Quantitative Analysis of Tea Leaf Serration Morphological Characteristics Based on Image Analysis

TANG Min; ZHONG Qitian; XU Jin; XIAO Fuliang; LI Jie; ZHAI Xiuming; HOU Yujia; GU Yu

doi:10.13305/j.cnki.jts.2023.06.004

PDF(970 KB)

Journal of Tea Science ›› 2023, Vol. 43 ›› Issue (6) : 835-843. DOI: 10.13305/j.cnki.jts.2023.06.004

Research Paper

Quantitative Analysis of Tea Leaf Serration Morphological Characteristics Based on Image Analysis

TANG Min¹, ZHONG Qitian², XU Jin¹, XIAO Fuliang¹, LI Jie¹, ZHAI Xiuming¹, HOU Yujia¹, GU Yu¹

Author information +

History +

Abstract

The size, shape, and arrangement of tea leaf serrations are important criteria for assessing and evaluating tea germplasm resources. However, for a long time, the determination of these criteria has mainly relied on the experience of technicians, resulting in subjective judgments and uncertainties. In this study, a custom convolutional operator based on the geometric morphological features of leaves was introduced, and the existing image recognition algorithms were optimized. A quantification method for tea leaf serrations based on leaf image analysis was proposed. Through experimental validation, the results show that this method can rapidly and accurately obtain basic parameters such as leaf area, perimeter, and number of serrations. It can also quantify descriptive indicators such as serration sharpness, serration depth, and serration density using custom operators. The coefficients of variation for the quantified results are all less than 1%, indicating strong repeatability and high stability. Compared to manual subjective identification, the measurement time of this method does not exceed 30 s, effectively enhancing the accuracy and efficiency of evaluating the morphological characteristics of tea leaf serrations. It provided a new approach and perspective for the quantitative evaluation of tea germplasm resources.

Key words

morphological quantification / serration density / serration depth / serration sharpness / tea leaf

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

TANG Min, ZHONG Qitian, XU Jin, XIAO Fuliang, LI Jie, ZHAI Xiuming, HOU Yujia, GU Yu. Quantitative Analysis of Tea Leaf Serration Morphological Characteristics Based on Image Analysis[J]. Journal of Tea Science. 2023, 43(6): 835-843 https://doi.org/10.13305/j.cnki.jts.2023.06.004

References

[1] 赵卫国, 伍贤密, 齐玉岗, 等. 茶树紫阳群体种种质叶片表型多样性分析[J]. 江西农业学报, 2023, 35(2): 53-59.
Zhao W G, Wu X M, Qi Y G, et al.Diversity analysis of leaf phenotypic characters of Ziyang tea population germplasm resources[J]. Acta Agriculturae Jiangxi, 2023, 35(2): 53-59.
[2] 佚名. 茶树新品种权简介[J]. 茶叶学报, 2022, 63(1): 2, 57.
Anon. Introduction to new tea plant variety rights [J]. Tea Science and Technology, 2022, 63(1): 2, 57.
[3] 郑卫红, 任云, 杨成忠. 基于数字图像处理技术的叶面测量仪研究[J]. 杭州电子工业学院学报, 2004, 24(3): 31-34.
Zheng W H, Ren Y, Yang C Z.Research on leaf area measurement instrument based on digital image processing technology[J]. Journal of Hangzhou Institute of Electronics Engineering, 2004, 24(3): 31-34
[4] 董晓华, 赵乔, 苏中波, 等. 基于漫水填充算法的叶面积仪研制[J]. 节水灌溉, 2016(9): 169-172.
Dong X H, Zhao Q, Su Z B, et al.Development of leaf area meter based on flood-fill algorithm[J]. Water-Saving Irrigation, 2016(9): 169-172.
[5] 宫志宏, 薛庆禹, 于红, 等. 基于数字照片解析的黄瓜叶片面积测定及效果分析[J]. 中国农学通报, 2015, 31(23): 230-234.
Gong Z H, Xue Q Y, Yu H, et al.Measurement of cucumber’s leaf area based on digital photo interpreted[J]. Chinese Agricultural Science Bullentin, 2015, 31(23): 230-234.
[6] 刘亚, 张团善, 王恩芝. 基于高效边缘检测的彩色图像灰度化算法[J]. 轻工机械, 2022, 40(6): 52-58.
Liu Y, Zhang T S, Wang E Z.Grayscale algorithm for color image based on efficient edge detection[J]. Light Industry Machinery, 2022, 40(6): 52-58.
[7] Li S H, Ye L L.Multi-level thresholding image segmentation for rubber tree secant using improved Otsu's method and snake optimizer[J]. Mathematical Biosciences and Engineering, 2023, 20(6): 9645-9669.
[8] 李应果, 杨洁, 董春雷. 木材表面缺陷特征轮廓提取算法研究[J]. 西北林学院学报, 2021, 36(4): 204-208, 281.
Li Y G, Yang J, Dong C L.Research on algorithm for extracting feature contours of surface defects in wood[J]. Journal of Northwest Forestry University, 2021, 36(4): 204-208, 281.
[9] 卢筱伟, 孟志青. 融合注意力机制和多尺度卷积的小麦病害识别模型[J]. 中国农学通报, 2023, 39(25): 147-154.
Lu X W, Meng Z Q.Wheat disease identification model based on fusion attention mechanism and multi-scale convolution[J]. Chinese Agricultural Science Bulletin, 2023, 39(25): 147-154.
[10] 蒋清健. 图像模式识别在农业病害监测与预测中的应用研究[J]. 农业灾害研究, 2023, 13(8): 74-76.
Jiang Q J.Research on the application of image pattern recognition in agricultural disease monitoring and prediction[J]. Agricultural Disaster Research, 2023, 13(8): 74-76.
[11] 李海涛, 罗维平. 基于深度学习的棉花品种识别[J]. 武汉纺织大学学报, 2022, 35(4): 22-26.
Li H T, Luo W P.Cotton variety identification based on deep learning[J]. Journal of Wuhan Textile University, 2022, 35(4): 22-26.
[12] 肖强智, 徐维新, 代娜, 等. 高寒牧草叶面积的冬季衰减过程与估算[J]. 草地学报, 2023, 31(8): 2436-2445.
Xiao Q Z, Xu W X, Dai N, et al.The temporal pattern of leaf area index in withered procedure and its estimation in winter in Qinghai-Tibet Plateau[J]. Acta Agrestia Sinica, 2023, 31(8): 2436-2445.
[13] 林甄, 李睿伟, 谢金冶, 等. 视觉神经网络林场巡检机器人的设计与开发[J]. 东北林业大学学报, 2023, 51(8): 127-135, 139.
Lin Z, Li R W, Xie J Y, et al.Design and development of forest farm inspection robot using visual neural network[J]. Journal of Northeast Foresrty University, 2023, 51(8): 127-135, 139.
[14] 张军凯, 李欣, 韩俊先, 等. 深度学习算法下的采摘机器人系统优化研究[J]. 农机化研究, 2024, 46(4): 58-62.
Zhang J K, Li X, Han J X, et al.Research on optimization of picking robot system under deep learning algorithm[J]. Journal of Agricultural Mechanization Research, 2024, 46(4): 58-62.