG Features with LBP Features Applied toTomato Disease and Pest Detection[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):021.[doi:10.3969/j.issn.1672-1292.2019.03.004]
点击复制

应用于番茄病虫害检测的HOG特征与LBP特征的结合
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
19卷
期数:
2019年03期
页码:
021
栏目:
计算机工程
出版日期:
2019-09-30

文章信息/Info

Title:
The Combination of HOG Features with LBP Features Applied toTomato Disease and Pest Detection
文章编号:
1672-1292(2019)03-0021-08
作者:
邹永杰; 张永军; 秦永彬; 郑世均
贵州大学计算机科学与技术学院,贵州 贵阳 550025
Author(s):
Zou Yongjie; Zhang Yongjun; Qin Yongbin; Zheng Shijun
College of Computer Science and Technology,Guizhou University,Guiyang 550025,China
关键词:
番茄; 病虫害检测; HOG特征; LBP特征
Keywords:
tomato; insect and disease detection; HOG features; LBP features
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2019.03.004
文献标志码:
A
摘要:
植物病虫害是农业部门面临的主要挑战,准确和快速地检测植物病虫害有助于发现早期治疗方法,同时大幅减少经济损失. 基于机器学习的目标检测方法能够很大程度地提高物体检测和识别系统的准确性. 提出了一种基于机器学习的番茄病虫害检测方法,通过提取有病虫害和无病虫害的番茄样本的HOG特征和LBP特征,然后结合SVM分类器训练样本得到检测模型. HOG特征能够较好地描述番茄叶的边缘特征,LBP特征能够较好地描述番茄叶的纹理特征,两个特征在一定程度上互补. 实验结果表明,基于HOG与LBP特征结合检测有病虫害的番茄叶取得了较好的效果,该方法在全球AI挑战赛中农作物病害的番茄数据集取得了99.49%的检测率.
Abstract:
Plant diseases and insect pests are the main challenges facing the agricultural sector. Accurate and rapid detection of plant diseases and insect pests can help to identify early treatment methods,while significantly reducing economic losses. Target detection method based on machine learning can greatly improve the accuracy of object detection and recognition system. This paper presents a tomato pest detection method based on machine learning. The method extracts the HOG and LBP features of tomato samples with and without pests and diseases,and then combines the training samples of SVM classifier to get the detection model. HOG features can better describe the edge characteristics of tomato leaves,and LBP features can better describe the texture characteristics of tomato leaves,so the two features can complement each other to a certain extent. The experimental results show that based on the combination of HOG and LBP features,the detection of tomato leaves with diseases and insect pests obtains good results,and achieves 99.49% detection rate on tomato data set of crop diseases in the global AI challenge.

参考文献/References:

[1] MABVAKURE B,MARTIN D P,KRABERGER S,et al. Ongoing geographical spread of Tomato yellow leaf curl virus[J]. Virology,2016,498:257-264.
[2]CANIZARES M C,ROSAS D T,RODRIGUEZ N E,et al. Arabidopsis thaliana,an experimental host for tomato yellow leaf curl disease-associated begomoviruses by agroinoculation and whitefly transmission[J]. Plant pathology,2015,64(2):265-271.
[3]NUTTER F W,ESKER P D,NETTO R A C. Disease assessment concepts and the advancements made in improving the accuracy and precision of plant disease data[J]. European journal of plant pathology,2006,115(1):95-103.
[4]GILBERTSON R L,BATUMAN O. Emerging viral and other diseases of processing tomatoes:biology,diagnosis and management[J]. Acta horticulturae,2013,971(6):35-48.
[5]JUAN A D,CANIZARES M C,MORIONES E,et al. Tomato yellow leaf curl viruses:ménage à trois between the virus complex,the plant and the whitefly vector[J]. Molecular plant pathology,2010,11(4):441-450.
[6]MUNYANEZA J E,CROSSLIN J M,BUCHMAN J L,et al. Susceptibility of different potato plant growth stages to purple top disease[J]. American journal of potato research,2010,87(1):60-66.
[7]FUENTES A,IM D H,YOON S,et al. Spectral analysis of CNN for tomato disease identification[J]. Artificial intelligence and soft computing,2017:40-51.
[8]LISTED N A. The economic value of breast-feeding. Food and agriculture organization of united nations[J]. Fao food & nutrition paper,1979,11:1-89.
[9]SANKARAN S,MISHRA A,EHSANI R,et al. A review of advanced techniques for detecting plant diseases[J]. Computers and electronics in agriculture,2010,72(1):1-13.
[10]CHAERANI R,VOORRIPS R E. Tomato early blight(Alternaria solani):the pathogen,genetics,and breeding for resistance[J]. Journal of general plant pathology,2006,72(6):335-347.
[11]ALVAREZ,ANNE M. Integrated approaches for detection of plant pathogenic bacteria and diagnosis of bacterial diseases[J]. Annual review of phytopathology,2004,42(1):339-366.
[12]ION G A,MEHLE N,DELIC D,et al. Real-time quantitative PCR based sensitive detection and genotype discrimination of Pepino mosaic virus[J]. Journal of virological methods,2009,162(1/2):46-55.
[13]MARTINELLI F,SCALENGHE R,DAVINO S,et al. Advanced methods of plant disease detection:a review[J]. Agronomy for sustainable development,2015,35(1):1-25.
[14]BOCK C H,POOLE G H,PARKER P E,et al. Plant disease severity estimated visually,by digital photography and image analysis,and by hyperspectral imaging[J]. Critical reviews in plant sciences,2010,29(2):59-107.
[15]TAMURA H,MATSUMOTO Y,YOKOMITSU S,et al. Shrink boost for selecting multi-LBP histogram features in object detection[C]//Computer Vision & Pattern Recognition. Washington,DC:IEEE,2012:3250-3257.
[16]MIZUNO K,TERACHI Y,TAKAGI K,et al. Architectural study of HOG feature extraction processor for real-time object detection[C]//Signal Processing Systems. Washington,DC:IEEE,2013.
[17]AUNG M,KALTWANG S,ROMERA P B,et al. The automatic detection of chronic pain-related expression:requirements,challenges and a multimodal dataset[J]. IEEE transactions on affective computing,2016,7(4):435-451.
[18]WANG B,JIA J,ZHANG L,et al. Structure-based sybil detection in social networks via local rule-based propagation[J]. IEEE transactions on network science & engineering,2015,14(8):1-14.
[19]WALK S,MAJER N,SCHINDLER K,et al. New features and insights for pedestrian detection[C]//Computer Vision and Pattern Recognition(CVPR). Washington,DC:IEEE,2010.

备注/Memo

备注/Memo:
收稿日期:2019-07-05.
基金项目:国家自然科学基金联合基金重点项目(U1836205)、国家自然科学基金重大研究计划项目(91746116)、贵州省重大应用基础研究项目(黔科合JZ字[2014]2001)、贵州省科技重大专项计划(黔科合重大专项字[2017]3002).
通讯联系人:张永军,博士,副教授,研究方向:图像处理和模式识别. E-mail:zyj6667@126.com
更新日期/Last Update: 2019-09-30