摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-目前的研究结果已经发表。根据NewsRx记者在杜阿拉大学的新闻报道，research说：“玉米-植物检疫状况的早期诊断对于防止作物损害和优化产量至关重要。”我们的新闻记者从杜阿拉大学的研究中获得了一句话：“然而，由于野外环境的背景变化，这种野外诊断提出了一个挑战，这可能会阻碍分类算法的性能。”本文介绍了一种新的分割技术，使用组合归一化差异植被指数，有效地分离出感兴趣的特征，如树叶，为了评估分割方法的有效性，我们利用监督分类算法对玉米植株进行了早期诊断，生成了一个包含能量、熵、对比度和逆四个基本纹理特征的数据集，并利用灰度共生矩阵从每个分割图像中提取这些特征。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on have been published. Acc ording to news reporting from the University of Douala by NewsRx journalists, re search stated, "Early diagnosis of maize-plant phytosanitary state in the field is crucial to prevent crop damage and optimize yield." Our news correspondents obtained a quote from the research from University of Do uala: "However, this field diagnosis presents a challenge due to the variable ba ckground of the field environment, which can hinder the performance of classific ation algorithms. In this article, we introduced a novel segmentation technique using a combined normalized difference vegetation index that effectively isolate s the features of interest, such as the leaves, from the surrounding image, whic h includes the diverse field background. To assess the effectiveness of our segm entation approach, we conducted early diagnosis of maize plants in the field usi ng supervised classification algorithms. We generated a dataset that incorporate d four essential texture features: energy, entropy, contrast, and inverse. These features were extracted from each of the segmented images using grayscale co-oc currence matrices."
NETL
NSTL