首页 > 分享 > 基于神经结构搜索的多种植物叶片病害识别

基于神经结构搜索的多种植物叶片病害识别

花匠小妙招
2024-09-15 10:01

摘要: 为实现植物病害的自动准确识别，该研究提出一种基于神经结构搜索的植物叶片图像病害识别方法，该方法能够依据特定数据集自动学习到合适的深度神经网络结构。采用包含14种作物和26种病害共54 306张的公开PlantVillage植物病害图像作为试验数据，按照4∶1的比例随机划分，分别用于神经结构搜索和测试搜索到的最优网络结构的性能。同时，为探究神经结构搜索对数据平衡问题是否敏感及图像在缺乏颜色信息时对神经结构搜索的影响，对训练数据进行过采样和亚采样平衡处理及灰度变换。试验结果显示，该研究方法在训练样本数据不平衡和平衡时均可以搜索出合适的网络结构，模型识别准确率分别为98.96%和99.01%；当采用未进行平衡处理的灰度图像作为训练数据时，模型识别准确率有所下降，为95.40%。该方法能够实现植物病害的准确识别，为科学制定病害防治策略提供有效的技术手段。

关键词: 病害 / 图像识别 / 植物 / 分类 / 神经结构搜索

Abstract: Abstract: A plant disease is one of the key factors affecting the yield and safety of agricultural products. Traditional monitoring methods rely mainly on field sampling, and thereby to assess the species and severity of diseases, normally implemented by plant conservation experts. Nevertheless, the time-consuming and laborious method cannot meet the application requirements of rapid detection in actual large-scale production in modern agriculture. Alternatively, the image analysis method for automatic identification of plant diseases can provide an effective technical way for the real-time monitoring, particularly on deep learning algorithms with the advantages of high spatial resolution and high speed. However, most previous methods strongly depend on the experience of experts during the design of deep neural network architectures. It is inevitable to frequently adjust the network architecture and parameters, in order to obtain the optimal recognition model. In this study, a disease recognition method from plant leaf image was proposed based on the Neural Architecture Search (NAS). Bayesian Optimization (BO) algorithm was used to guide the network morphism, and thereby the network architecture can be selected as the optimal operation of network morphism every time. The proposed method can also automatically learn the appropriate deep neural network architecture according to the specific data set. A total of 54 306 plant disease images including 14 crops and 26 diseases of PlantVillage were used as experimental data. The balanced data after oversampling and subsampling, and the data after grayscale processing, where the 80% of images were used as the training dataset, whereas, the rest as the testing dataset. Firstly, the initial architecture of NAS was set as a three-layer convolutional neural network. Each layer was set as a convolution block, including a ReLU layer, a batch-normalization layer, a convolutional layer, and a pooling layer. Training data was used as the NAS input, while, the search history can be all generated network architecture, parameters learned from network architecture, and model loss values. Secondly, the acquisition function algorithm was optimized to generate the next network architecture for the observation. In the algorithm, the input data can be taken as the minimum temperature, cooling rate and search history of simulated annealing algorithm, whereas, the output data can be the new network architecture, and the required network morphing operation, in order to transform the existing architecture into a new one. After that, it needed to divide the data into multiple batches, and then to train each searched neural architecture. The optimal network architecture was automatically marked when the given search time reached. As such, the required network architecture was finally trained to obtain the disease classification model. Consequently, the disease identification can be gained using the test data as input to the model. Experimental results showed that the proposed method can search the appropriate network architecture in a short time. Furthermore, the method can also find out the optimal network structure, when the training sample data was in unbalanced and balanced conditions, where the accuracies of model recognition were 98.96% and 99.01%, respectively. Additionally, the color information of images related to plant disease has a positive promoting effect on the recognition of the diseases. Nevertheless, the accuracy of model recognition relatively decreased to 95.40%, when the gray image without balance processing was used as the training data. The proposed method can effectively simplify the workload of network architecture design, while identify accurately plant diseases, and thereby to provide a promising technical way for scientific formulation of disease control strategies.

[1] Kaur S, Pandey S, Goel S. Plants disease identification and classification through leaf images: A survey[J]. Arch Comput Method Eng, 2018, 26(4): 1-24. [2] 翁杨，曾睿，吴陈铭，等. 基于深度学习的农业植物表型研究综述[J]. 中国科学：生命科学，2019，49(6)：698-716. Weng Yang, Zeng Rui, Wu Chenming, et al. A survey on deep-learning-based plant phenotype research in agriculture[J]. Scientia Sinica Vitae, 2019, 49(6): 698-716. (in Chinese with English abstract) [3] Mohanty S P, Hughes D P, Salathe M, et al. Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016, 7: 1-10. [4] Esgario J G, Krohling R A, Ventura J A, et al. Deep learning for classification and severity estimation of coffee leaf biotic stress[J]. Computers and Electronics in Agriculture, 2020, 169: 105162. [5] Bock C H, Poole G H, Parker P E, et al. Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging[J]. Critical Reviews in Plant Sciences, 2010, 29(2): 59-107. [6] Ghosal S, Blystone D, Singh A K, et al. An explainable deep machine vision framework for plant stress phenotyping[J]. Proceedings of the National Academy of Sciences, 2018, 115(18): 4613-4618. [7] 张飞云. 基于量子神经网络和组合特征参数的玉米叶部病害识别[J]. 南方农业学报，2013，44(8)：1286-1290. Zhang Feiyun. Recognition of corn leaf disease based on quantum neural network and combination characteristic parameter[J]. Journal of Southern Agriculture, 2013, 44(8): 1286-1290. (in Chinese with English abstract) [8] 许良凤，徐小兵，胡敏，等. 基于多分类器融合的玉米叶部病害识别[J]. 农业工程学报，2015，31(14)：194-201. Xu Liangfeng, Xu Xiaobing, Hu Min, et al. Corn leaf disease identification based on multiple classifiers fusion[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2015, 31(14): 194-201. (in Chinese with English abstract) [9] 祁钊，江朝晖，杨春合，等. 基于图像技术的玉米叶部病害识别研究[J]. 安徽农业大学学报，2016，43(2)：325-330. Qi Zhao, Jiang Zhaohui, Yang Chunhe, et al. Identification of maize leaf diseases based on image technology[J]. Journal of Anhui Agricultural University, 2016, 43(2): 325-330. (in Chinese with English abstract) [10] 贾少鹏，高红菊，杭潇. 基于深度学习的农作物病虫害图像识别技术研究进展[J]. 农业机械学报，2019，50(S1)： 313-317. Jiang Shaopeng, Gao Hongju, Hang Xiao. Research progress on image recognition technology of crop pests and diseases based on deep learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1): 313-317. (in Chinese with English abstract) [11] Ferentinos K P. Deep learning models for plant disease detection and diagnosis[J]. Computers and Electronics in Agriculture, 2018, 145: 311-318. [12] Srdjan S, Marko A, Andras A, et al. Deep neural networks based recognition of plant diseases by leaf image classification[J]. Computational Intelligence and Neuroscience, 2016(6): 1-11. [13] Alvaro F, Sook Y, Sang K, et al. A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition[J]. Sensors-Basel, 2017, 17(9): 1-21. [14] Wang Guan, Sun Yu, Wang Jianxin. Automatic image-based plant disease severity estimation using deep learning[J]. Computational Intelligence & Neuroscience, 2017(2017): 1-8. [15] 孙俊，谭文军，毛罕平，等. 基于改进卷积神经网络的多种植物叶片病害识别[J]. 农业工程学报，2017，33(19)： 209-215. Sun Jun, Tan Wenjun, Mao Hanping, et al. Recognition of multiple plant leaf diseases based on improved convolutional neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(19): 209-215. (in Chinese with English abstract) [16] 马浚诚，杜克明，郑飞翔，等. 基于卷积神经网络的温室黄瓜病害识别系统[J]. 农业工程学报，2018，34(12)： 186-192. Ma Juncheng, Du Keming, Zheng Feixiang, et al. Disease recognition system for greenhouse cucumbers based on deep convolutional neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(12): 186-192. (in Chinese with English abstract) [17] Singh U P, Chouhan S S, Jain S, et al. Multilayer convolution neural network for the classification of mango leaves infected by anthracnose disease[J]. IEEE Access, 2019, 7: 43721-43729. [18] Barbedo J G. Plant disease identification from individual lesions and spots using deep learning[J]. Biosystems Engineering, 2019, 180: 96-107. [19] Nazki H, Yoon S, Fuentes A, et al. Unsupervised image translation using adversarial networks for improved plant disease recognition[J]. Computers and Electronics in Agriculture, 2020, 168: 105117. [20] 郭小清，范涛杰，舒欣. 基于改进Multi-Scale AlexNet的番茄叶部病害图像识别[J]. 农业工程学报，2019，35(13)： 162-169. Guo Xiaoqing, Fan Taojie, Shu Xin. Tomato leaf diseases recognition based on improved Multi-Scale AlexNet[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(13): 162-169. (in Chinese with English abstract) [21] 刘洋，冯全，王书志. 基于轻量级CNN的植物病害识别方法及移动端应用[J]. 农业工程学报，2019，35(17)： 194-204. Liu Yang, Feng Quan, Wang Shuzhi. Plant disease identification method based on lightweight CNN and mobile application[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(17): 194-204. (in Chinese with English abstract) [22] Elsken T, Metzen J H, Hutter F, et al. Neural architecture search: A survey[J]. Journal of Machine Learning Research, 2019, 20(55): 1-21. [23] Zoph B, Le Q V. Neural architecture search with reinforcement learning[C]//International Conference on Learning Representations. Toulon, France: 2017. [24] Zoph B, Vasudevan V K, Shlens J, et al. Learning transferable architectures for scalable image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: 2018: 8697-8710. [25] Adedoja A, Owolawi P A, Mapayi T. Deep learning based on NASNet for plant disease recognition using leave images[C]// 2019 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD). Winterton, South Africa: 2019. [26] Wei Tao, Wang Changhu, Rui Yong, et al. Network morphism[C]// International Conference on Machine Learning, Budapest, Hungary: 2016: 564-572. [27] Cai Han, Chen Tianyao, Zhang Weinan, et al. Efficient architecture search by network transformation[C]// 2018 National Conference on Artificial Intelligence, AAAI, New Orleans, USA: 2018: 2787-2794. [28] Elsken T, Metzen J H, Hutter F. Simple and efficient architecture search for convolutional neural networks[J/OL]. arXiv,: Machine Learning, 2017[2017-11-13]. https: //arxiv. org/abs/1711. 04528 [29] Jin Haifeng, Song Qingquan, Hu Xia. Auto-keras: An efficient neural architecture search system[C]// the 25th ACM SIGKDD International Conference. Anchorage, AK, USA: 2019: 1946-1956. [30] Hughes D P, Salathe M. An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing[J/OL]. arXiv: Computers and Society, 2015-11-25[2016-04-12]. https: //arxiv. org/abs/1511. 08060 [31] Barbedo J G A , Koenigkan L V , Santos T T . Identifying multiple plant diseases using digital image processing[J]. Biosystems Engineering, 2016, 147:104-116.