Rosewood discriminating method and system based on hyperspectral data

Abstract

The invention proposes a rosewood discriminating method based on hyperspectral data, and the method comprises the following steps: obtaining a training sample and a testing sample, wherein the type is known; classifying the spectral data of all n dimensions according to the training sample, and extracting spectral data with the maximum classification accuracy in m dimensions, wherein m is less than n; obtaining a characteristic point set S with the dimension n, wherein the characteristic point in the set S will serve as a characteristic selection waveband for the later classification, thereby replacing a later classification algorithm; classifying the spectral data of m dimensions according to a K-nearest neighbor classification algorithm, so as to determine the type of rosewood. The method can improve the classification accuracy of data, and reduces the processing time of a data classification algorithm. The invention also provides a rosewood discriminating system based on the hyperspectral data.

Description

technical field [0001] The invention relates to the technical field of hyperspectral data processing, in particular to a method and system for identifying mahogany based on hyperspectral data. Background technique [0002] Hyperspectral imaging technology can obtain more information than traditional imaging technology, and use this information to complete problems that traditional imaging data cannot handle. Most current imaging photography technologies record scene images based on red, green, and blue three-color information. Although three-color sensing imaging technology meets the imaging requirements of the human visual system, from the perspective of physical principles, real scenes are not Only three-color information is so simple. The light emitted from a light source or reflected by an object has abundant wavelengths, among which visible light covers a wide area from 390nm to 780nm, and contains a large amount of information. Scene light spectrum refers to the dist...

AI Technical Summary

Problems solved by technology

[0004] However, there is a large amount of data redundancy in hyperspectral data. Direct data processing and classification of raw spectral data will result in insufficient processing speed. Therefore, it is necessary to perform some preprocessing on the data before classifying and analyzing the data. of

However, traditional data mining and data dimensionality reduction (such as PCA, LDP) methods mostly use the feature matrix to perform feature transformation on the original data. Fundamentally speaking, they also operate on the original data. There is no obvious one-to-one comparison between the transformed matrix and the original data

Therefore, the classification accuracy of current classification methods is low

Images