+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Convolutional Neural Networks for the Automatic Identification of Plant Diseases

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          Deep learning techniques, and in particular Convolutional Neural Networks (CNNs), have led to significant progress in image processing. Since 2016, many applications for the automatic identification of crop diseases have been developed. These applications could serve as a basis for the development of expertise assistance or automatic screening tools. Such tools could contribute to more sustainable agricultural practices and greater food production security. To assess the potential of these networks for such applications, we survey 19 studies that relied on CNNs to automatically identify crop diseases. We describe their profiles, their main implementation aspects and their performance. Our survey allows us to identify the major issues and shortcomings of works in this research area. We also provide guidelines to improve the use of CNNs in operational contexts as well as some directions for future research.

          Related collections

          Most cited references 45

          • Record: found
          • Abstract: found
          • Article: not found

          Reproducible research in computational science.

           Roger Peng (2011)
          Computational science has led to exciting new developments, but the nature of the work has exposed limitations in our ability to evaluate published findings. Reproducibility has the potential to serve as a minimum standard for judging scientific claims when full independent replication of a study is not possible.
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Pesticide Residues and Bees – A Risk Assessment

            Bees are essential pollinators of many plants in natural ecosystems and agricultural crops alike. In recent years the decline and disappearance of bee species in the wild and the collapse of honey bee colonies have concerned ecologists and apiculturalists, who search for causes and solutions to this problem. Whilst biological factors such as viral diseases, mite and parasite infections are undoubtedly involved, it is also evident that pesticides applied to agricultural crops have a negative impact on bees. Most risk assessments have focused on direct acute exposure of bees to agrochemicals from spray drift. However, the large number of pesticide residues found in pollen and honey demand a thorough evaluation of all residual compounds so as to identify those of highest risk to bees. Using data from recent residue surveys and toxicity of pesticides to honey and bumble bees, a comprehensive evaluation of risks under current exposure conditions is presented here. Standard risk assessments are complemented with new approaches that take into account time-cumulative effects over time, especially with dietary exposures. Whilst overall risks appear to be low, our analysis indicates that residues of pyrethroid and neonicotinoid insecticides pose the highest risk by contact exposure of bees with contaminated pollen. However, the synergism of ergosterol inhibiting fungicides with those two classes of insecticides results in much higher risks in spite of the low prevalence of their combined residues. Risks by ingestion of contaminated pollen and honey are of some concern for systemic insecticides, particularly imidacloprid and thiamethoxam, chlorpyrifos and the mixtures of cyhalothrin and ergosterol inhibiting fungicides. More attention should be paid to specific residue mixtures that may result in synergistic toxicity to bees.
              • Record: found
              • Abstract: not found
              • Article: not found

              A review of advanced techniques for detecting plant diseases


                Author and article information

                Front Plant Sci
                Front Plant Sci
                Front. Plant Sci.
                Frontiers in Plant Science
                Frontiers Media S.A.
                23 July 2019
                : 10
                1Department of Applied Geomatics, Université de Sherbrooke , Sherbrooke, QC, Canada
                2Vision and Imagery Team, Computer Research Institute of Montréal , Montréal, QC, Canada
                3Quebec Centre for Biodiversity Science (QCBS) , Montreal, QC, Canada
                Author notes

                Edited by: Jose Antonio Jimenez-Berni, Spanish National Research Council (CSIC), Spain

                Reviewed by: Jayme Garcia Arnal Barbedo, Brazilian Agricultural Research Corporation (EMBRAPA), Brazil; Amanda Ramcharan, Pennsylvania State University, United States

                *Correspondence: Justine Boulent justine.boulent@

                This article was submitted to Technical Advances in Plant Science, a section of the journal Frontiers in Plant Science

                Copyright © 2019 Boulent, Foucher, Théau and St-Charles.

                This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

                Page count
                Figures: 7, Tables: 2, Equations: 0, References: 61, Pages: 15, Words: 11108
                Funded by: Mitacs 10.13039/501100004489
                Funded by: Ministère de l'Économie, de la Science et de l'Innovation - Québec 10.13039/100013690
                Plant Science


                Comment on this article