Plant leaf recognition model based on two-way convolutional neural network

Yu Huiling; Ma Junwei; Zhang Yizhuo

doi:10.13332/j.1000-1522.20180182

Journal of Beijing Forestry University > 2018 > 40(12): 132-137. > DOI: 10.13332/j.1000-1522.20180182

Yu Huiling, Ma Junwei, Zhang Yizhuo. Plant leaf recognition model based on two-way convolutional neural network[J]. Journal of Beijing Forestry University, 2018, 40(12): 132-137. DOI: 10.13332/j.1000-1522.20180182

Citation:

PDF (2209 KB)

Plant leaf recognition model based on two-way convolutional neural network

1.
School of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, Heilongjiang, China
2.
Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, Heilongjiang, China

More Information

Received Date: May 29, 2018
Revised Date: October 21, 2018
Published Date: November 30, 2018

Graphical Abstract

Abstract

Abstract

ObjectiveAiming at the problem that the leaf edge shape has an excessive effect on the convolution layer during the process of identifying the leaf of convolutional neural network, which leads to the error recognition of similar edge shape leaves, a plant leaf recognition model of two-way convolutional neural network was proposed.
MethodThe model considers the edge shape and internal texture features of the blade information to construct a two-way convolutional neural network structure. Wherein, the shape feature path used a network structure of 7 layers of convolution layers, the first three layers used large-size 11×11 and 5×5 convolution kernels, extracting large field of view features to complete blade shape feature extraction, the other 4 layers of convolution layer used a 3×3 small size convolution core, extracting blade detail features. The two types of feature linear transformations were merged into one-dimensional feature vectors through a fully connected layer. Finally, the fully connected layer identified the plant leaf species.
ResultThe experimental results showed that the two-way convolutional network model was compared with the single-channel convolutional network and the image recognition classification recognition model. On the Flavia leaf dataset and the expanded complex background leaf dataset, the accuracy of Top-1 recognition increased to 99.28% and 97.31%, respectively. The accuracy of Top-3 recognition increased to 99.97% and 99.74%, respectively. The standard deviation decreased to 0.18 and 0.20 compared with other identification and classification models.
ConclusionThe blade recognition and classification model proposed in this paper can effectively avoid the problems caused by the similar blade edge shape interference and improve the recognition accuracy of leaf plant species.
- plant identification,
- blade image,
- feature fusion,
- convolutional neural network

FullText(HTML)

References (11)

References

[1]	魏蕾, 何东健, 乔永亮.基于图像处理和SVM的植物叶片分类研究[J].农机化研究, 2013, 35(5): 12-15. doi: 10.3969/j.issn.1003-188X.2013.05.003 Wei L, He D J, Qiao Y L. Plant leaves classification based on image processing and SVM[J]. Journal of Agricultural Mechanization Research, 2013, 35(5):12-15. doi: 10.3969/j.issn.1003-188X.2013.05.003
[2]	张宁, 刘文萍.基于克隆选择算法和K近邻的植物叶片识别方法[J].计算机应用, 2013, 33(7): 2009-2013. doi: 10.11772/j.issn.1001-9081.2013.07.2009 Zhang N, Liu W P. Plant leaf recognition method based on clonal selection algorithm and K nearest neighbor[J]. Journal of Computer Applications, 2013, 33(7): 2009-2013. doi: 10.11772/j.issn.1001-9081.2013.07.2009
[3]	王丽君, 淮永建, 彭月橙.基于叶片图像多特征融合的观叶植物种类识别[J].北京林业大学学报, 2015, 37(1):55-61. doi: 10.13332/j.cnki.jbfu.2015.01.006 Wang L J, Huai Y J, Peng Y C. Method of identification of foliage from plants based on extraction of multiple features of leaf images[J]. Journal of Beijing Forestry University, 2015, 37(1): 55-61. doi: 10.13332/j.cnki.jbfu.2015.01.006
[4]	杨天天, 潘晓星, 穆立蔷.基于叶片图像特征数字化信息识别7种柳属植物[J].东北林业大学学报, 2014, 42(12):75-79. doi: 10.3969/j.issn.1000-5382.2014.12.016 Yang T T, Pan X X, Mu L Q. Identification of seven Salix species using digital information analysis of leaf image characteristics[J]. Journal of Northeast Forestry University, 2014, 42(12):75-79. doi: 10.3969/j.issn.1000-5382.2014.12.016
[5]	张帅, 淮永建.基于分层卷积深度学习系统的植物叶片识别研究[J].北京林业大学学报, 2016, 38(9):108-115. doi: 10.13332/j.1000-1522.20160035 Zhang S, Huai Y J. Leaf image recognition based on layered convolutions neural network deep learning[J]. Journal of Beijing Forestry University, 2016, 38(9):108-115. doi: 10.13332/j.1000-1522.20160035
[6]	Lee S H, Chan C S, Wilkin P, et al. Deep-plant: plant identification with convolutional neural networks[C]//Proceedings of 2015 IEEE International Conference on Image Processing (ICIP). Quebec: IEEE, 2015: 452-456.
[7]	Wu S G, Bao F S, Xu E Y, et al. A leaf recognition algorithm for plant classification using PNN (probabilistic neural network)[C/OL]//Proceedings of 2007 IEEE International Symposium on Signal Processing and Information Technology. New York: IEEE, 2007[2018-02-27]. https://ieeexplore.ieee.org/document/4458016.
[8]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe: ACM, 2012: 1097-1105.
[9]	卢宏涛, 张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理, 2016, 31(1):1-17. http://d.old.wanfangdata.com.cn/Periodical/sjcjycl201601001 Lu H T, Zhang Q C. Applications of deep convolutional neural network in computer vision[J]. Journal of Data Acquisition and Processing, 2016, 31(1):1-17. http://d.old.wanfangdata.com.cn/Periodical/sjcjycl201601001
[10]	Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
[11]	Bouvrie J. Notes on convolutional neural networks[EB/OL]. (2006-11-22)[2015-10-11]. http://cogprints.org/5869/1/cnn_tutorial.pdf.

[1]	Chen Tingqiao, Yuan Tao, Xie Mengyu, Tang Ying, Zeng Xiuli. Development of secondary branches and apical buds of Paeonia ludlowii under cultivated conditions[J]. Journal of Beijing Forestry University, 2022, 44(6): 106-114. DOI: 10.12171/j.1000-1522.20210144
[2]	LIU Jin-chun, MA Ye, TAO Jian-ping, GAO Kai-min, LIANG Qian-hui. Effects of AM fungus on root growth of Lonicera japonica under alternate dry and wet conditions in karst regions of southwestern China.[J]. Journal of Beijing Forestry University, 2015, 37(10): 110-116. DOI: 10.13332/j.1000-1522.20150057
[3]	CHEN Jie, XIE Jing, TANG Ming. Effects of arbuscular mycorrhizal fungi on the growth and drought resistance of Amorpha fruticosa under water stress.[J]. Journal of Beijing Forestry University, 2014, 36(6): 142-148. DOI: 10.13332/j.cnki.jbfu.2014.06.026
[4]	WEI Bao, DING Guo-dong, WU Bin, ZHANG Yu-qing, BAO Yan-feng, GAO Guang-lei1, SHI Hui-shu, ZHAO Jin-hong. Windbreak mechanism under different shrub cover conditions.[J]. Journal of Beijing Forestry University, 2013, 35(5): 73-78.
[5]	XU Yan, YU Xue-jun, GAO Yan, GAO Pei-jun, ZHANG Ru-min. Effects of NO on seed germination and seedling growth of Haloxylon ammodendron under osmosis stress[J]. Journal of Beijing Forestry University, 2011, 33(6): 65-69.
[6]	MENG Fan-juan, WANG Jian-zhong, HUANG Feng-lan, WANG Yan-jie. Ultrastructure of mesophyll cells in two Robinia pseudoacacia hybrids under NaCl stress.[J]. Journal of Beijing Forestry University, 2010, 32(4): 97-102.
[7]	WANG Jin-li, LIANG Wen-yan, CHEN Li. Separation and purification of microcystin-LR.[J]. Journal of Beijing Forestry University, 2010, 32(2): 184-188.
[8]	XIA Songhua, LI Li, LI Jian-zhang.. Ureaformaldehyde resin modified by nanoTiO2 under ultrasonic treatment[J]. Journal of Beijing Forestry University, 2009, 31(4): 123-129.
[9]	WANG Xing-zu, CHENG Xiang, ZHENG Hui, SUN De-zhi. Autocatalysis in biological decolorization of Reactive Black 5 under anaerobic condition．[J]. Journal of Beijing Forestry University, 2009, 31(3): 135-139.
[10]	ZHENG Yong-hong, , LIANG Er-yuan, ZHU Hai-feng, SHAO Xue-mei. Response of radial growth of Qilian juniper to climatic change under different habitats[J]. Journal of Beijing Forestry University, 2008, 30(3): 7-12.

Cited By

Cited by

Periodical cited type(8)

1.	杨灿，范习健，张九于. SSFYOLO：一种面向复杂森林场景的树干检测算法. 北京林业大学学报. 2025(02): 132-142 . 本站查看
2.	刘伟起，刘洪杰，史璐，杨欣，李建平，王鹏飞. 电动果园作业平台结构设计与试验. 农机化研究. 2024(01): 75-83 .
3.	刘伟起，刘洪杰，史璐，杨欣，李建平，王鹏飞. 履带式果园作业平台结构稳定性分析与研究. 农机化研究. 2024(04): 42-47 .
4.	郭昊生，马蓉，张垚鑫，李子迎. 丫形欠驱动库尔勒香梨采摘机械手的设计与仿真分析. 农机化研究. 2023(01): 110-117 .
5.	虞浪，俞高红，吴浩宇，孙福兴，钱孟波. 欠驱动关节型柑橘采摘末端执行器设计与试验. 农业工程学报. 2023(17): 29-38 .
6.	于泳超，康峰，郑永军，吕昊暾，王亚雄. 果园高位自动调平作业平台设计及仿真. 北京林业大学学报. 2021(02): 150-159 . 本站查看
7.	曹琨，张姗姗. 基于机器视觉的蔬果辅助采摘装置系统设计与优化. 食品工业. 2021(05): 362-366 .
8.	董杰，赵元豪，尚宁宁，蒋创宇，赵秒. 一种旋转式欠驱动自适应水果采摘器. 科学技术创新. 2019(13): 155-156 .

Other cited types(1)

Get Citation

PDF

XML

Article views (1797) PDF downloads (51) Cited by(9)

Turn off MathJax

Article Contents

Abstract

References

Plant leaf recognition model based on two-way convolutional neural network