Automatic stomata recognition and measurement based on improved YOLO deep learning model and entropy rate superpixel algorithm

被引:23
作者
Zhang, Fan [1 ,2 ]
Ren, Fangtao [2 ]
Li, Jieping [3 ]
Zhang, Xinhong [4 ]
机构
[1] Henan Univ, Henan Key Lab Big Data Anal & Proc, Kaifeng 475004, Peoples R China
[2] Henan Univ, Sch Comp & Informat Engn, Kaifeng 475004, Peoples R China
[3] Henan Univ, Sch Life Sci, Kaifeng 475004, Peoples R China
[4] Henan Univ, Sch Software, Kaifeng 475004, Peoples R China
基金
中国国家自然科学基金;
关键词
Stomata; Deep learning; YOLO; Superpixel algorithm; DENSITY;
D O I
10.1016/j.ecoinf.2021.101521
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
The traditional methods of analyzing stomatal traits are mostly manual observation and measurement. These methods are time-consuming, labor-intensive, and inefficient. Some methods have been proposed for the automatic recognition and counting of stomata, however most of those methods could not complete the automatic measurement of stomata parameters at the same time. Some non-deep learning methods could automatically measure the parameters of stomata, but they could not complete the automatic recognition and detection of stomata. In this paper, a deep learning-based method was proposed for automatically identifying, counting and measuring stomata of maize (Zea mays L.) leaves at the same time. An improved YOLO (You Only Look Once) deep learning model was proposed to identify stomata of maize leaves automatically, and an entropy rate superpixel algorithm was used for the accurate measurement of stomatal parameters. According to the characteristics of the stomata images data set, the network structure of YOLOv5 was modified, which greatly reduced the training time without affecting the recognition performance. The predictor in YOLO deep learning model was optimized, which reduced the false detection rate. At the same time, the 16-fold and 32-fold down-sampling layers were simplified according to the characteristics of stomatal objects, which improved the recognition efficiency. Experimental results showed that the recognition precision of the improved YOLO deep learning model reached 95.3% on the maize leaves stomatal data set, and the average accuracy of parameter measurement reached 90%. The proposed method could fully automatically complete the recognition, counting and measurement of stomata of plants, which can help agricultural scientists and botanists to conduct large-scale researches of stomatal morphology, structure and physiology, as well as the researches combined with genetic analysis or molecular-level analysis.
引用
收藏
页数:13
相关论文
共 37 条
[1]  
Adarsh P, 2020, INT CONF ADVAN COMPU, P687, DOI [10.1109/ICACCS48705.2020.9074315, 10.1109/icaccs48705.2020.9074315]
[2]   Leaf elongation response to blue light is mediated by stomatal-induced variations in transpiration in Festuca arundinacea [J].
Barillot, Romain ;
De Swaef, Tom ;
Combes, Didier ;
Durand, Jean-Louis ;
Escobar-Gutierrez, Abraham J. ;
Martre, Pierre ;
Perrot, Cedric ;
Roy, Eric ;
Frak, Elzbieta .
JOURNAL OF EXPERIMENTAL BOTANY, 2021, 72 (07) :2642-2656
[3]   Deep Convolutional Neural Networks Based Framework for Estimation of Stomata Density and Structure from Microscopic Images [J].
Bhugra, Swati ;
Mishra, Deepak ;
Anupama, Anupama ;
Chaudhury, Santanu ;
Lall, Brejesh ;
Chugh, Archana ;
Chinnusamy, Viswanathan .
COMPUTER VISION - ECCV 2018 WORKSHOPS, PT VI, 2019, 11134 :412-423
[4]   Effects of elevated carbon dioxide on stomatal characteristics and carbon isotope ratio of Arabidopsis thaliana ecotypes originating from an altitudinal gradient [J].
Caldera, H. Iroja U. ;
De Costa, W. A. Janendra M. ;
Woodward, F. Ian ;
Lake, Janice A. ;
Ranwala, Sudheera M. W. .
PHYSIOLOGIA PLANTARUM, 2017, 159 (01) :74-92
[5]   LabelStoma: A tool for stomata detection based on the YOLO algorithm [J].
Casado-Garcia, Angela ;
del-Canto, Arantza ;
Sanz-Saez, Alvaro ;
Perez-Lopez, Usue ;
Bilbao-Kareaga, Amaia ;
Fritschi, Felix B. ;
Miranda-Apodaca, Jon ;
Munoz-Rueda, Alberto ;
Sillero-Martinez, Anna ;
Yoldi-Achalandabaso, Ander ;
Lacuesta, Maite ;
Heras, Jonathan .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 178
[6]   Molecular Evolution of Grass Stomata [J].
Chen, Zhong-Hua ;
Chen, Guang ;
Dai, Fei ;
Wang, Yizhou ;
Hills, Adrian ;
Ruan, Yong-Ling ;
Zhang, Guoping ;
Franks, Peter J. ;
Nevo, Eviatar ;
Blatt, Michael R. .
TRENDS IN PLANT SCIENCE, 2017, 22 (02) :124-139
[7]   Segmenting High-quality Digital Images of Stomata using the Wavelet Spot Detection and the Watershed Transform [J].
Duarte, Kaue T. N. ;
de Carvalho, Marco A. G. ;
Martins, Paulo S. .
PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 4, 2017, :540-547
[8]   StomataCounter: a neural network for automatic stomata identification and counting [J].
Fetter, Karl C. ;
Eberhardt, Sven ;
Barclay, Rich S. ;
Wing, Scott ;
Keller, Stephen R. .
NEW PHYTOLOGIST, 2019, 223 (03) :1671-1681
[9]  
Girshick R., 2015, PROC ADVNEURAL INF P, P1440
[10]   Rich feature hierarchies for accurate object detection and semantic segmentation [J].
Girshick, Ross ;
Donahue, Jeff ;
Darrell, Trevor ;
Malik, Jitendra .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :580-587