使用可见光和近红外光谱学与深度学习相结合,识别蓝中早期的伤程度
Yuping Huang1, Zhouchen Bian1, Haojun Jin2
1College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
|November 22, 2025
概括
早期发现蓝内部的伤对经济至关重要. 先进的光谱分析与CNN和TabTransformer等深度学习模型相结合,准确识别了伤程度,提高了质量评估.
科学领域:
- 农业科学 农业科学
- 食品科学 食品科学 食品科学
- 频谱学是一种光谱学.
- 机器学习 机器学习
背景情况:
- 收获后的影响会导致蓝的内部伤,严重影响其经济价值和质量.
- 早期发现这些伤对于有效的质量控制和可销售性至关重要.
研究的目的:
- 开发和评估用于早期检测蓝内部伤的光谱方法.
- 为了比较部分最小平方差异分析 (PLSDA),卷积神经网络 (CNN) 和表格变压器 (TabTransformer) 模型在识别伤严重性的性能.
主要方法:
- 一个新的光谱系统收集了蓝反射频谱 (400-1000 nm和1350-2200 nm).
- 使用PLSDA,CNN和TabTransformer模型,根据光谱数据对伤程度进行分类.
- 显微镜分析检查了伤严重程度和细胞结构变化之间的关系.
主要成果:
- 深度学习模型 (CNN和TabTransformer) 在伤检测方面表现优于PLSDA.
- 在分辨伤程度方面,CNN模型获得了最高的准确性 (96.9%),对于大多数伤程度的二进制分类,准确性超过95%.
- 在TabTransformer模型中,准确度达到91.8%.
- 在1350-2200纳米范围内,较低的精度归因于受细胞破坏影响的吸水带.
结论:
- 开发的光学系统与深度学习模型相结合,显示了识别蓝伤程度的巨大潜力.
- CNN和TabTransformer模型为蓝中早期伤检测提供了一个有希望的非破坏性方法.
- 进一步的研究可能会优化光谱范围和模型参数,以提高准确性.
更多相关视频
11:37RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
16.9K
06:50O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
Published on: November 8, 2019
7.0K
相关概念视频
01:02Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview
4.4K
Ultraviolet–visible (UV–visible or UV–Vis) spectroscopy is an analytical technique that investigates the interaction between matter and UV–Vis light within the electromagnetic spectrum. This method is widely used for its versatility, simplicity, and relatively quick data acquisition, making it valuable for both qualitative and quantitative analysis. When UV–Vis radiation passes through a material, molecules absorb light depending on the energy required for...
4.4K
02:16Light Acquisition
9.3K
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.
9.3K