Hyperspectral pattern classification and identification method, device and equipment for medicinal material origin grades

Abstract

The invention relates to a hyperspectral pattern classification and identification method, device and equipment for medicinal material origin grades. The method comprises the steps of obtaining hyperspectral graphic data of a to-be-identified medicinal material; preprocessing the hyperspectral graphic data to obtain a training sample and a test sample; processing the training sample and the test sample by using a least square regression algorithm to obtain a training projection sample and a test projection sample; classifying the training projection samples and the test projection samples based on a collaborative representation method of Kilov regularization to obtain test sample class labels; and calculating the classification precision according to the test sample class label in combination with the ground object real label map corresponding to the to-be-identified medicinal material. According to the method, the least square regression algorithm and the collaborative representationmethod based on the Gilonov regularization are adopted, so that the feature extraction precision and the classification precision are improved, and the classification and recognition efficiency and precision of the medicinal material origin grades are improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, device and equipment for classification and recognition of hyperspectral graphics at the origin level of medicinal materials. Background technique [0002] At present, there have been a lot of research results in the field of medicinal botany on the origin, quality and yield estimation of Chinese medicinal materials. However, due to the variety of medicinal plants and the large differences in structure and composition between different species, In production practice, non-artificial identification technology methods with excellent effects and easy implementation are still in the process of continuous exploration and development. In the traditional origin identification, two commonly used technologies are mineral element analysis and isotope fingerprinting technology, both of which require the use of stoichiometric methods in the identification process, although...

AI Technical Summary

Problems solved by technology

In the traditional origin identification, two commonly used technologies are mineral element analysis and isotope fingerprinting technology, both of which require the use of stoichiometric methods in the identification process, although they have high accuracy and sensitivity, but the cost In addition, near-infrared spectroscopy is a rapid, non-destructive and widely used identification technology developed in recent years, but its identification results are easily affected by the sample state and environmental conditions, and its sensitivity is low

Images