Litcius/Paper detail

ResNet-Based Deep Convolutional Model for Automated Corn Leaf Disease Classification

Rajesh Dey, Deepak Banerjee, Vishnu Kant, Manish Kumar Singla, Ashish Kumar Singh, P William, Monish Khan

202516 citationsDOI

Abstract

Common Rust, Gray Leaf Spot and Blight and other corn leaf diseases may compromise agricultural activities in all corners of the world by lowering the harvest and quality of the crops. Blight causes plants to lose their leaves very fast; Common Rust with Puccinia sorghi and Grey Leaf Spot disrupt the photosynthesis process and cause losses. Early and accurate detection of diseases can be useful in timely treatments and reducing addiction to chemicals and finding food resources. The researchers have implemented Residual Networks (ResNet) to aid in the detection of several diseases. ResNet is based on a deep learning mechanism that enables it to classify images well. ResNet having processed the images of the maize leaves identified whether they were infected with common rust, grey leaf spot, blight or were normal and the success rate was 96%. When a model has a high precision and recall, it leads to a more accurate model. It supports the cultivation of crops, bolsters against various issues, and utilizes new technology to provide food to all.

Topics & Concepts

Leaf spotBlightRust (programming language)Artificial intelligenceDeep learningResidualAgronomyBiologyPrecision agriculturePlant diseasePattern recognition (psychology)Computer sciencePhotosynthesisResidual neural networkTraining setAgricultureMultispectral imageSmart Agriculture and AISmart Systems and Machine LearningPlant Disease Management Techniques
ResNet-Based Deep Convolutional Model for Automated Corn Leaf Disease Classification | Litcius