Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Chinese Computer Science
  4. Volume 1, Issue 1
  5. Article
Volume 1, Issue 1
  • ISSN: 2665-9972
  • E-ISSN: 2665-9964

Abstract

Crop diseases are a primary hazard to nutrient safety, which proves to be a serious problem in many places in the world due to the unavailability of essential aid. Typically agriculturalists or specialists perceive the plants with a naked eye for detection and identification of an illness. Machine vision models, in specific Convolutional Neural Networks (CNNs) have directed an impact in feature extraction to a greater extent. Since 2015, numerous solicitations for the automatic classification and recognition of crop illnesses have been established.

In this paper, we proposed, analyzed, and assessed various state-of-the-art models proposed over a decade. These models are pre-trained with the finest parameters where we modeled a design-oriented method with numerous leaf-images and classified them into infection and healthy class for each type of leaf independently.

Through our examination, we concluded that VGG models stand-alone with many cited prototypes and give on par results. As declared, these VGG models (VGG16 and VGG19) are utilized for feature extraction, and further, we augmented a set of dense layers and train them consequently for classification. The performances of various machine vision prototypes were pictorially perceived and their sophisticated architecture is not only capable of extracting detailed features but also repressed many loop-holes. The performance is assessed and computed for several types of leaf images and the accuracy scores attained were more than 97.5% for VGG16 and 96.72% for VGG19.

AUC-ROC curves were portrayed to illustrate its inspiration in defining an accurate classification where VGG16 and VGG19 have at least 96.6% and 95% area under the curve (AUC) which resembles their robustness.

© 2021 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cccs/10.2174/2665997201999200811150433
2021-04-01
2024-11-26

  • From This Site

    /content/journals/cccs/10.2174/2665997201999200811150433
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. CamargoA. SmithJ.S. Image pattern classification for the identification of disease causing agents in plants.Comput. Electron. Agric.200966212112510.1016/j.compag.2009.01.003
     [Google Scholar]
  2. RumpfT. Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance.Comput. Electron. Agric.2010741919910.1016/j.compag.2010.06.009
     [Google Scholar]
  3. BashishA. Dheeb, Malik Braik, and Sulieman Bani-Ahmad. “A framework for detection and classification of plant leaf and stem diseases.” 2010 international conference on signal and image processing.IEEE2010
     [Google Scholar]
  4. Al-HiaryH. Fast and accurate detection and classification of plant diseases.Int. J. Comput. Appl.20111713138
     [Google Scholar]
  5. Al BashishD. BraikM. Bani-AhmadS. Detection and classification of leaf diseases using K-means-based segmentation and.Information Technology Journal201110226727510.3923/itj.2011.267.275
     [Google Scholar]
  6. ArivazhaganS. Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features.Agric. Eng. Int. CIGR J.2013151211217
     [Google Scholar]
  7. SladojevicS. ArsenovicM. AnderlaA. CulibrkD. StefanovicD. Deep neural networks based recognition of plant diseases by leaf image classificationComput. Intell. Neurosci.20162016328980110.1155/2016/328980127418923
     [Google Scholar]
  8. MohantyS.P. HughesD.P. SalathéM. Using deep learning for image-based plant disease detection.Front. Plant Sci.20167141910.3389/fpls.2016.0141927713752
     [Google Scholar]
  9. KrizhevskyA. SutskeverI. HintonG.E. Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems.201210971105
     [Google Scholar]
  10. SzegedyC. Going deeper with convolutions2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)201519Boston, MA, USA
     [Google Scholar]
  11. SinghV. MisraA.K. Detection of plant leaf diseases using image segmentation and soft computing techniques.Inf. Process. Agric.201741414910.1016/j.inpa.2016.10.005
     [Google Scholar]
  12. AmaraJihen BouazizBassem AlgergawyAlsayed A deep learning-based approach for banana leaf diseases classificationDatenbanksysteme für Business, Technologie und Web (BTW 2017)-Workshopband2017
     [Google Scholar]
  13. SaleemM.H. PotgieterJ. Mahmood ArifK. plant disease detection and classification by deep learning.Plants (Basel)811E468, 201910.3390/plants811046831683734
     [Google Scholar]
  14. PetrellisN. Mobile application for plant disease classification based on symptom signaturesProceedings of the 21st Pan-Hellenic Conference on Informatics201710.1145/3139367.3139368
     [Google Scholar]
  15. BrahimiM. BoukhalfaK. MoussaouiA. Deep learning for tomato diseases: classification and symptoms visualization.Appl. Artif. Intell.201731429931510.1080/08839514.2017.1315516
     [Google Scholar]
  16. OppenheimD. ShaniG. Potato disease classification using convolution neural networks.Adv. Anim. Biosci.20178224424910.1017/S2040470017001376
     [Google Scholar]
  17. FuentesAlvaro A robust deep-learning-based detector for real-time tomato plant diseases and pests recognitionSensors 17.9201710.3390/s17092022
     [Google Scholar]
  18. CamargoA. SmithJ.S. An image-processing based algorithm to automatically identify plant disease visual symptoms.Biosystems engineering 102.1(2009):921
     [Google Scholar]
  19. PrajwalaT.M. PranathiA. AshrithaK.S. B. ChittaragiNagaratna KoolagudiS. Tomato leaf disease detection using convolutional neural networksIEEE Xplore, Eleventh International Conference on Contemporary Computing (IC3)2018
     [Google Scholar]
  20. JeonW-S. RheeS-Y. Plant Leaf Recognition Using a Convolution Neural Network.Int. J. Fuzzy Logic Intelligent Syst.2017171263410.5391/IJFIS.2017.17.1.26
     [Google Scholar]
  21. MainkarP.M. GhorpadeS. AdawadkarM. Plant leaf disease detection and classification using image processing techniques.Int. J. Innovative Emerging Res. Engineering201524139144
     [Google Scholar]
  22. WallelignS. PolceanuM. BucheC. soybean plant disease identification using convolutional neural networkArtificial Intelligence Research Society Conference (FLAIRS-31)2018146151
     [Google Scholar]
  23. GoodfellowI. LeeH. LeQ.V. SaxeA. NgA.Y. Measuring invariances in deep networks.Adv. Neural Inform. Processings syst.2009646654
     [Google Scholar]
  24. LarssonG. MaireM. ShakhnarovichG. Fractalnet: Ultra-deep neural networks without residualsArXiv Preprint ArXiv:1605.076482016
     [Google Scholar]
  25. CortesC. GonzalvoX. KuznetsovV. MohriM. YangS. Adanet: Adaptive structural learning of artificial neural networksProceedings of the 34th Int. Conference Machine Learning JMLR702017874883
     [Google Scholar]
  26. XieS. GirshickR. DollárP. TuZ. HeK. Aggregated residual transformations for deep neural networksProceedings of the IEEE conference on computer vision and pattern recognition20171492150010.1109/CVPR.2017.634
     [Google Scholar]
  27. TanM. LeQ.V. Efficientnet: Rethinking model scaling for convolutional neural networksArXiv Preprint ArXiv:1905.119462019
     [Google Scholar]
  28. ZhouJ. CuiG. ZhangZ. YangC. LiuZ. WangL. LiC. SunM. Graph neural networks: a review of methods and applicationsarXiv preprint arXiv:1812.084341812
     [Google Scholar]
  29. LiY. TarlowD. BrockschmidtM. ZemelR. Gated graph sequence neural networksArXiv Preprint ArXiv:1511.054931511
     [Google Scholar]
  30. VeličkovićP. CucurullG. CasanovaA. RomeroA. LioP. BengioY. Graph attention networksArXiv Preprint ArXiv:1710.109031710
     [Google Scholar]
  31. CollobertR. J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa, “Natural language processing (almost) from scratch.J. Mach. Learn. Res.201112Aug24932537
     [Google Scholar]
  32. LeCunY. BottouL. BengioY. HaffnerP. Gradient-based learning applied to document recognition.Proceedings IEEE1998861122782324
     [Google Scholar]
  33. DengJ. DongW. SocherR. LiL-J. LiK. Imagenet: A large-scale hierarchical image database.CVPR2009
     [Google Scholar]
  34. PanS.J. YangQ. A survey on transfer learning.IEEE Trans. Knowl. Data Eng.201022101345135910.1109/TKDE.2009.191
     [Google Scholar]
  35. WeissK. KhoshgoftaarT.M. WangD. A survey of transfer learning.J. Big Data20163910.1186/s40537‑016‑0043‑6
     [Google Scholar]
  36. BengioY. Deep learning of representations for unsupervised and transfer learning.JMLR: Workshop Conference Proceedings2012271737
     [Google Scholar]
  37. MesnilG. DauphinY. GlorotX. RifaiS. BengioY. GoodfellowI. LavoieE. MullerX. DesjardinsG. Warde-FarleyD. VincentP. Unsupervised and transfer learning challenge: a deep learning approach.JMLR: Workshop and Conference Proceedings20122797111
     [Google Scholar]
  38. GuoY. LiuY. OerlemansA. LaoS. WuS. LewM.S. Deep learning for visual understanding: A review.Neurocomputing2016187274810.1016/j.neucom.2015.09.116
     [Google Scholar]
  39. IandolaF.N. HanS. MoskewiczM.W. AshrafK. DallyW.J. KeutzerK. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model sizeArXiv Preprint ArXiv:1602.073601602
     [Google Scholar]
  40. SmithS.L. KindermansP.J. YingC. LeQ.V. Don’t decay the learning rate, increase the batch sizeArXiv Preprint ArXiv:1711.004891711
     [Google Scholar]
  41. SzegedyC. VanhouckeV. IoffeS. ShlensJ. WojnaZ. Rethinking the inception architecture for computer vision.CVPR201610.1109/CVPR.2016.308
     [Google Scholar]
  42. SrivastavaR.K. GreffK. SchmidhuberJ. Highway networksArXiv Preprint ArXiv:1505.003871505
     [Google Scholar]
  43. MoodyJ DarkenC Learning with localized receptive fields
     [Google Scholar]
  44. LuoW. LiY. UrtasunR. ZemelR. Understanding the effective receptive field in deep convolutional neural networks.Adv. Neural Information Processing Syst.201648984906
     [Google Scholar]
  45. KarenS. andrewZ. Very deep convolutional networks for large-scale image recognitionArXiv 1409.1556.2014
     [Google Scholar]
  46. HeK. ZhangX. RenS. SunJ. Deep residual learning for Image recognitionComputer Vision and Pattern Recognition, Dec.2015
     [Google Scholar]
  47. HeK. ZhangX. Identity mappings in deep residual networksEuropean conference on computer vision2016, 630645
     [Google Scholar]
  48. HuangG. LiuZ. Van Der MaatenL. WeinbergerK.Q. Densely connected convolutional networksProceedings of the IEEE conference on computer vision and pattern recognition20174700470810.1109/CVPR.2017.243
     [Google Scholar]
  49. HowardA.G. ZhuM. ChenB. KalenichenkoD. WangW. WeyandT. AndreettoM. AdamH. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.ArXiv2017
     [Google Scholar]
  50. SandlerM. HowardA. ZhuM. ZhmoginovA. ChenL. MobileNetV2: Inverted Residuals and Linear Bottlenecks2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition201845104520Salt Lake City, UT10.1109/CVPR.2018.00474
     [Google Scholar]
  51. CholletF. Xception: deep learning with depthwise separable convolutionsConference on Computer Vision and Pattern Recognition7 Oct.2016
     [Google Scholar]
  52. LinM. ChenQ. YanS. Network in Network.CoRR2013
     [Google Scholar]
  53. LeCunY. BengioY. HintonG. Deep learning.Nature2015521436444
     [Google Scholar]
  54. GoodfellowI. BengioY. CourvilleA. Deep learning
     [Google Scholar]
  55. LeeC.Y. XieS. GallagherP. ZhangZ. TuZ. Deeply-supervised nets.Artificial Intelligence Statistics2015562570
     [Google Scholar]
  56. NairV. HintonG.E. Rectified linear units improve restricted boltzmann machinesIn Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML’10). Omnipress, Madison, WI, USA2010807814
     [Google Scholar]
  57. LiuW. WenY. YuZ. YangM. Large-margin softmax loss for convolutional neural networks.ICML201627
     [Google Scholar]
  58. BoureauY.L. BachF. LeCunY. PonceJ. Learning mid-level features for recognitionIEEE Computer Society Conference on Computer Vision and Pattern Recognition201025592566IEEE, 201010.1109/CVPR.2010.5539963
     [Google Scholar]
  59. HeK. ZhangX. RenS. SunJ. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.IEEE Trans. Pattern Anal. Mach. Intell.2015371904191610.1109/TPAMI.2015.238982426353135
     [Google Scholar]
  60. SmithS.L. KindermansP.J. YingC. LeQ.V. Don’t decay the learning rate, increase the batch sizeArXiv Preprint ArXiv:1711.004891711
     [Google Scholar]
  61. HofferE. HubaraI. SoudryD. Train longer, generalize better: closing the generalization gap in large batch training of neural networksAdvances in Neural Information Processing Syst.201717311741
     [Google Scholar]
  62. AbadiM. BarhamP. ChenJ. ChenZ. DavisA. DeanJ. DevinM. GhemawatS. IrvingG. IsardM. KudlurM. Tensorflow: A system for large-scale machine learning12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16)2016265283
     [Google Scholar]
  63. LeCunY. BoserB. DenkerJ.S. HendersonD. HowardR.E. HubbardW. JackelL.D. Backpropagation applied to handwritten zip code recognition.Neural Comput.198910.1162/neco.1989.1.4.541
     [Google Scholar]
  64. Hecht-NielsenR. Theory of the backpropagation neural network.Neural networks for perception.Academic Press1992659310.1016/B978‑0‑12‑741252‑8.50010‑8
     [Google Scholar]
  65. RumelhartD.E. HintonG.E. WilliamsR.J. Learning representations by back-propagating errors.Nature19863236088533536
     [Google Scholar]
  66. KingmaD. BaJ. Adam: A Method for Stochastic OptimizationInternational Conference on Learning Representations2014
     [Google Scholar]
  67. IoffeS. SzegedyC. Batch normalization: Accelerating deep network training by reducing internal covariate shiftICML2015
     [Google Scholar]
  68. SrivastavaN. HintonG.E. KrizhevskyA. SutskeverI. SalakhutdinovR. Dropout: A simple way to prevent neural networks from overfitting.JMLR2014
     [Google Scholar]
  69. DavisJ. GoadrichM. The relationship between Precision-Recall and ROC curvesProceedings of the 23rd international conference on Machine learning2006, 23324010.1145/1143844.1143874
     [Google Scholar]
  70. Hajian-TilakiK. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation.Caspian J. Intern. Med.2013462763524009950
     [Google Scholar]
/content/journals/cccs/10.2174/2665997201999200811150433
Loading
Leaf Image Classification with the Aid of Transfer Learning: A Deep Learning Approach
Current Chinese Computer Science 1, 61 (2021); https://doi.org/10.2174/2665997201999200811150433
/content/journals/cccs/10.2174/2665997201999200811150433
/content/journals/cccs/10.2174/2665997201999200811150433
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): automated plant diagnosis; CNNs; deep learning; Leaf classification; transfer learning

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test