相关实验视频
Updated: Jun 20, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.0K
一种新的方法,将深度学习与肯纳德-斯通算法相结合,用于训练数据集选择以图像为基础的米种子品种识别
Chen Jin1, Xinyue Zhou1, Mengyu He1
1School of Information Engineering, Huzhou University, Huzhou, China.
Journal of the science of food and agriculture
|July 20, 2024
概括
这项研究引入了一种使用深度学习和肯纳德-斯通算法选择培训样本的新方法,将大米品种分类准确度提高了10%以上. 这种方法提高了图像分辨率,即使在有噪音数据的情况下也保持了性能.
科学领域:
- 农业科学 农业科学
- 计算机科学 计算机科学
- 数据科学数据科学数据科学
背景情况:
- 鉴定米品种是非常重要的,因为增加了繁殖和多样化的特点.
- 准确的识别影响贸易和农业实践.
- 先进的育种技术需要有效的识别方法.
研究的目的:
- 开发一种改进的米品种分类方法.
- 为了提高图像分辨率,以获得更好的分类准确性.
- 引入一种新的培训样本选择策略.
主要方法:
- 收集了20种混合大米种子品种的RGB图像.
- 使用增强的深度超分辨率网络 (EDSR) 进行图像增强.
- 集成深度学习 (CNN,自动编码器) 与肯纳德-斯通 (KS) 算法用于训练样本选择.
主要成果:
- 高分辨率图像提高了品种分类性能.
- 新的培训样本选择方法在准确度上超过了随机选择约10.08%.
- 提出的方法证明了对图像噪声的稳定性.
结论:
- 监督和无监督学习模型是有效的特征提取器.
- 深度学习显著影响训练集的样本选择进行分类.
- 这项研究提出了一种用于各种数据集的培训样本选择的新方法.
相关概念视频
02:16Light 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
01:59Plant Breeding and Biotechnology
18.9K
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
18.9K