艾尔格网 (AELGNet):以关注为基础的增强局部和全球特征网络,用于药用叶子和植物的分类
Shubham Sharma1, Manu Vardhan1
1Department of Computer Science and Engineering, National Institute of Technology, Raipur, Chhattisgarh 492010, India.
Computers in biology and medicine
|November 28, 2024
概括
本研究引入了一种先进的深度学习模型,即基于注意力的增强局部和全球特征网络 (AELGNet),用于准确的药用植物分类. AELGNet的准确度超过99%,显著优于现有的草药识别方法.
科学领域:
- 植物学和药物识别学
- 计算机科学和人工智能 人工智能
- 生物技术是生物技术.
背景情况:
- 药用植物为传统药物提供了具有成本效益和更安全的替代品,推动了制药业的兴趣.
- 药用植物的准确分类对于传统医学,制药安全和生物多样性保护至关重要.
- 手动分类效率低,易出错,需要自动化解决方案来识别治疗植物.
研究的目的:
- 开发一种可通用的深度学习方法,以使用组合植物和叶子图像进行有效的药用植物分类.
- 引入基于注意力的增强局部和全球特征网络 (AELGNet),以提高特征提取和分类准确性.
- 在印度药用植物的数据集上验证AELGNet的疗效.
主要方法:
- 图像预处理使用对比度有限的自适应直方体平衡 (CLAHE) 来增强功能.
- 开发基于注意力的增强局部和全球特征网络 (AELGNet),结合MBConv模块.
- 从图像补丁中提取本地特征,从基本特征中提取全球特征,通过剩余的通道智能和空间注意力来增强.
主要成果:
- AELGNet实现了高性能指标:准确率为99.71%,精度为99.80%,回忆率为99.75%,F1得分为99.77%.
- 拟议的AELGNet比现有的14种方法的准确率高出2%至10%.
- 该模型显示了强大的可通用性,用于对药用植物及其叶子进行分类.
结论:
- 艾尔格网为准确和快速识别药用植物和叶子提供了强大而高效的工具.
- 这些发现支持AELGNet在医疗和工业环境中用于草药识别的应用.
- 这种自动化方法提高了草药治疗的可靠性,并有助于生物多样性保护工作.
相关概念视频
Light Acquisition
8.4K
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.
8.4K
Key Elements for Plant Nutrition
18.7K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.7K


