Method for improving the classification accuracy of laser probes by using image features

Abstract

The invention belongs to the technical field of laser probe component analysis, and discloses a method for improving classification accuracy of laser probe by utilizing image characteristics. The method comprises the following steps: S1, collecting plasma spectrum of a sample by adopting a spectrum collecting device, wherein the plasma spectrum is a multi-dimensional spectrum; S2, performing imageprocessing on the plasma spectrum to obtain a 16-bit gray scale image; S3, extracting image features based on the gray image, wherein the image features are multi-dimensional spectral features; S4, training the image features as an input of a classification algorithm to obtain a classification model based on the image features; S5, inputting the image features of the sample to be classified to the classification model, and outputting the classification result by the classification model, thereby completing the classification. The invention improves the splitting precision and does not need manual or automatic route selection, simplifies the classification process and improves the classification efficiency.

Description

technical field [0001] The invention belongs to the technical field related to laser probe component analysis, and more specifically relates to a method for improving the classification accuracy of laser probes by using image features. Background technique [0002] Laser probe technology, that is, laser-induced breakdown spectroscopy (LIBS for short), is a method that uses high-energy laser irradiation to generate plasma on the surface of the sample, and then collects and analyzes the plasma spectrum through a spectrometer to determine the elemental composition of the sample. and content of an elemental analysis technique. LIBS technology has been widely used in sample identification and classification in many fields such as metal detection, traceability of agricultural products, and ore exploration due to its in-situ, rapid, and non-polluting advantages. [0003] Existing LIBS classification methods are generally based on multi-line intensity, such as multi-line peak inten...

AI Technical Summary

Problems solved by technology

On the aluminum substrate, the classification accuracy rates based on these two models are 98.9% and 89.2%, respectively, and the classification accuracy rates based on the composite substrate are 54.8% and 47.4%. Although the combination of algorithms realizes simple multi-classification of unknown samples, the classification process is still complicated, and the recognition rate for complex environments (such as multi-substrate conditions) is still low

Another example is that the patent with the announcement number CN104483292A, the announcement date is April 1, 2015, and the invention name is a method for improving the analysis accuracy of laser probes by using the multispectral ratio method discloses a method using the multispectral ratio method A method to improve the analysis accuracy of laser probes. Although this method can improve the classification accuracy of laser probes, it still cannot avoid the complicated process of line selection and the phenomenon of different classification results due to different objects or numbers of selected spectral lines.

Images