Computer vision for plant pathology: A review with examples from cocoa agriculture

Abstract

Plant pathogens can decimate crops and render the local cultivation of a species unprofitable. In extreme cases this has caused famine and economic collapse. Timing is vital in treating crop diseases, and the use of computer vision for precise disease detection and timing of pesticide application is gaining popularity. Computer vision can reduce labour costs, prevent misdiagnosis of disease, and prevent misapplication of pesticides. Pesticide misapplication is both financially costly and can exacerbate pesticide resistance and pollution. Here, we review the application and development of computer vision and machine learning methods for the detection of plant disease. This review goes beyond the scope of previous works to discuss important technical concepts and considerations when applying computer vision to plant pathology. We present new case studies on adapting standard computer vision methods and review techniques for acquiring training data, the use of diagnostic tools from biology, and the inspection of informative features. In addition to an in‐depth discussion of convolutional neural networks (CNNs) and transformers, we also highlight the strengths of methods such as support vector machines and evolved neural networks. We discuss the benefits of carefully curating training data and consider situations where less computationally expensive techniques are advantageous. This includes a comparison of popular model architectures and a guide to their implementation.

Intelligent pesticide recommendation system for cocoa plant using computer vision and deep learning techniques

“…The present production of cocoa beans in India is not sufficient to meet the demand of the industry [3]. This is because, cocoa plants are easily prone to diseases like black pod rot, anthracnose, stem canker, etc [4,5]. This will significantly impact the yield and quality of cocoa beans.…”

Resilient botany: Innovation in the face of limited mobility and resources

“…The third paper in this issue provides a focused review on the increasing use of CV for precise disease detection and optimal pesticide application timing, featuring case studies from agricultural practices in cocoa production. Here, Sykes et al ( 2024 ) underscore the advantages of CV, including cost reduction and prevention of misapplication, discussing financial and ecological implications. The analysis goes beyond previous work, exploring technical concepts in applying CV to plant pathology, training data acquisition, and insights into machine learning methods.…”

“…The authors highlight the significance of curated training data, exploring computationally efficient techniques and providing a comparative analysis of model architectures. Furthermore, Sykes et al ( 2024 ) discuss the evolving role of machine learning in optimizing pesticide application and provide a comprehensive perspective on applying CV in plant pathology, including practical considerations for data gathering and a roadmap for commercial implementation.…”

“…The gatoRs R package streamlines access to and use of digitized biodiversity data, while a cost‐effective moist chamber culture technique enhances our understanding of microbiota. The integration of computer vision in agriculture, discussed by Sykes et al ( 2024 ), demonstrates its potential for precise disease detection and pesticide application. Furthermore, the issue showcases accessible methods for lichen thalli hydrophobicity assessment and plant tissue sectioning, emphasizing simple and cost‐effective ways to advance research in plant physiology and anatomy.…”