相关实验视频

Updated: Jul 4, 2025

LeafJ: An ImageJ Plugin for Semi-automated Leaf Shape Measurement

LeafJ: An ImageJ Plugin for Semi-automated Leaf Shape Measurement

Published on: January 21, 2013

一个强大而轻量级的基于转移学习的架构,用于在多种植物中准确检测叶病,使用更少的图像数量

Md Khairul Alam Mazumder¹, M F Mridha¹, Sultan Alfarhood²

¹Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh.

Frontiers in plant science

|January 26, 2024

概括

LeafDoc-Net使用转移学习准确地检测植物叶病,即使数据有限. 这种深度学习模型通过改善疾病诊断来提高作物生产和食品保存.

科学领域:

农业科学农业科学
计算机科学计算机科学
植物病理学植物病理学

背景情况:

叶病对全球作物生产和粮食安全构成重大威胁.
准确和早期发现植物疾病对于有效的管理策略至关重要.

研究的目的:

开发一种强大而轻量级的深度学习架构,用于在多种植物物种中准确检测叶病.
为了应对有限的图像数据在植物疾病诊断中的挑战.

主要方法:

介绍了LeafDoc-Net,这是一个结合DenseNet121和MobileNetV2.2的新型转移学习架构.
增强的基本模型与注意力机制,全球平均池,和额外密集的层与swish激活和批量规范化.
评估了用Grad-CAM++进行性能分析的麻瓜和小麦叶疾病数据集的模型.

主要成果:

与现有模型相比,LeafDoc-Net在准确性,精度,回忆和AUC方面表现优异.
该模型在检测不同植物物种的叶病方面取得了很高的准确性,即使数据有限.
格拉德-CAM++为模型的决策过程提供了有价值的见解.

结论:

LeafDoc-Net提供了一种强大而高效的解决方案,用于自动诊断叶病.
开发的架构显示了改善作物监测和管理的巨大潜力,有助于食品保存.
使用增强的深度学习模型进行转移学习是有效的植物疾病检测有限的数据集.

关键词:

注意力模块的注意力模块.注意的过渡注意的过渡轻量级的建筑轻量级的建筑.多叶病是一种多叶病.多植物叶病多植物叶病植物叶病植物叶病坚固的建筑,强大的建筑.活化激活的激活方式

更多相关视频

Detection of Histone Modifications in Plant Leaves

Detection of Histone Modifications in Plant Leaves

Published on: September 23, 2011

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.