计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211200009-6.doi: 10.11896/jsjkx.211200009

• 图像处理&多媒体技术 • 上一篇    下一篇

基于迁移学习和模型压缩的玉米病害识别方法

邓朋飞, 官铮, 王宇阳, 王学   

  1. 云南大学信息学院 昆明 650500
  • 出版日期:2022-11-10 发布日期:2022-11-21
  • 通讯作者: 官铮(gz_627@sina.com)
  • 作者简介:(2621399490@qq.com)
  • 基金资助:
    国家自然科学基金(61761045)

Identification Method of Maize Disease Based on Transfer Learning and Model Compression

DENG Peng-fei, GUAN Zheng, WANG Yu-yang, WANG Xue   

  1. School of Information,Yunnan University,Kunming 650500,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:DENG Peng-fei,born in 1991,postgra-duate.His main research interests include deep learning and image proces-sing.
    GUAN Zheng,born in 1982,Ph.D,associate professor,is a member of China Computer Federation.Her main research interests include deep learning,intelligent traffic control and so on.
  • Supported by:
    National Natural Science Foundation of China(61761045).

摘要: 传统的图像识别方法在对玉米病害图像进行识别时准确率低,而卷积神经网络对图像识别有很好的效果,但其网络模型计算量大、参数量多,使其难以依托算力有限的移动端设备在小样本应用中推广使用。因此,以提高玉米病害图像的准确率、降低网络参数和模型大小为目的,提出了一种结合迁移学习和模型压缩的卷积神经网络用于玉米病害识别。为提高模型的泛化性,对数据集进行增强,构建基于迁移学习的卷积神经网络结构。通过迁移学习,利用在ImageNet上预先训练改进的VGG16-Inception网络模型,对常见玉米病害图像进行迁移识别。实验表明,在ImageNet数据集上,利用迁移学习对玉米病害图像的平均识别准确率达到93.38%。在迁移完成后,结合通道剪枝和知识蒸馏的方法对模型进行压缩,压缩后的模型再利用迁移学习进行玉米病害图像识别。实验表明:压缩后对玉米病害图像的平均识别准确率达到92.40%,准确率下降了0.98%,模型大小由73.90 MB压缩到9.45 MB,参数量减少了87.80%。本方法能够在小样本场景下确保识别准确率,并进一步实现模型轻量化。

关键词: 卷积神经网络, 玉米病害图像, 迁移学习, 图像识别, 模型压缩

Abstract: Traditional image recognition methods have low accuracy in recognizing maize disease images,and convolutional neural networks have a good effect on image recognition.However,the network model has a large amount of calculation and a large amount of parameters,making it difficult to rely on mobile devices with limited computing power to popularize and use in small sample applications.Therefore,this paper aims to improve the accuracy of maize disease images,reduce network parameters and model size,and proposes a convolutional neural network model that combines migration learning and model compression for maize disease recognition.In order to improve the generalization of the model,the data set is enhanced and the structure of convolutional neural network based on transfer learning is constructed.In this paper,the migration recognition of common maize disease images is carried out by using the improved VGG16-Inception network model pre-trained on ImageNet through transfer learning.Experimental results show that the average recognition accuracy of maize disease images using transfer learning is 93.38% on ImageNet data set.After the migration,the model is compressed by channel pruning and knowledge distillation,and the compressed model is used to recognize the maize disease image by transfer learning.Experimental results show that the average recognition accuracy of corn disease image after compression reaches 92.40%,the accuracy is reduced by 0.98%,the model size is compressed from 73.90 MB to 9.45 MB,and the number of parameters is reduced by 87.80%.The proposed method can ensure the recognition accuracy in small sample scenarios and further realize the model lightweight.

Key words: Convolutional neural network, Maize disease image, Transfer learning, Image identification, Model compression

中图分类号: 

  • TP391
[1]MENG Y,CHEN G F,LU J,et el.Simulink platform real-time diagnosis in the video image of corn diseases[J].Journal of Jilin Agricultural University,2017,39(4):483-487.
[2]LV G Z,CHEN J,BAI J K,at el.Present situation and control measures of corn diseases in China[J].Plant Protection,1997,23(4):20-21.
[3]MILLER S A,BEED F D,HARMON C L.Plant disease diagnostic capabilities and networks[J].Annual Review of Phytopathology,2009,47(1):15-38.
[4]LI Q Q,GUO M K,GUO C,et al.Occurrence dynamics of maize diseases in Gansu Province[J].Plant Protection,2014,40(3):161-164.
[5]KUSSUL N,LAVRENIUK M,SKAKUN S,et al.Deep learning classification of land cover and crop typs using remote sensing data[J/OL].IEEE Geoscience and Remote Sensing Letters,2017,PP(99):1-5.https://xueshu.baidu.com/usercenter/paper/show?paperid=b525470daa7f9623c2f138d8cca55d17&site=xueshu_se.
[6]KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetclassifica-tion with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25(2):1097-1105.
[7]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[8]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9.
[9]HE K,ZHANG S R,SUN J.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:770-778.
[10]YANG Y,ZHANG Y L,MIAO W,et al.Accurate identification and location of corn rhizome based on Faster R-CNN[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):46-53.
[11]GAO Y,GUO J L,LI X,et al.Instance-level segmentationmethod for group pig images based on deep learning[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(4):179-187.
[12]BI S,GAO F,CHEN J W,et al.Detection method of citrus based on deep convolution neural network[J].Transacions of the Chinese Society for Agricultural Machinery,2019,50(5):181-186.
[13]LIU Y B,LEI B,CAO Y,et al.Recognition of maize disease based on deep convolutional Neural network[J].Chinese Agricultural Science Bulletin,2018,34(36):15-9-164.
[14]YANG M Y,ZHANG Y G,LIU T.Small sample recognition of maize disease based on convolutional neural network[J].Chinese Journal of Eco-Agriculture(Chinese and English),2020,28(12):1924-1931.
[15]XU Y,ZHAO B,ZHAI Y,et al.Maize Diseases Identification Method Based on Multi-Scale Convolutional Global Pooling Neural Network[J].IEEE Access,2021,9:27959-27970.
[16]HAN S,MAO H Z,DALLY W J.Deep compression:com-pressing deep neural networks with pruning,trained quantization and huffman coding[J].Fiber,2015,56(4):3-7.
[17]HINTON G,VINYALS O,DEAN J.Distilling the knowledge in a neural network[J].arXiv:1503.02531,2014.
[1] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[2] 方义秋, 张震坤, 葛君伟.
基于自注意力机制和迁移学习的跨领域推荐算法
Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning
计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[3] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[4] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[5] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[6] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[7] 张颖涛, 张杰, 张睿, 张文强.
全局信息引导的真实图像风格迁移
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[8] 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮.
基于DNGAN的磁共振图像超分辨率重建算法
Super-resolution Reconstruction of MRI Based on DNGAN
计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[9] 刘月红, 牛少华, 神显豪.
基于卷积神经网络的虚拟现实视频帧内预测编码
Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network
计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179
[10] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[11] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[12] 孙福权, 崔志清, 邹彭, 张琨.
基于多尺度特征的脑肿瘤分割算法
Brain Tumor Segmentation Algorithm Based on Multi-scale Features
计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217
[13] 吴子斌, 闫巧.
基于动量的映射式梯度下降算法
Projected Gradient Descent Algorithm with Momentum
计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039
[14] 王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰.
基于多源迁移学习的大坝裂缝检测
Dam Crack Detection Based on Multi-source Transfer Learning
计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124
[15] 楚玉春, 龚航, 王学芳, 刘培顺.
基于YOLOv4的目标检测知识蒸馏算法研究
Study on Knowledge Distillation of Target Detection Algorithm Based on YOLOv4
计算机科学, 2022, 49(6A): 337-344. https://doi.org/10.11896/jsjkx.210600204
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!