[1]陈舒迪,柴琴琴,张勋,等.基于多特征融合和LightGBM的金线莲品系识别[J].江苏农业学报,2021,(01):155-162.[doi:doi:10.3969/j.issn.1000-4440.2021.01.020]
　CHEN Shu-di,CHAI Qin-qin,ZHANG Xun,et al.Identification of Anoectochilus roxburghii strains based on multi feature fusion and LightGBM[J].,2021,(01):155-162.[doi:doi:10.3969/j.issn.1000-4440.2021.01.020]
点击复制

基于多特征融合和LightGBM的金线莲品系识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年01期
页码:
155-162
栏目:
园艺
出版日期:
2021-02-28

文章信息/Info

Title:
Identification of Anoectochilus roxburghii strains based on multi feature fusion and LightGBM
作者:
陈舒迪1; 2; 柴琴琴1; 2; 张勋3; 黄泽豪3; 林羽3; 徐伟3
（1.福州大学电气工程与自动化学院，福建福州350108；2.福建省医疗器械和医药技术重点实验室，福建福州350108；3.福建中医药大学药学院，福建福州350122）
Author(s):
CHEN Shu-di1; 2; CHAI Qin-qin1; 2; ZHANG Xun3; HUANG Ze-hao3; LIN Yu3; XU Wei3
(1.College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China;2.Ministry of Education Key Laboratory of Medical Instrument and Pharmaceutical Technology, Fuzhou University, Fuzhou 350108, China;3.College of Pharmacy, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China）
关键词:
金线莲; 多特征融合; LightGBM; 叶片识别
Keywords:
Anoectochilus roxburghii; multi feature fusion; LightGBM; leaf recognition
分类号:
TP391
DOI:
doi:10.3969/j.issn.1000-4440.2021.01.020
文献标志码:
A
摘要:
金线莲是中国珍稀中草药，不同品系的金线莲具有细微的形态差异和显著的药效差异。针对金线莲的单一特征贡献能力不足以及传统分类器泛化能力不佳的问题，提出使用形状、颜色和纹理特征对金线莲叶片图像进行特征提取与融合，再使用表现性能更优的LightGBM（轻量级梯度提升机）构建分类器，以提高金线莲识别正确率。LightGBM具有精确高效等优点，将提取得到的高层次特征导入LightGBM进行训练预测，可以有效提高分类准确性。对金线莲数据集中的6个品系共368幅叶片图像进行试验，结果表明，相比于传统的分类方法，基于多特征融合和LightGBM的模型识别效果最好，10次随机试验的平均识别率比传统方法KNN、SVM和GBDT高，并且在分类评价指标精确率、召回率、综合评价指标上有较优表现，该研究结果可为中药材品系识别提供参考。
Abstract:
Anoectochilus roxburghii is a rare Chinese herbal medicine, different strains of A.roxburghii have slight morphological difference and significant variance in medicinal effects. To solve the problems of insufficient contribution ability of single-feature in A.roxburghii and poor generalization ability of traditional classifiers, it was proposed to use shape, color and texture features to extract and fuse features of A.roxburghii leaf images. Then LightGBM (light weight class elevator) with a better performance was used in building classifier, so as to improve the recognition accuracy of A.roxburghii. LightGBM had the advantages of accurate and efficient, and the prediction accuracy could be improved effectively by importing the extracted high-level features into LightGBM to forecast the training. A total of 368 leaf images from six strains of A.roxburghii dataset were trained and tested. The results showed that model based on multi-feature fusion and LightGBM had the best recognition effect compared with traditional classification methods. The average recognition rate of ten random experiments was higher than traditional methods such as KNN, SVM and GBDT, and it showed good performance in classification evaluation indices like precision, recall rate and comprehensive evaluation index. The result can provide reference for the identification of different strains of traditional Chinese medicine.

参考文献/References:

[1]王勇,陈硕,卢端萍, 等.金线莲化学成分的研究[J]. 中草药, 2017(13):36-41.
[2]何春年,王春兰,郭顺星,等. 福建金线莲的化学成分研究Ⅱ[J]. 中国中药杂志, 2005, 39(10): 581-582.
[3]马玉芳,郑小香,衣伟萌,等. 金线莲多糖对免疫抑制小鼠脾淋巴细胞体外增殖、 分泌NO及细胞因子的影响[J]. 天然产物研究与开发, 2018，30(1)：21-26.
[4]李芹,周文,刘路,等. 金线莲喷雾剂治疗手足口病口腔疱疹临床观察[J]. 福建中医药, 2012, 43(3)：9-10.
[5]肖雪洋. 植物叶片图像识别特征的研究和在线识别系统实现[D]. 合肥：中国科学技术大学,2011.
[6]蔡超. 金线莲的鉴别与应用[J]. 中国中医药现代远程教育, 2016, 14(21)：123-124, 127.
[7]蔡文燕,肖华山,范秀珍. 金线莲研究进展(综述)[J]. 亚热带植物科学, 2003(3)：69-73.
[8]王海阁,许文,张勋,等. 林下栽培金线莲的生药鉴别[J]. 中药材, 2020, 43(2)：303-308.
[9]TAO O, LIN Z, ZHANG X B, et al. Research on identification model of chinese herbal medicine by texture feature parameter of transverse section image[J]. World Science and Technology-Modernization of Traditional Chinese Medicine, 2014(12)：2558-2562.
[10]沈宝国,陈树人,尹建军,等. 基于颜色特征的棉田绿色杂草图像识别方法[J]. 农业工程学报,2009,25(6)：163-167.
[11]HERRERA P J, DORADO J, RIBEIRO . A novel approach for weed type classification based on shape descriptors and a fuzzy decision-making method[J]. Sensors, 2014（14）：15304－15324.
[12]TURKOGLU M, HANBAY D. Leaf-based plant species recognition based on improved local binary pattern and extreme learning machine[J]. Physica A: Statistical Mechanics and its Applications, 2019, 527: 121297.
[13]PAL M , FOODY G M . Feature selection for classification of hyperspectral data by SVM[J]. IEEE Transactions on Geoence and Remote Sensing, 2010, 48(5): 2297-2307.
[14]ZHANG S C, LI X L, ZONG M,et al. Learning k for kNN classification[J]. ACM Transactions on Intelligent Systems and Technology, 2017, 8(8):1-19.
[15]KIM S Y , UPNEJA A . Predicting restaurant financial distress using decision tree and AdaBoosted decision tree models[J]. Economic Modelling, 2014, 36(1): 354-362.
[16]FAGERLAND M W , HOSMER D W , BOFIN A M . Multinomial goodness-of-fit tests for logistic regression models[J]. Statistics in Medicine, 2008, 27(21): 4238-4253.
[17]HAN J , ZHANG D , CHENG G , et al. Advanced deep-learning techniques for salient and category-specific object detection: a survey[J]. IEEE Signal Processing Magazine, 2018, 35(1):84-100.
[18]DYRMANN M, KARSTOFT H, MIDTIBY H S, et al. Plant species classification using deep convolutional neural network[J]. Biosystems Engineering,2016, 151:72-80 .
[19]邓向武,齐龙,马旭,等. 基于多特征融合和深度置信网络的稻田苗期杂草识别[J]. 农业工程学报, 2018, 34(14):173-180.
[20]KE G, MENG Q, FINLEY T, et al. Lightgbm: a highly efficient gradient boosting decision tree[C]//Ulrike von Luxburg, Isabelle Guyon. Proceedings of the 31st International Conference on Neural Information Processing SystemsDecember. San Diego,CA: Neural Information Processing Systems Foundation, 2017: 3146-3154.
[21]WANG D H, ZHANG Y, ZHAO Y. LightGBM: an effective miRNA classification method in breast cancer patients [C]// Association for Computing Machinery.Proceedings of the 2017 International Conference on Computational Biology and Bioinformatics. New York: Association for Computing Machinery, 2017: 7-11.
[22]ZHANG J, MUCS D, NORINDER U, et al. LightGBM: an effective and scalable algorithm for prediction of chemical toxicity-application to the Tox21 and mutagenicity data sets[J]. Journal of Chemical Information & Modeling, 2019, 59(10):4150-4158.
[23]POST F H, VROLIJK B, HAUSER H, et al. The state of the art in flow visualisation: feature extraction and tracking[J]. Computer Graphics Forum, 2010, 22(4):775-792.
[24]胡维炜,张武,刘连忠,等. 利用图像处理技术计算大豆叶片相对病斑面积[J]. 江苏农业学报,2016,32(4):774-779.
[25]WANG X F, HUANG D S, DU J X, et al. Classification of plant leaf images with complicated background［J］. Applied Mathematics and Computation, 2008, 205（2）： 916-926.
[26]HWANG W, WANG H T, KIM H, et al. Face recognition system using multiple face model of hybrid fourier feature under uncontrolled illumination variation[J]. IEEE Transactions on Image Processing, 2011, 20(4):1152-1165.
[27]HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification[J]. Studies in Media and Communication, 1973, 3(6): 610-621.
[28]LIU L, FIEGUTH P, GUO Y, et al. Local binary features for texture classification: taxonomy and experimental study[J]. Pattern Recognition, 2017（62）: 135-160.
[29]OJALA T, PIETIKINEN M, MENP T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

相似文献/References:

[1]赵建鹏,杨秀峰,李国洪,等.基于面向对象的设施蔬菜高分遥感影像提取[J].江苏农业学报,2019,(04):911.[doi:doi:10.3969/j.issn.1000-4440.2019.04.023]
　ZHAO Jian peng,YANG Xiu feng,LI Guo hong,et al.Object oriented extraction of high resolution remote sensing images of facility vegetables[J].,2019,(01):911.[doi:doi:10.3969/j.issn.1000-4440.2019.04.023]
[2]梅瑜,王继华,蔡时可,等.金线莲应答高温胁迫的蛋白质组学分析[J].江苏农业学报,2020,(06):1389.[doi:doi:10.3969/j.issn.1000-4440.2020.06.006]
　MEI Yu,WANG Ji-hua,CAI Shi-ke,et al.Proteomics analysis on Anoectochilus roxburghii in response to high temperature stress[J].,2020,(01):1389.[doi:doi:10.3969/j.issn.1000-4440.2020.06.006]

备注/Memo

备注/Memo:
收稿日期：2020-06-02基金项目：福建省科技厅重大产学研项目（2019Y4009）；晋江市福大科教园区发展中心科研项目（2019-JJFDKY-48）作者简介：陈舒迪（1997-），女，福建南平人，硕士研究生，主要从事机器学习与图像处理研究。（E-mail）chshud@163.com通讯作者：柴琴琴，（E-mail）qq.chai@fzu.edu.cn；林羽，（E-mail）lyfjtcm@163.com
更新日期/Last Update: 2021-03-15