Deep Learning for Image-Based Cassava Disease Detection

Abstract

Cassava is the third largest source of carbohydrates for human food in the world but is vulnerable to virus diseases, which threaten to destabilize food security in sub-Saharan Africa. Novel methods of cassava disease detection are needed to support improved control which will prevent this crisis. Image recognition offers both a cost effective and scalable technology for disease detection. New deep learning models offer an avenue for this technology to be easily deployed on mobile devices. Using a dataset of cassava disease images taken in the field in Tanzania, we applied transfer learning to train a deep convolutional neural network to identify three diseases and two types of pest damage (or lack thereof). The best trained model accuracies were 98% for brown leaf spot (BLS), 96% for red mite damage (RMD), 95% for green mite damage (GMD), 98% for cassava brown streak disease (CBSD), and 96% for cassava mosaic disease (CMD). The best model achieved an overall accuracy of 93% for data not used in the training process. Our results show that the transfer learning approach for image recognition of field images offers a fast, affordable, and easily deployable strategy for digital plant disease detection.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 25

1. 1.

   Abdullakasim W. Powbunthorn K. Unartngam J. Takigama T. (2011 ). An images analysis technique for recognition of brown leaf spot disease in cassava. Tarım. Makinaları. Bilimi. Dergisi. 7, 165–169.

   Not in our library

2. 2.

   Aduwo J. R. Mwebaze E. Quinn J. A. (2010 ). Automated vision-based diagnosis of Cassava Mosaic Disease, in Industrial Conference on Data Mining-Workshops (New York, NY), 114–122.

   Not in our library

3. 3.

   Bellotti A. C. Smith L. Lapointe S. L. (1999 ). Recent advances in cassava pest management. Ann. Rev. Entomol. 44, 343–370.

   Not in our library10.1146/annurev.ento.44.1.343

4. 4.

   De Bruijn G. Fresco L. (1989 ). The importance of cassava in world food production. Netherl. J. Agric. Sci. 37, 21–34.

   Not in our library

5. 5.

   Dubey S. R. Jalal A. S. (2014 ). Adapted approach for fruit disease identification using images. arXiv preprint arXiv:1405.4930.

   Not in our library

6. 6.

   FAOSTAT (2017 ). Faostat:Food and Agriculture Data. Rome: FAOSTAT. (Accessed Jan 04, 2017).

   Not in our library

7. 7.

   Gibson D. Burghardt T. Campbell N. Canagarajah N. (2015 ). Towards automating visual in-field monitoring of crop health, in IEEE International Conference on Image Processing (ICIP), 2015 (Quebec City, QC: IEEE), 3906–3910.

   Not in our library

8. 8.

   Karpathy A. Toderici G. Shetty S. Leung T. Sukthankar R. Fei-Fei L. (2014 ). Large-scale video classification with convolutional neural networks, in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (Columbus), 1725–1732.

   Not in our library

9. 9.

   Legg J. (1999 ). Emergence, spread and strategies for controlling the pandemic of cassava mosaic virus disease in east and central africa. Crop Protect. 18, 627–637.

   Not in our library10.1016/s0261-2194(99)00062-9

10. 10.

    Legg J. Owor B. Sseruwagi P. Ndunguru J. (2006 ). Cassava mosaic virus disease in east and central africa: epidemiology and management of a regional pandemic. Adv. Virus Res. 67, 355–418.

    Not in our library10.1016/s0065-3527(06)67010-3

11. 11.

    Mbanzibwa D. Tian Y. Tugume A. Mukasa S. Tairo F. Kyamanywa S.. (2011 ). Simultaneous virus-specific detection of the two cassava brown streak-associated viruses by rt-pcr reveals wide distribution in east africa, mixed infections, and infections in manihot glaziovii. J. Virol. Methods 171, 394–400.

    Not in our library10.1016/j.jviromet.2010.09.024

12. 12.
    Using Deep Learning for Image-Based Plant Disease Detection · 2016

    No notice
13. 13.

    Mwebaze E. Owomugisha G. (2016 ). Machine learning for plant disease incidence and severity measurements from leaf images, in Machine Learning and Applications (ICMLA), 2016 15th IEEE International Conference on (IEEE) (Anaheim, CA).

    Not in our library

14. 14.

    Nagayet O. (2005 ). Small farms: current status and key trends, in The Future of Small Farms: Proceedings of a Research Workshop (Washington, DC), 355–367.

    Not in our library

15. 15.
    Molecular biodiversity of cassava begomoviruses in Tanzania: evolution of cassava geminiviruses in Africa and evidence for East Africa being a center of diversity of cassava geminiviruses · 2005

    Not checked
16. 16.

    Nichols R. (1950 ). The brown streak disease of cassava: distribution, climatic effects and diagnostic symptoms. East Afr. Agric. J. 15, 154–160.

    Not in our library10.1080/03670074.1950.11664727

17. 17.

    Nweke F. I. Spencer D. S. Lynam J. K. (2002 ). The Cassava Transformation: Africa's Best-Kept Secret. East Lansing.

    Not in our library

18. 18.

    Puig E. Gonzalez F. Hamilton G. Grundy P. (2015 ). Assessment of crop insect damage using unmanned aerial systems: a machine learning approach, in 21st International Congress on Modelling and Simulation (MODSIM2015), (Gold Coast, QLD). Available online at: https://eprints.qut.edu.au/95241/

    Not in our library

19. 19.

    Siricharoen P. Scotney B. Morrow P. Parr G. (2016 ). A lightweight mobile system for crop disease diagnosis, in International Conference Image Analysis and Recognition, (Póvoa de Varzim: Springer), 783–791.

    Not in our library

20. 20.

    Skovgård H. Tomkiewicz J. Nachman G. Münster-Swendsen M. (1993 ). The effect of the cassava green mite mononychellus tanajoa on the growth and yield of cassava manihot esculenta in a seasonally dry area in kenya. Exp. Appl. Acarol. 17, 41–58.

    Not in our library

21. 21.

    Storey H. (1936 ). Virus diseases of east african plants: V.—streak disease of maize. East Afr. Agric. J. 1, 471–475.

    Not in our library

22. 22.

    Szegedy C. Vanhoucke V. Ioffe S. Shlens J. Wojna Z. (2016 ). Rethinking the inception architecture for computer vision, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Las Vegas), 2818–2826.

    Not in our library

23. 23.

    Thresh J. Fargette D. Otim-Nape G. (1994 ). Effects of african cassava mosaic geminivirus on the yield of cassava. Trop. Sci. Lond. 34, 26–26.

    Not in our library

24. 24.

    Warburg O. (1894 ). Die Kulturpflanzen Usambaras. Mitteilungen aus den Deutschen Schutzgebieten 7, 131.

    Not in our library

25. 25.

    Yosinski J. Clune J. Bengio Y. Lipson H. (2014 ). How transferable are features in deep neural networks?, in Advances in Neural Information Processing Systems (Montreal), 3320–3328.

    Not in our library

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.