[1]陆静,王家亮,朱赛华,等.基于特征优化的稻飞虱图像分类[J].南京农业大学学报,2019,42(4):767-774.[doi:10.7685/jnau.201810012]
 LU Jing,WANG Jialiang,ZHU Saihua,et al.Classification of rice planthoppers image based on feature optimition[J].Journal of Nanjing Agricultural University,2019,42(4):767-774.[doi:10.7685/jnau.201810012]
点击复制

基于特征优化的稻飞虱图像分类()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
42卷
期数:
2019年4期
页码:
767-774
栏目:
食品与工程
出版日期:
2019-07-08

文章信息/Info

Title:
Classification of rice planthoppers image based on feature optimition
作者:
陆静 王家亮 朱赛华 何瑞银
南京农业大学工学院, 江苏 南京 210031
Author(s):
LU Jing WANG Jialiang ZHU Saihua HE Rinyin
College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
关键词:
稻飞虱图像分类特征优化BP神经网络
Keywords:
rice planthopperimage classificationfeature optimizationBP neural network
分类号:
TP391.41
DOI:
10.7685/jnau.201810012
摘要:
[目的]为了进一步提高稻飞虱图像分类的效率,本文提出一种基于特征优化的稻飞虱图像分类算法。[方法]对采集到的原始昆虫图像进行阈值分割、形态学滤波以及边缘跟踪来获取完整的昆虫彩色背部图像,同时基于该图像集提取昆虫的形态、颜色以及纹理特征66个,结合F-score特征评价方法,筛选出10个特征参数作为最优特征子集,并将其作为BP神经网络的输入特征值。[结果]当采用全部66个特征作为输入特征值时,稻飞虱图像的分类准确率达到96.19%;当采用最优特征子集作为输入特征值时,稻飞虱图像的分类准确率也为96.19%。[结论]以该方法获得的最优特征子集作为稻飞虱图像的特征参数不仅降低特征维度,提高稻飞虱图像分类效率,而且保证分类性能,为实现水稻虫害实时监测预警系统提供了技术支持。
Abstract:
[Objectives]In order to improve the efficiency of the image classification of rice planthopper(RPH),an image classification algorithm based on feature optimization has been proposed in this paper.[Methods]Threshold segmentation,morphological filtering and edge tracking were used to obtain the complete colorful back image of insects,and 66 of insect morphology,color and texture features were extracted based on the image set. With the F-score feature evaluation method,10 feature parameters were selected as the optimal feature subset,which were classified by BP neural network.[Results]When all 66 of features were used as input feature values,the insect image recognition accuracy rate reached 96.19%. What’s more,the recognition accuracy rate of the rice planthopper image was also 96.19%,while those input feature values were the optimal feature subset.[Conclusions]The optimal feature subset,presented in this paper,as the feature parameters of RPH image can reduce the feature dimension,improve the classification efficiency of RPH image and maintain the classification accuracy. The research results provide technical support for a real-time monitoring and forecasting system on main crop pests.

参考文献/References:

[1] 包云轩,蒋蓉,谢晓金,等. 近30年气候异常对江苏省褐飞虱灾变性迁入的影响[J]. 生态学报,2014,34(23):7078-7092. Bao Y X,Jiang R,Xie X J,et al. Impact of climate anomalies on catastrophic immigrations of Nilaparvata lugens in Jiangsu Province[J]. Acta Ecologica Sinica,2014,34(23):7078-7092(in Chinese with English abstract).
[2] 程家安,祝增荣. 2005年长江流域稻区褐飞虱暴发成灾原因分析[J]. 植物保护,2006,32(4):1-4. Cheng J A,Zhu Z R. Analysis on the key factors causing the outbreak of brown planthopper in Yangtze Area,China in 2005[J]. Plant Protection,2006,32(4):1-4(in Chinese with English abstract).
[3] 徐磊,谭晔,刘向东.水稻冠层反射光谱监测褐飞虱种群密度及水稻穗粒质量的可能性[J]. 南京农业大学学报,2016,39(6):954-959.DOI:10.7685/jnau.201601046. Xu L,Tan Y,Liu X D. Possibility of monitoring population density of brown planthoppers and grain weight of rice using spectral reflectance from rice canopy[J]. Journal of Nanjing Agricultural University,2016,39(6):954-959(in Chinese with English abstract).
[4] 张智,张云慧,姜玉英,等. 雷达昆虫学研究进展及应用前景[J]. 植物保护,2017,43(5):18-26. Zhang Z,Zhang Y H,Jiang Y Y,et al. Development of radar entomological and related prospects for future application[J]. Plant Protection,2017,43(5):18-26(in Chinese with English abstract).
[5] 祁骁杰,卜宇飞,许志春,等. 杨树木段内光肩星天牛幼虫数量的声学检测[J]. 环境昆虫学报,2016,38(3):529-534. Qi X J,Bu Y F,Xu Z C,et al. Using acoustic technology detect the different numbers of Anoplophora glabripennis larvae in poplar[J]. Journal of Environmental Entomology,2016,38(3):529-534(in Chinese with English abstract).
[6] 潘鹏亮,张方梅,尹健,等. 菊方翅网蝽雌雄成虫图像识别技术的初步研究[J]. 植物保护,2017,43(3):70-75. Pan P L,Zhang F M,Yin J,et al. Preliminary studies on image recognition technology for female and male adults of Corythucha marmorata(Uhler)(Hemiptera:Tingidae)[J]. Plant Protection,2017,43(3):70-75(in Chinese with English abstract).
[7] Yu H M,Wang J L,Kang R,et al. Automatic identification of Asian rice plant-hopper based on image processing[J]. Applied Engineering in Agriculture,2017,33(5):591-602.
[8] 刘德营,王家亮,林相泽,等. 基于卷积神经网络的白背飞虱识别方法[J]. 农业机械学报,2018,49(5):51-56. Liu D Y,Wang J L,Lin X Z,et al. Automatic identification method for Sogatella furcifera based on convolutional neural network[J]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(5):51-56(in Chinese with English abstract).
[9] 谢堂胜,刘德营,陈京,等. 白背飞虱智能识别技术研究[J]. 南京农业大学学报,2016,39(3):519-526.DOI:10.7685/jnau.201508026. Xie T S,Liu D Y,Chen J,et al. Automatic identification of Sogatella furcifera[J]. Journal of Nanjing Agricultural University,2016,39(3):519-526(in Chinese with English abstract).
[10] Mala C,Sridevi M. Multilevel threshold selection for image segmentation using soft computing techniques[J]. Soft Computing,2016,20:1793-1810.
[11] Treece G. The bitonic filter:linear filtering in an edge-preserving morphological framework[J]. IEEE Transactions on Image Processing,2016,25(11):5199-5211.
[12] 岳安志,杨建宇,张超,等. 基于多尺度形态学滤波的高分辨率遥感影像分割[J]. 农业工程学报,2013,29(增刊1):89-95. Yue A Z,Yang J Y,Zhang C,et al. Multi-scale morphological filter for image segmentation of very high resolution satellite imagery[J]. Transactions of the Chinese Society of Agricultural Engineering,2013,29(Suppl 1):89-95(in Chinese with English abstract).
[13] Medeiros H,Holguín G,Shin P J,et al. A parallel histogram-based particle filter for object tracking on SIMD-based smart cameras[J]. Computer Vision & Image Understanding,2010,114(11):1264-1272.
[14] Andalo F A,Miranda P A V,da Torres S. Shape feature extraction and description based on tensor scale[J]. Pattern Recognition,2010,43(1):26-36.
[15] Martineau M,Conte D,Raveaux R,et al. A survey on image-based insect classification[J]. Pattern Recognition,2017,65:273-284.
[16] Chen W T,Liu W C,Chen M S. Adaptive color feature extraction based on image color distributions[J]. IEEE Transactions on Image Processing,2010,19(8):2005-2016.
[17] Mohanaiah P,Sathyanarayana P,Gurukumar L. Image texture feature extraction using GLCM approach[J]. International Journal of Scientific and Research Publications,2013,3(5):1-5.
[18] Hubara I,Courbariaux M,Soudry D,et al. Quantized neural networks:training neural networks with low precision weights and activations[J]. Journal of Machine Learning Research,2017,18:1-30.
[19] 秦立峰,何东健,宋怀波.词袋特征PCA多子空间自适应融合的黄瓜病害识别[J]. 农业工程学报,2018,34(8):200-205. Qin L F,He D J,Song H B. Bag of words feature multi-PCA subspace adaptive fusion for cucumber diseases identification[J]. Transactions of the Chinese Society of Agricultural Engineering,2018,34(8):200-205(in Chinese with English abstract).
[20] Kemal P,Salih G. A new feature selection method on classification of medical datasets:kernel F-score feature selection[J]. Expert Systems with Applications,2009,36:10367-10373.
[21] Hu S C,Zhu C,Xie F L,et al. A recommendation algorithm for two-sided matching problems based on F-Score[C]//IEEE International Conference on Computer and Communications,2016:25-29.

备注/Memo

备注/Memo:
收稿日期:2018-10-13。
基金项目:国家重点研发计划项目(2016YFD0300908)
作者简介:陆静,博士研究生。
通信作者:何瑞银,教授,博导,研究方向为农业智能,E-mail:ryhe@njau.edu.cn。
更新日期/Last Update: 1900-01-01