Evaluation of Freezing Injury Degree of Tea Plant Based on Deep
Learning, Wavelet Transform and Visible Spectrum
LI He1, WANG Yu2, FAN Kai2, MAO Yi-lin2, DING Shi-bo3, SONG Da-peng3, WANG Meng-qi3, DING Zhao-tang1*
1. Tea Research Institute of Shandong Academy of Agricultural Sciences, Jinan 250108, China
2. Tea Research Institute of Qingdao Agricultural University, Qingdao 266109, China
3. Tea Research Institute of Rizhao Academy of Agricultural Sciences, Rizhao 276827, China
Abstract：Identifying the freezing injury of tea plants is the basis of evaluating the stress resistance of tea plants and guiding the overwintering management of tea plantations. The traditional method of tea plant freezing injury identification observes the number and degree of freezing injury of tea leaves manually, which has some disadvantages, such as low accuracy, low efficiency, strong subjectivity and so on. A framework for evaluating freezing injury of tea trees based on deep learning, wavelet transform, and visible spectrum is proposed. Firstly, we collected 1000 crown images of frozen tea trees, divided them into the training sets and test sets according to 4∶1, and labeled the frozen leaves in the training set images. Secondly, we use the Faster R-CNN network to identify and extract tea plants' frozen leaves, select three feature extractors: AlexNet, VGG19 and ResNet50 respectively, and select the feature extractor with the highest robustness as the backbone network. Then, the extracted image of frozen leaves of tea plants is enhanced by wavelet transform, and one low-frequency image and three high-frequency images are obtained. Then the images processed by wavelet transform and those not processed by wavelet transform are input into VGG16, SVM, AlexNet, ResNet50 and other networks to classify the frozen leaves, and the classification performance of the four networks is compared. Finally, according to the number of frozen damaged leaves, the degree of frozen damaged leaves and the weight coefficient of leaves with different degrees of frozen damage, the freezing degree of tea plants is scored to evaluate the overall freezing degree of tea plants. The results show that: (1) the Faster R-CNN model based on ResNet50 has the best performance in extracting frozen leaves of tea plants, with a precision rate of 93.33% and a recall rate of 92.57%, which is higher than the recognition performance of VGG19 and AlexNet as the backbone network, which can ensure that most frozen leaves can be extracted and provide a basis for further classification of the degree of freezing damage of leaves. (2) The overall accuracy of the VGG16 model in classifying leaves with different degrees of freezing injury is 89%, which is higher than that of other models (SVM, AlexNet, ResNet50), which shows that the vgg16 model has high robustness. (3) Compared with the frozen leaves without wavelet transform, the overall classification accuracy of the model can be improved by 2%~6%. It shows that wavelet transforms enhancement technology can improve the accuracy of the network. Therefore, this experimental framework can accurately and efficiently classify the frozen leaves of tea plants, which is of great value for evaluating the degree of freezing injury of tea plantations and provides technical support for the overwintering protection of tea plantations in the north.
李 赫，王 玉，范 凯，毛艺霖，丁仕波，宋大鹏，王梦琪，丁兆堂. 基于深度学习、小波变换和可见光谱的茶树冻害程度评估[J]. 光谱学与光谱分析, 2024, 44(01): 234-240.
LI He, WANG Yu, FAN Kai, MAO Yi-lin, DING Shi-bo, SONG Da-peng, WANG Meng-qi, DING Zhao-tang. Evaluation of Freezing Injury Degree of Tea Plant Based on Deep
Learning, Wavelet Transform and Visible Spectrum. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 234-240.
[1] Samarina L，Bobrovskikh A，Doroshkov A，et al. Frontiers in Genetics, 2020, 11: 611283.
[2] He K, Zhang X, Ren S, et al. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9): 1904.
[3] Ren S, He K, Girshick R, et al. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137.
[4] Redmon J, Divvala S, Girshick R, et al. Computer Vision & Pattern Recognition, 2016, 6(1): 779.
[5] Ma J, Du K, Zheng F, et al. Computers & Electronics in Agriculture, 2018, 154: 18.
[6] GUO Yang, XU Bei-bei, CHEN Gui-peng, et al(郭 阳, 许贝贝, 陈桂鹏, 等). Journal of Agricultural Science and Technology（中国农业科技导报）, 2021, 23(11)：99.
[7] Jothiaruna N，Sundar K, Karthikeyan B. Computers and Electronics in Agriculture, 2019, 165: 104934.
[8] XIE Xin-hui, TANG Li-jun, SONG Hai-zha, et al(谢新辉, 唐立军, 宋海吒, 等). Computer Engineering and Applications（计算机工程与应用）, 2012, (8): 197.
[9] Simonyan K, Zisserman A. Computer Science, 2014, 9: 1.
[10] Krizhevsky A, Sutskever I, Hinton G E. Communications of the ACM, 2017, 60(6): 84.
[11] Russakovsky O, Deng J, Su H, et al. International Journal of Computer Vision, 2015, 115(3): 211.
[12] XIE Juan-ying, HOU Qi, SHI Ying-huan, et al(谢娟英, 侯 琦, 史颖欢, 等). Journal of Computer Research and Development(计算机研究与发展), 2018, 55(8): 1609.
[13] Chang C, Lin C. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1.
[14] Mao Yilin, Li He, Wang Yu, et al. Frontiers in Plant Science, 2023, 14: 1096490.
