基于深度残差网络与迁移学习的水稻病虫害图像识别

doi:10.13733/j.jcam.issn.2095-5553.2023.09.028

摘要/Abstract

摘要： 提出一个针对大多数类型的水稻害虫的图像识别方法。对ResNet34网络进行改进，提高网络的识别能，以实现基于给定的图像自动地识别分类出主要害虫。此外，基于迁移学习方法有效避免由于数据量缺乏而使得训练不足的问题。通过ImageNet数据库开展网络参数预训练能够进一步提升网络的提取性能，通过IDADP数据库可以开展参数微调工作以及训练工作。将提出的改进ResNet34模型与其他模型的性能进行对比评估。结果显示，改进ResNet34模型的识别准确度最高，F1-score达到0.98，证明所提模型对水稻病虫害图像具有较好的识别效果。

关键词: 水稻害虫, 深度残差网络, 迁移学习, 改进ResNet34模型, 卷积神经网络

Abstract: This paper presents an image recognition method for most types of rice pests. ResNet34 network is improved to realize the recognition ability of the network, so as to automatically recognize and classify the main pests based on the given image. In addition, the transfer learning method overcomes the shortcomings of insufficient training caused by insufficient data. Firstly, the ImageNet database is used for network parameter pre training to make the network have good feature extraction ability. According to the migration learning method, the IDADP database is used for parameter finetuning and training. In this paper, the performance of the proposed improved ResNet34 model is compared with other models. The results show that the improved ResNet34 model has the highest recognition accuracy, and the F1-score is 0.98, which proves that the proposed model has a good recognition effect on rice pest images.

Key words: rice pests, deep residual network, transfer learning, improved ResNet34 model, convolutional neural network

中图分类号:

TP391

汪健, 梁兴建, 雷刚. 基于深度残差网络与迁移学习的水稻病虫害图像识别[J]. 中国农机化学报, 2023, 44(9): 198-204.

Wang Jian, Liang Xingjian, Lei Gang. Image recognition of rice diseases and insect pests based on deep residual network and transfer learning[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(9): 198-204.

参考文献

［1］　Martineau M, Conte D, Raveaux R, et al. A survey on imagebased insect classification a survey on imagebased insects classification ［J］. Pattern Recogn, 2017, 65: 273-284.
［2］　郭阳, 许贝贝, 陈桂鹏, 等. 基于卷积神经网络的水稻虫害识别方法［J］. 中国农业科技导报, 2021, 23(11): 11.
［3］　Jia D, Wei D, Socher R, et al. ImageNet: A largescale hierarchical image database［C］. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.
［4］　肖德琴, 黄一桂, 张远琴,等. 基于改进Faster RCNN的田间黄板害虫检测算法［J］. 农业机械学报, 2021, 52(6): 10.Xiao Deqin, Huang Yigui, Zhang Yuanqin, et al. Pest detection algorithm of yellow plate in field based on improved Faster R-CNN［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(6): 10.
［5］　Mayo M, Watson A T. Automatic species identification of live moths ［J］. KnowledgeBased Systems, 2007, 20(2): 195-202.
［6］　Fina F, Birch P, Young R, et al. Automatic plant pest detection and recognition using kmeans clustering algorithm and correspondence filters［J］. International Journal of Advanced Biotechnology and Research, 2013, 4(2): 189-199.
［7］　Xie C, Zhang J, Li R, et al. Automatic classification for field crop insects via multipletask sparse representation and multiplekernel learning ［J］. Computers & Electronics in Agriculture, 2015, 119: 123-132.
［8］　Gassoumi H, Prasad N R, Ellington J J. Neural networkbased approach for insect classification in cotton ecosystems［C］∥International Conference on Intelligent Technologies. InTech 2000 Bangkok, Thailand, 2000, 7
［9］　唐聪, 凌永顺, 郑科栋,等. 基于深度学习的多视窗SSD目标检测方法［J］. 红外与激光工程, 2018, 47(1): 290-298.Tang Cong, Ling Yongshun, Zheng Kedong, et al. Object detection method of multiview SSD based on deep learning ［J］. Infrared and Laser Engineering, 2018, 47(1): 290-298.
［10］　Kamilaris A, PrenafetaBoldu F X. Deep learning in agriculture: A survey ［J］. Computers and Electronics in Agriculture, 2018, 147: 70-90.
［11］　Cheng X, Zhang Y, Chen Y, et al. Pest identification via deep residual learning in complex background［J］. Computers and Electronics in Agriculture, 2017, 141: 351-56.
［12］　Lim S, Kim S and Kim D. Performance effect analysis for insect classification using convolutional neural network ［C］. 2017 7th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 2017: 210-215.
［13］　He K, Zhang X, Ren S, et al. Deep residual learning for image recognition［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
［14］　Santurkar S, Tsipras D, Ilyas A, et al. How does batch normalization help optimization?［C］. Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018: 2483-2493.
［15］　Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting ［J］. The journal of machine learning research, 2014, 15(1): 1929-1958.
［16］　Pan S J, Qiang Y. A survey on transfer learning ［J］. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
［17］　Smith L N. Cyclical learning rates for training neural networks ［C］. 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2017: 464-472.
［18］　Abadi M, Chu A, Goodfellow I, et al. Deep learning with differential privacy［C］∥Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 2016: 308-318.
［19］　Martineau M, Conte D, Raveaux R, et al. A survey on imagebased insect classification［J］. Pattern Recognition, 2016, 65: 273-284.
［20］　Ebrahimi M A, Khoshtaghaza M H, Minaei S, et al. Visionbased pest detection based on SVM classification method ［J］. Computers and Electronics in Agriculture, 2017, 137: 52-58.

[1]	梁万杰, 曹静, 孙传亮, 曹宏鑫, 张文宇, . 基于深度学习的农作物病害识别系统研发[J]. 中国农机化学报, 2023, 44(9): 169-175.
[2]	杨波, 何金平, 张立娜. 基于改进SPP-x的YOLOv5神经网络水稻叶片病害识别检测[J]. 中国农机化学报, 2023, 44(9): 190-197.
[3]	吴潇, 杨颖, 刘刚, 张倩, 宁远霖. 基于迁移学习和改进ResNet34的猪个体识别方法[J]. 中国农机化学报, 2023, 44(9): 214-221.
[4]	余胜, 谢莉. 基于迁移学习和卷积视觉转换器的农作物病害识别研究[J]. 中国农机化学报, 2023, 44(8): 191-197.
[5]	李宗南, 蒋怡, 王思, 李源洪, 黄平, 魏鹏. 基于YOLOv5模型的飞蓬属入侵植物目标检测[J]. 中国农机化学报, 2023, 44(7): 200-206.
[6]	李平, 马玉琨, 李艳翠, 冯继克, 赵明富. 基于迁移学习的小麦籽粒品种识别研究[J]. 中国农机化学报, 2023, 44(7): 220-228.
[7]	周显沁, 韩震宇, 刘成源. 基于改进卷积神经网络与图像处理的蚕茧识别方法[J]. 中国农机化学报, 2023, 44(5): 100-106.
[8]	王磊, 袁英, 高玲. 基于改进多元宇宙算法的番茄病害图像识别[J]. 中国农机化学报, 2023, 44(5): 176-181.
[9]	付豪, , 赵学观, 翟长远, , 郑康, 郑申玉, 王秀. 基于深度学习的杂草识别方法研究进展[J]. 中国农机化学报, 2023, 44(5): 198-207.
[10]	李岩舟, 何艳洲, 覃锋, 钱万强, 吴媚, 乔曦, . 基于卷积神经网络的互花米草识别研究[J]. 中国农机化学报, 2023, 44(4): 159-166.
[11]	惠巧娟, 马伟, 边超. 融合强化注意力机制的农田杂草识别方法[J]. 中国农机化学报, 2023, 44(4): 195-201.
[12]	何雨霜, 王琢, 王湘平, 肖进, 罗友谊, 张俊峰. 深度学习在农作物病害图像识别中的研究进展[J]. 中国农机化学报, 2023, 44(2): 148-155.
[13]	刘宇泽, 孙涵, 李明洋, 李明心, 康巨涛, 王恩浩. 细粒度图像识别任务的多层和区域特征融合模型[J]. 中国农机化学报, 2023, 44(1): 199-207.
[14]	陈品岚, 张小花, 朱立学, 李浩林. 基于树莓派及深度学习的柑橘识别系统设计[J]. 中国农机化学报, 2022, 43(9): 131-136.
[15]	王晓婷, 赵展, 王阳, 李林, . 基于改进Mask R-CNN的植物表型智能检测算法[J]. 中国农机化学报, 2022, 43(8): 151-157.