Agricultural engineering |
|
|
|
|
Extraction and discrimination of tobacco leaf shape based on landmark method |
Peige ZHONG1(),Yeying ZHOU1,Yan ZHANG2,Yi SHI2,Yan GUO1,Baoguo LI1,Yuntao MA1() |
1.College of Land Science and Technology, China Agricultural University, Beijing 100193, China 2.Key Laboratory of Tobacco Biology and Processing, Ministry of Agriculture and Rural Affairs, Tobacco Research Institute, Chinese Academy of Agricultural Sciences, Qingdao 266101, Shandong, China |
|
|
Abstract The shape information of leaves from 39 tobacco varieties was extracted by using landmark method. The differences in leaf shapes were compared and analyzed among different varieties and different leaf positions at different growth stages. Principal component analysis was used to reduce the dimensionality of the data. The sources of differences were visualized among different leaf shapes. Decision tree, random forest and support vector machine were used to perform discriminant analysis on tobacco leaf shapes. The results of the principal component analysis showed that the first three principal components accounted for 42.7%, 21.3% and 10.7% of the total differences in tobacco leaves at the flowering stage, which were characterized by leaf width and the maximum width position, leaf torsion, and petiole size, respectively. The discriminant results of tobacco leaf shape based on machine learning showed that the discriminant accuracy based on landmark data was 52%-62%, while the value was 51%-54% for common leaf shape indicators. The discriminant accuracy on superior or medial leaves was about 10% higher than that of inferior leaves, representing more obvious characteristics of variety. Due to the growth of the leaves, the discriminant accuracy of the leaves at rosette stage was nearly 10% lower than flowering stage. The discriminant accuracy of landmark method increased to 77% after removing 12 atypical varieties. The effect of the landmark method on leaf shape information extraction is better than the common leaf shape indicators, which provides a new idea for the automated extraction of leaf shape information.
|
Received: 09 July 2021
Published: 03 September 2022
|
|
Corresponding Authors:
Yuntao MA
E-mail: zhongpg1998@163.com;yuntao.ma@cau.edu.cn
|
基于标志点法的烟草叶形提取与判别
本研究采用标志点法并基于39个烟草品种叶片图像提取叶形信息,比较分析了不同生长时期、不同品种和不同叶位间的叶形差异。采用主成分分析法实现数据降维并对叶形差异进行可视化表达,采用决策树、随机森林和支持向量机法对不同类型叶形进行判别分析。主成分分析结果表明,烟草叶片间差异的主要来源分别为叶片宽和最大宽位置、叶片扭转程度以及叶柄部3方面,分别占总差异的42.7%、21.3%、10.7%。叶形判别结果表明,采用标志点数据的判别精度为52%~62%,而采用常用叶形指标的判别精度为51%~54%。上部叶、中部叶的判别精度高于下部叶10%左右,具有更明显的品种特征。团棵期叶片由于处于营养生长期,判别精度低于开花期叶片近10%。去除12类非典型品种后,标志点法判别精度上升至77%。标志点数据在叶形信息提取上的效果优于常用叶形指标,为叶形信息的自动化提取提供了新的思路。
关键词:
几何形态学,
标志点法,
烟草,
叶形,
机器学习
|
|
[1] |
张宁,刘文萍.基于图像分析的植物叶片识别技术综述[J].计算机应用研究,2011,28(11):4001-4007. DOI:10.3969/j.issn.1001-3695.2011.11.001 ZHANG N, LIU W P. Plant leaf recognition technology based on image analysis[J]. Application Research of Computers, 2011, 28(11): 4001-4007. (in Chinese with English abstract)
doi: 10.3969/j.issn.1001-3695.2011.11.001
|
|
|
[2] |
王晓峰,黄德双,杜吉祥,等.叶片图像特征提取与识别技术的研究[J].计算机工程与应用,2006(3):190-193. DOI:10.3321/j.issn:1002-8331.2006.03.056 WANG X F, HUANG D S, DU J X, et al. Feature extraction and recognition for leaf images[J]. Computer Engineering and Applications, 2006(3): 190-193. (in Chinese with English abstract)
doi: 10.3321/j.issn:1002-8331.2006.03.056
|
|
|
[3] |
WÄLDCHEN J, MÄDER P. Plant species identification using computer vision techniques: a systematic literature review[J]. Archives of Computational Methods in Engineering, 2018, 25(2): 507-543. DOI:10.1007/s11831-016-9206-z
doi: 10.1007/s11831-016-9206-z
|
|
|
[4] |
LEE S H, CHAN C S, MAYO S J, et al. How deep learning extracts and learns leaf features for plant classification[J]. Pattern Recognition, 2017, 71: 1-13. DOI:10.1016/j.patcog.2017.05.015
doi: 10.1016/j.patcog.2017.05.015
|
|
|
[5] |
LARESE M G, NAMÍAS R, CRAVIOTTO R M, et al. Automatic classification of legumes using leaf vein image features[J]. Pattern Recognition, 2014, 47(1): 158-168. DOI:10.1016/j.patcog.2013.06.012
doi: 10.1016/j.patcog.2013.06.012
|
|
|
[6] |
MUNISAMI T, RAMSURN M, KISHNAH S, et al. Plant leaf recognition using shape features and colour histogram with k-nearest neighbour classifiers[J]. Procedia Computer Science, 2015, 58: 740-747. DOI:10.1016/j.procs.2015.08.095
doi: 10.1016/j.procs.2015.08.095
|
|
|
[7] |
郑一力,钟刚亮,王强,等.基于多特征降维的植物叶片识别方法[J].农业机械学报,2017,48(3):30-37. DOI:10.6041/j.issn.1000-1298.2017.03.004 ZHENG Y L, ZHONG G L, WANG Q, et al. Method of leaf identification based on multi-feature dimension reduction[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(3): 30-37. (in Chinese with English abstract)
doi: 10.6041/j.issn.1000-1298.2017.03.004
|
|
|
[8] |
白明,杨星科,李静,等.几何形态学:关于形态定量比较的科学计算工具[J].科学通报,2014,59(10):887-894. DOI:10.1360/972012-1561 BAI M, YANG X K, LI J, et al. Geometric morphometrics, a super scientific computing tool in morphology comparison[J]. Chinese Science Bulletin, 2014, 59(10): 887-894. (in Chinese with English abstract)
doi: 10.1360/972012-1561
|
|
|
[9] |
刘媛,吕佳,宋佳,等.基于几何形态测量学的植物鉴定方法[J].植物科学学报,2017,35(6):894-899. DOI:10.11913/PSJ.2095-0837.2017.60894 LIU Y, LÜ J, SONG J, et al. Plant species delimitation method based on geometric morphometrics[J]. Plant Science Journal, 2017, 35(6): 894-899. (in Chinese with English abstract)
doi: 10.11913/PSJ.2095-0837.2017.60894
|
|
|
[10] |
CHITWOOD D H, OTONI W C. Morphometric analysis of Passiflora leaves: the relationship between landmarks of the vasculature and elliptical Fourier descriptors of the blade[J]. GigaScience, 2017, 6(1): giw008. DOI:10.1093/gigascience/giw008
doi: 10.1093/gigascience/giw008
|
|
|
[11] |
FELDMANN M J, HARDIGAN M A, FAMULA R A, et al. Multi-dimensional machine learning approaches for fruit shape phenotyping in strawberry[J]. GigaScience, 2020, 9(5): giaa030. DOI:10.1093/gigascience/giaa030
doi: 10.1093/gigascience/giaa030
|
|
|
[12] |
LIU Y, LI Y J, SONG J L, et al. Geometric morphometric analyses of leaf shapes in two sympatric Chinese oaks: Quercus dentata Thunberg and Quercus aliena Blume (Fagaceae)[J]. Annals of Forest Science, 2018, 75(4): 90. DOI:10.1007/s13595-018-0770-2
doi: 10.1007/s13595-018-0770-2
|
|
|
[13] |
WOEBBECKE D M, MEYER G E, VON BARGEN K, et al. Color indices for weed identification under various soil, residue, and lighting conditions[J]. Transactions of the ASAE, 1995, 38(1): 259-269. DOI:10.13031/2013.27838
doi: 10.13031/2013.27838
|
|
|
[14] |
OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66. DOI:10.1109/tsmc.1979.4310076
doi: 10.1109/tsmc.1979.4310076
|
|
|
[15] |
FIRMANSYAH Z, HERDIYENI Y, SILALAHI B P, et al. Landmark analysis of leaf shape using polygonal approximation[C]. IOP Conference Series: Earth and Environmental Science, 2016, 31(1): 012018. DOI:10.1088/1755-1315/31/1/012018
doi: 10.1088/1755-1315/31/1/012018
|
|
|
[16] |
ROHLF F J, SLICE D. Extensions of the Procrustes method for the optimal superimposition of landmarks[J]. Systematic Zoology, 1990, 39(1): 40-59. DOI:10.2307/2992207
doi: 10.2307/2992207
|
|
|
[17] |
VISCOSI V, CARDINI A. Leaf morphology, taxonomy and geometric morphometrics: a simplified protocol for beginners[J]. PLoS ONE, 2011, 6(10): e25630. DOI:10.1371/journal.pone.0025630
doi: 10.1371/journal.pone.0025630
|
|
|
[18] |
DRYDEN I L. Shapes: Statistical Shape Analysis, with Application in R Package Version 1.2.5[CP]. Chichester, UK: Wiley, 2019.
|
|
|
[19] |
柴宏红,邵科,于超,等.基于三维点云的甜菜根表型参数提取与根型判别[J].农业工程学报,2020,36(10):181-188. DOI:10.11975/j.issn.1002-6819.2020.10.022 CHAI H H, SHAO K, YU C, et al. Extraction of phenotypic parameters and discrimination of beet root types based on 3D point cloud[J]. Transactions of the CSAE, 2020, 36(10): 181-188. (in Chinese with English abstract)
doi: 10.11975/j.issn.1002-6819.2020.10.022
|
|
|
[20] |
BREIMAN L, FRIEDMAN J H, OLSHEN R A, et al. Classification and Regression Trees[M]. New York, USA: Routledge, 2017. DOI:10.1201/9781315139470
doi: 10.1201/9781315139470
|
|
|
[21] |
BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. DOI:10.1023/a:1010933404324
doi: 10.1023/a:1010933404324
|
|
|
[22] |
CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297. DOI:10.1007/bf00994018
doi: 10.1007/bf00994018
|
|
|
[23] |
KLINGENBERG C P. MorphoJ: an integrated software package for geometric morphometrics[J]. Molecular Ecology Resources, 2011, 11(2): 353-357. DOI:10.1111/j.1755-0998.2010.02924.x
doi: 10.1111/j.1755-0998.2010.02924.x
|
|
|
[24] |
MALOOF J N, NOZUE K, MUMBACH M R, et al. LeafJ: an ImageJ plugin for semi-automated leaf shape measurement[J]. Journal of Visualized Experiments, 2013(71): 50028. DOI:10.3791/50028
doi: 10.3791/50028
|
|
|
[25] |
ADAMS D C, ROHLF F J, SLICE D E. A field comes of age: geometric morphometrics in the 21st century[J]. Hystrix, the Italian Journal of Mammalogy, 2013, 24(1): 7-14. DOI:10.4404/hystrix-24.1-6283
doi: 10.4404/hystrix-24.1-6283
|
|
|
[26] |
招启柏,顾世梁,俞惠梅,等.烟草叶片生长的动态分析[J].中国烟草学报,2004,10(2):12-20. DOI:10.3321/j.issn:1004-5708.2004.02.003 ZHAO Q B, GU S L, YU H M, et al. A dynamic analysis of tobacco leaf growth[J]. Acta Tabacaria Sinica, 2004, 10(2): 12-20. (in Chinese with English abstract)
doi: 10.3321/j.issn:1004-5708.2004.02.003
|
|
|
[27] |
MIGICOVSKY Z, LI M, CHITWOOD D H, et al. Morphometrics reveals complex and heritable apple leaf shapes[J]. Frontiers in Plant Science, 2018, 8: 2185. DOI:10.3389/fpls.2017.02185
doi: 10.3389/fpls.2017.02185
|
|
|
[28] |
XIAO S F, CHAI H H, SHAO K, et al. Image-based dynamic quantification of aboveground structure of sugar beet in field[J]. Remote Sensing, 2020, 12(2): 269. DOI:10.3390/rs12020269
doi: 10.3390/rs12020269
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|