Machine Learning in the Classification of RGB Images of Maize (Zea mays L.) Using Texture Attributes and Different Doses of Nitrogen
Authors:
- Thiago Lima da SilvaTSThiago Lima da Silva
- Fernanda de Fátima da Silva DevechioFDFernanda de Fátima da Silva Devechio
- Marcos Silva TavaresMTMarcos Silva Tavares
- Jamile Raquel RegazzoJRJamile Raquel Regazzo
- Edson José de Souza SardinhaESEdson José de Souza Sardinha
- Liliane Maria Romualdo AltãoLALiliane Maria Romualdo Altão
- Gabriel PaginGPGabriel Pagin
- Adriano Rogério Bruno TechATAdriano Rogério Bruno Tech
- Murilo Mesquita BaessoMBMurilo Mesquita Baesso
Open Access
- 23 September 2025
- journal article
- research article
- Published by MDPI AG in Agriengineering
- Vol. 7 (10) , 317
Abstract
Nitrogen fertilization is decisive for maize productivity, fertilizer use efficiency, and sustainability, which calls for fast and nondestructive nutritional diagnosis. This study evaluated the classification of maize plant nutritional status from red, green, and blue (RGB) leaf images using texture attributes. A greenhouse experiment was conducted under a completely randomized factorial design with four nitrogen doses, one maize hybrid Pioneer 30F35, and four replicates, at two sampling times corresponding to distinct phenological stages, totaling thirty-two experimental units. Images were processed with the gray-level cooccurrence matrix computed at three distances 1, 3, and 5 pixels and four orientations 0°, 45°, 90°, and 135°, yielding eight texture descriptors that served as inputs to five supervised classifiers: an artificial neural network, a support vector machine, k nearest neighbors, a decision tree, and Naive Bayes. The results indicated that texture descriptors discriminated nitrogen doses with good performance and moderate computational cost, and that homogeneity, dissimilarity, and contrast were the most informative attributes. The artificial neural network showed the most stable performance at both stages, followed by the support vector machine and k nearest neighbors, whereas the decision tree and Naive Bayes were less suitable. Confusion matrices and receiver operating characteristic curves indicated greater separability for omission and excess classes, with D1 standing out, and the patterns were consistent with the chemical analysis. Future work should include field validation, multiple seasons and genotypes, integration with spectral indices and multisensor data, application of model explainability techniques, and assessment of latency and scalability in operational scenarios.Keywords
This publication has 47 references indexed in Scilit:
- Precision monitoring of rice nitrogen fertilizer levels based on machine learning and UAV multispectral imageryComputers and Electronics in Agriculture, 2025
- A novel ensemble learning method using majority based voting of multiple selective decision treesComputing, 2024
- Auxin synthesis promotes N metabolism and optimizes root structure enhancing N acquirement in maize (Zea mays L.)Planta, 2024
- Enhancing tomato leaf nitrogen analysis through portable NIR spectrometers combined with machine learning and chemometricsChemometrics and Intelligent Laboratory Systems, 2023
- A spectral decomposition method for estimating the leaf nitrogen status of maize by UAV-based hyperspectral imagingComputers and Electronics in Agriculture, 2023
- Expression levels of nitrogen assimilation-related genes, physiological responses, and morphological adaptations of three indica rice (Oryza sativa L. ssp. indica) genotypes subjected to nitrogen starvation conditionsProtoplasma, 2022
- Improved Naive Bayes with optimal correlation factor for text classificationSN Applied Sciences, 2019
- Recognition of Chinese food using convolutional neural networkMultimedia Tools and Applications, 2018
- Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imageryPrecision Agriculture, 2018
- Texture analysis of medical imagesClinical Radiology, 2004