研究目的
Identifying a suitable distance function for hyperspectral images to maintain the accuracy of hyperspectral image processing results.
研究成果
The most suitable distance function for hyperspectral data, one that is a metric and responds proportionally without saturating in both cases of translation and magnitude change, is Euclidean distance of cumulative spectrum (ECS).
研究不足
The study identifies that many distance functions saturate or fail to proportionally reflect input parameter evolution, especially in the presence of noise or variations in real spectral data.
1：Experimental Design and Method Selection:
The study compares existing distance functions and defines a set of selection criteria for evaluating their suitability for hyperspectral images. Theoretical constraints and behavior, as well as numerical tests, are proposed for the evaluation.
2：Sample Selection and Data Sources:
Simulated spectral reflectance signals using Gaussian distribution functions and real hyperspectral images of pigment patches are used for evaluation.
3：List of Experimental Equipment and Materials:
Not explicitly mentioned in the abstract.
4：Experimental Procedures and Operational Workflow:
The study involves theoretical evaluation with simulated spectra and numerical evaluation using real spectra of known properties.
5：Data Analysis Methods:
The performance of distance functions is evaluated based on their theoretical properties and numerical tests on real spectral data.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
