|Table of Contents|

Research on the Application of Tomato Disease Identification Based on Model Compression

《北方园艺》[ISSN:1001-0009/CN:23-1247/S]

Issue:
2023年10
Page:
138-144
Research Field:
Publishing date:

Info

Title:
Research on the Application of Tomato Disease Identification Based on Model Compression
Author(s):
DUAN Junming1; YANG Xiang1; 2; DONG Minggang1; 2
(1.School of Information Science and Engineering,Guilin University of Technology,Guilin,Guangxi 541004;2.Guangxi Key Laboratory of Embedded Technology and Intelligent System,Guilin University of Technology,Guilin,Guangxi 541004)
Keywords:
tomato diseases; convolutional neural networks; pyramid squeeze attention; knowledge distillation; raspberry
PACS:
-
DOI:
10.11937/bfyy.20222864
Abstract:
Early detection of tomato leaf disease category is conducive to rapid diagnosis and treatment to save crop losses.The traditional method of tomato disease identification based on deep learning has the problems of large model size and large consumption of computing resources,which is not suitable for direct deployment on portable devices with low computing power and limited storage space.In this study,knowledge distillation technology was used to compress the model,and pyramid squeeze attention module was used to improve the teacher network ResNet50 to enhance the network performance.Under the guidance of the teacher network,the student network ShuffleNetV2 had achieved excellent performance.By selecting tomato diseased leaves in PlantVillage dataset for experiment,the experimental results showed that the distilled network KD-ShuffleNetV2 improved the accuracy of the model,and saved more storage space and computing resources than deep convolution neural networks Alexnet,Vgg11,and ResNet50.The network achieved 95.66% recognition accuracy on tomato disease dataset,and the size of the model was only 4.98 MB.Finally,the model was transplanted and deployed to the low-cost Raspberry Pi to complete the tomato leaf recognition system development and recognition application.

References:

[1]郭利进,李言.基于DCNN的玉米叶部病害识别方法[J].粮食与油脂,2022,35(3):72-75,98.[2]张建华,孔繁涛,吴建寨,等.基于改进VGG卷积神经网络的棉花病害识别模型[J].中国农业大学学报,2018,23(11):161-171.[3]宋晨勇,白皓然,孙伟浩,等.基于GoogLeNet改进模型的苹果叶病诊断系统设计[J].中国农机化学报,2021,42(7):148-155.[4]黄林生,罗耀武,杨小冬,等.基于注意力机制和多尺度残差网络的农作物病害识别[J].农业机械学报,2021,52(10):264-271.[5]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Las Vegas:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016.[6]MA N,ZHANG X,ZHENG H T,et al.Shufflenetv2:Practical guidelines for efficient cnn architecture design[C]//Munich: Proceedings of the European Conference on Computer Vision (ECCV),2018.[7]HUGHES D,SALATHE M.An open access repository of images on plant health to enable the development of mobile disease diagnostics[EB/OL].https://arxiv.org/abs/1511.08060.2015-11-25.[8]HINTON G,VINYALS O,DEAN J.Distilling the knowledge in a neural network[J].Computer Science,2015,14(7):38-39.[9]郝立扬.基于量化卷积神经网络的模型压缩方法研究[D].成都:电子科技大学,2020.[10]YIM J,JOO D,BAE J,et al.A gift from knowledge distillation:Fast optimization,network minimization and transfer learning[C]//Honolulu: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017.[11]KIM Y,RUSH A M.Sequence-level knowledge distillation[C]//Texas: Proceedings of the 2016 conference on Empirical Methods in Natural Language Processing,2016.[12]GOU J,YU B,MAYBANK S J,et al.Knowledge distillation:A survey[J].International Journal of Computer Vision,2021,129(6):1789-1819.[13]黄震华,杨顺志,林威,等.知识蒸馏研究综述[J].计算机学报,2022,45(3):624-653.[14]XU C,GAO W,LI T,et al.Teacher-student collaborative knowledge distillation for image classification[J].Applied Intelligence,2023,2(53):1997-2009.[15]ZHANG H,ZU K,LU J,et al.EPSANet:An efficient pyramid squeeze attention block on convolutional neural network[C]//Macau:Proceedings of the Asian Conference on Computer Vision，2022 .[16]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Salt Lake : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018.[17]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25(2):84-90.[18]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//San Diego:Proceedings of the 3rd International Conference on Learning Representations,2015.[19]赵宏宇,沈江,安邦.基于代价敏感方法的智能制造故障诊断[J].计算机集成制造系统,2019,25(9):2180-2187.[20]贾兆红,张袁源,王海涛,等.基于Res2Net的双线性注意力番茄病害时期识别方法[J].农业机械学报,2023,53(7):259-266.

Memo

Memo:
-
Last Update: 2023-07-13