Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models
Maize (Zea mays) is a crucial global staple crop that serves as a primary source of food and income, especially for smallholder farmers. However, it is susceptible to diseases that drastically reduce yields if not controlled. Traditional methods of disease detection of visual inspections are often i...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525004575 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849765545434415104 |
|---|---|
| author | Basani Lammy Nkuna Khaled Abutaleb Johannes George Chirima Solomon W. Newete Adriaan Johannes van der Walt Adolph Nyamugama |
| author_facet | Basani Lammy Nkuna Khaled Abutaleb Johannes George Chirima Solomon W. Newete Adriaan Johannes van der Walt Adolph Nyamugama |
| author_sort | Basani Lammy Nkuna |
| collection | DOAJ |
| description | Maize (Zea mays) is a crucial global staple crop that serves as a primary source of food and income, especially for smallholder farmers. However, it is susceptible to diseases that drastically reduce yields if not controlled. Traditional methods of disease detection of visual inspections are often inaccurate and uncertain. Recent advances in computer vision and deep learning techniques have shown promise in improving image recognition for crop disease detection. This study aims to develop models for detecting maize leaf diseases at the subfieldlevel using red, green, and blue (RGB)-based images using convolutional neural network (CNN) and residual network (ResNet50) models. A dataset of 1500 maize leaf images representing seven categories of maize disease symptoms was collected from the maize fields in Mopani District, Limpopo, South Africa. The data were processed to train and compare two deep learning models, CNNs and ResNet50. Both models demonstrated good classification accuracy with ResNet50 outperforming CNN, achieving an accuracy of 78.76% compared to 71.01% for CNN. The findings underscore ResNet50 enhanced capability to classify maize leaf diseases more accurately than CNN, attributed to its deeper architecture. This study illustrates the potential for deploying deep learning model in detecting maize leaf diseases. This study supports the transformative potential of deep learning in advancing agricultural practices, serving as a vital tool for early disease detection and contributing to food security in maize-producing regions, particularly smallholder farming systems. Therefore, this study trains the models that can be included in the mobile applications to be used to detected diseases in a sub-field level of the smallholder farms. |
| format | Article |
| id | doaj-art-2dc3a6e0d99c4bc68167acf95f851908 |
| institution | DOAJ |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-2dc3a6e0d99c4bc68167acf95f8519082025-08-20T03:04:49ZengElsevierSmart Agricultural Technology2772-37552025-12-011210122610.1016/j.atech.2025.101226Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) modelsBasani Lammy Nkuna0Khaled Abutaleb1Johannes George Chirima2Solomon W. Newete3Adriaan Johannes van der Walt4Adolph Nyamugama5University of Free State (UFS) - Faculty of Agricultural Sciences, Department of Geography, Bloemfontein, 9300, South Africa; Agricultural Research Council - Natural Resources and Engineering (ARC-NRE), Geoinformation Science division, Arcadia, Private Bag X79, Pretoria, 0001, South Africa; Corresponding author at: Agricultural Research Council - Natural Resources and Engineering (ARC-NRE), Geoinformation Science division, Arcadia, Private Bag X79, Pretoria, 0001, South Africa.Agricultural Research Council - Natural Resources and Engineering (ARC-NRE), Geoinformation Science division, Arcadia, Private Bag X79, Pretoria, 0001, South Africa; School of Animal, Plant and Environmental Sciences, University of Witwatersrand, Private Bag X3, Johannesburg, 2050, South Africa; National Authority for Remote Sensing and Space Sciences (NARSS), Cairo, EgyptAgricultural Research Council - Natural Resources and Engineering (ARC-NRE), Geoinformation Science division, Arcadia, Private Bag X79, Pretoria, 0001, South Africa; Centre for Geoinformation Science, Department of Geography, Geoinformatics, and Meteorology, University of Pretoria, Pretoria, 0001, South AfricaUniversity of Free State (UFS) - Faculty of Agricultural Sciences, Department of Geography, Bloemfontein, 9300, South Africa; School of Animal, Plant and Environmental Sciences, University of Witwatersrand, Private Bag X3, Johannesburg, 2050, South AfricaUniversity of Free State (UFS) - Faculty of Agricultural Sciences, Department of Geography, Bloemfontein, 9300, South AfricaAgricultural Research Council - Natural Resources and Engineering (ARC-NRE), Geoinformation Science division, Arcadia, Private Bag X79, Pretoria, 0001, South AfricaMaize (Zea mays) is a crucial global staple crop that serves as a primary source of food and income, especially for smallholder farmers. However, it is susceptible to diseases that drastically reduce yields if not controlled. Traditional methods of disease detection of visual inspections are often inaccurate and uncertain. Recent advances in computer vision and deep learning techniques have shown promise in improving image recognition for crop disease detection. This study aims to develop models for detecting maize leaf diseases at the subfieldlevel using red, green, and blue (RGB)-based images using convolutional neural network (CNN) and residual network (ResNet50) models. A dataset of 1500 maize leaf images representing seven categories of maize disease symptoms was collected from the maize fields in Mopani District, Limpopo, South Africa. The data were processed to train and compare two deep learning models, CNNs and ResNet50. Both models demonstrated good classification accuracy with ResNet50 outperforming CNN, achieving an accuracy of 78.76% compared to 71.01% for CNN. The findings underscore ResNet50 enhanced capability to classify maize leaf diseases more accurately than CNN, attributed to its deeper architecture. This study illustrates the potential for deploying deep learning model in detecting maize leaf diseases. This study supports the transformative potential of deep learning in advancing agricultural practices, serving as a vital tool for early disease detection and contributing to food security in maize-producing regions, particularly smallholder farming systems. Therefore, this study trains the models that can be included in the mobile applications to be used to detected diseases in a sub-field level of the smallholder farms.http://www.sciencedirect.com/science/article/pii/S2772375525004575Data augmentationImage processingPrecision agricultureHyperspectral |
| spellingShingle | Basani Lammy Nkuna Khaled Abutaleb Johannes George Chirima Solomon W. Newete Adriaan Johannes van der Walt Adolph Nyamugama Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models Smart Agricultural Technology Data augmentation Image processing Precision agriculture Hyperspectral |
| title | Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models |
| title_full | Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models |
| title_fullStr | Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models |
| title_full_unstemmed | Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models |
| title_short | Identification of maize leaf diseases using red, green, blue-based images with convolutional neural network (CNN) and residual network (ResNet50) models |
| title_sort | identification of maize leaf diseases using red green blue based images with convolutional neural network cnn and residual network resnet50 models |
| topic | Data augmentation Image processing Precision agriculture Hyperspectral |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525004575 |
| work_keys_str_mv | AT basanilammynkuna identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models AT khaledabutaleb identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models AT johannesgeorgechirima identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models AT solomonwnewete identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models AT adriaanjohannesvanderwalt identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models AT adolphnyamugama identificationofmaizeleafdiseasesusingredgreenbluebasedimageswithconvolutionalneuralnetworkcnnandresidualnetworkresnet50models |