Identifying multiple plant diseases using digital image processing

• Published in: Biosystems engineering Vol. 147; pp. 104 - 116
• Main Authors: Barbedo, Jayme Garcia Arnal, Koenigkan, Luciano Vieira, Santos, Thiago Teixeira
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.07.2016
• Subjects: abiotic stress; Algorithms; Automatic disease recognition; Color; Colour; Colour transformations; digital images; Diseases; image analysis; leaves; Plant diseases; plant diseases and disorders; Plants (organisms); Visible symptoms; Automatic disease recognition; Visible symptoms; Colour transformations
• DOI: 10.1016/j.biosystemseng.2016.03.012
• ISSN: 1537-5110

The gap between the current capabilities of image-based methods for automatic plant disease identification and the real-world needs is still wide. Although advances have been made on the subject, most methods are still not robust enough to deal with a wide variety of diseases and plant species. This paper proposes a method for disease identification, based on colour transformations, colour histograms and a pairwise-based classification system. Its performance was tested using a large database containing images of symptoms belonging to 82 different biotic and abiotic stresses, affecting the leaves of 12 different plant species. The wide variety of images used in the tests made it possible to carry out an in-depth investigation about the main advantages and limitations of the proposed algorithm. A comparison with other algorithms is also presented, and some possible solutions for the main challenges that still prevent this kind of tool to be adopted in practice. •An algorithm for identifying multiple plant diseases is proposed.•It is based on image processing applied to conventional colour images.•It does not depend on any input or response from the user.•Tests considered 12 plant species and 82 diseases.•Accuracy varied between 40% and 80% for the plant species considered.