Please wait a minute...
浙江大学学报(农业与生命科学版)  2018, Vol. 44 Issue (6): 748-754    DOI: 10.3785/j.issn.1008-9209.2017.07.131
农业工程     
基于图像法的离体小麦叶片几何参数计算
张万红*
(西北农林科技大学水土保持研究所,陕西杨凌712100)
Geometrical parameter calculation of excised wheat leaves based on image analysis
ZHANG Wanhong* 
(Institute of Soil and Water Conservation, Northwest A & F University, Yangling 712100, Shaanxi, China)
 全文: PDF(3907 KB)   HTML (
摘要: 针对目前植物叶片几何参数计算中的一些不足,提出适用于离体小麦叶片叶面积、叶长、叶宽和周长的计算方法。首先使用直方图阈值法对特定背景下小麦图像进行分割;然后采用统计像素数法计算小麦叶面积,采用叶片边缘相邻像素间距离的方法计算周长,使用改进后的最小外接矩形法计算叶长和叶宽;最后对计算结果与实测值进行比较,并使用统计分析方法对计算结果进行检验。结果显示,计算值接近实测值,叶面积、叶长和叶宽的均方根误差(root mean square error, RMSE)分别为0.49 cm2、0.57 cm、0.04 cm,决定系数(R2)分别为0.99、0.97、0.96。RMSE值接近于0、R2值接近于1,以及计算值与测量值之间存在的较小差异,表明改进后的叶长和叶宽算法的计算结果不受小麦叶片形状的影响,方法普适性好,且叶长、叶宽、叶面积和周长算法对相应参数的计算结果准确度高。
关键词: 小麦叶片图像分割叶面积叶周长叶长叶宽    
Abstract: Aiming at some deficiency of geometrical parameter calculation in plant leaves at present, we proposed a computational method suitable for measuring area, length, width and perimeter of excised wheat leaves. Wheat image was segmented under a certain background by histogram algorithm. Leaf area was calculated by statistical image number method, and leaf perimeter was calculated on the distance between adjacent pixels of the blade edge. Leaf length and width were measured by improved minimum enclosing rectangle. Then the calculated results were compared with the measured values, and statistical analysis was carried out. The results showed the calculated results were close to the measured values. The root mean square error (RMSE) values for area, length and width of wheat leaves were 0.49 cm2, 0.57 cm and 0.04 cm, respectively. The coefficient of determination (R2) for area, length and width of wheat leaves were 0.99, 0.97 and 0.96, respectively. The differences in RMSE values were close to 0 and R2 values were close to 1, and the calculated results and the measured values were insignificant, indicating that the improved algorithms for measuring area, length, width and perimeter of wheat leaves are not influenced by wheat leaf shapes, suitable for different conditions, reliable and practicable.
Key words: wheat leaf    image segmentation    leaf area    leaf perimeter    leaf length    leaf width
出版日期: 2018-11-25
CLC:  S 24  
基金资助: 中国科学院重点部署项目(KFZD-SW-306-03)
通讯作者: 张万红(https://orcid.org/0000-0002-0101-3220)     E-mail: zhwhong@nwafu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
张万红

引用本文:

张万红. 基于图像法的离体小麦叶片几何参数计算[J]. 浙江大学学报(农业与生命科学版), 2018, 44(6): 748-754.

ZHANG Wanhong. Geometrical parameter calculation of excised wheat leaves based on image analysis. Journal of Zhejiang University (Agriculture and Life Sciences), 2018, 44(6): 748-754.

链接本文:

http://www.zjujournals.com/agr/CN/10.3785/j.issn.1008-9209.2017.07.131        http://www.zjujournals.com/agr/CN/Y2018/V44/I6/748

[1] 张宁,张庆国,于海敬,程梦笛,董世杰. 作物生长模拟模型的参数敏感性分析[J]. 浙江大学学报(农业与生命科学版), 2018, 44(1): 107-115.
[2] 张万红,刘文兆. 覆膜玉米冠层图像分割方法[J]. 浙江大学学报(农业与生命科学版), 2017, 43(5): 649-656.
[3] 吕腾飞,周伟,孙永健,朱懿,严奉君,杨志远,马均. 不同秧龄和氮肥运筹对杂交籼稻株型的影响[J]. 浙江大学学报(农业与生命科学版), 2015, 41(2): 169-178.
[4] 刘晓红, 黄廷林, 王国栋, 张 钢. 盐胁迫对小麦叶片电阻抗图谱参数的影响[J]. 浙江大学学报(农业与生命科学版), 2009, 35(5): 564-568.
[5] 付峰  应义斌. 生物图像阈值分割方法的研究[J]. 浙江大学学报(农业与生命科学版), 2003, 29(1): 108-112.
[6] 王秀珍  黄敬峰  李云梅  沈掌泉  王人潮. 高光谱数据与水稻农学参数之间的相关分析[J]. 浙江大学学报(农业与生命科学版), 2002, 28(3): 283-288.