Corn Leaf Disease Recognition Using Convolutional Neural Network DenseNet

View at publisher Summarise with VIRAT
Authors: Mohamad Shahrulnizam Rosmadi, Ahmad Nazmi Fadzal, Wan Muhammad Ikhwan Wan Mohammad, Nazuha Fadzal, Ahmad Nazri Fadzal
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Corn crop is one of the major agricultural products in the world, but its production is always under a threat of a leaf diseases. This paper was focus on the shortcomings of the traditional and manual method of disease detection that is costly in terms of time consumption and human error. The objectives are to identify the characteristics of corn leaf diseases, develop a prototype to recognize them using a Convolutional Neural Network (CNN) DenseNet, and evaluate the prototype's performance. The current study used a dataset of corn leaf images (PlantVillage) that was downloaded from Kaggle, which were put through a set of preprocessing steps, such as resizing, normalization, and data augmentation to increase the diversity and segmentation of the dataset. A CNN DenseNet model architecture was created to classify, with the use of two-phase training strategy that entailed feature extraction and fine-tuning, and the model was evaluated with the help of a confusion matrix and key performance metrics. The system performed well in the identification of Healthy leaves (99.6 % F1-score) and Common Rust (92.4 % F1-score) but was significantly poor in the identification of Northen Leaf Blight with an F1-score of only 77.4 % because of a low recall of 70.0 %. The contribution of this work is that it provides an effective and precise system that can assist farmers and other stakeholders in the agricultural sector to identify the early stages of the disease so as to reduce losses incurred in crops and improve the sustainability of agriculture.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Industrial Vision Systems and Defect Detection

Publication details

Journal / source
International Conference on Cognitive Systems and Computer Interaction (ICoSCI)
Pages
1–6
Publication date
15 January 2026
Language
EN