Al-Shamasneh Ala'a R
Department of Computer Science, College of Computer & Information Sciences, Prince Sultan University, Rafha Street, Riyadh 11586, Saudi Arabia.
MethodsX. 2025 Jun 6;14:103421. doi: 10.1016/j.mex.2025.103421. eCollection 2025 Jun.
The detection of plant diseases in the modern era offers a promising first step toward sustainable agriculture and food security. Plant physiology can be studied quantitatively thanks to advances in imaging and computer vision. Conversely, manual interpretation requires a great deal of labor, knowledge of plant diseases. Numerous innovative methods for identifying and classifying particular diseases have been widely used. In order to diagnose potato diseases more accurately and quickly using a machine learning model, this study uses a new feature extraction method based on GJPs image features. The methodology of this study relies on:•Modules for preprocessing, feature extraction, dimension reduction, and classification.•Generalized jones polynomials as new image features method is used to extract the texture features from potato images for diagnosing potato diseases. The data used in this model were collected from the plant village image dataset using samples of potato leaves. Using an SVM classifier on potato leaf images, the disease was accurately identified in 98.45 % of cases. The recommended feature extraction technique can reduce financial loss while also assisting in the efficient management of plant diseases, enhancing crop productivity and ensuring food security.
现代植物病害检测为可持续农业和粮食安全迈出了充满希望的第一步。得益于成像和计算机视觉技术的进步，植物生理学可以进行定量研究。相反，人工解读需要大量劳动力以及植物病害知识。众多用于识别和分类特定病害的创新方法已被广泛使用。为了使用机器学习模型更准确、快速地诊断马铃薯病害，本研究采用了一种基于GJPs图像特征的新特征提取方法。本研究的方法依赖于：•预处理、特征提取、降维和分类模块。•使用广义琼斯多项式作为新的图像特征方法从马铃薯图像中提取纹理特征以诊断马铃薯病害。该模型使用的数据是从植物村图像数据集中采集的马铃薯叶片样本。在马铃薯叶片图像上使用支持向量机分类器，在98.45%的病例中准确识别出病害。推荐的特征提取技术可以减少经济损失，同时有助于植物病害的有效管理，提高作物产量并确保粮食安全。
