Medical foreign matter hyperspectral classification detection method

Abstract

The invention discloses a medical foreign matter hyperspectral classification detection method. Firstly, a medical foreign matter hyperspectral image is input; secondly, a foreign matter hyperspectral denoising method based on polynomial smoothing filtering is provided, and spectral noise interference is suppressed; secondly, a foreign matter spectral band clustering grouping PCA dimension reduction and semi-supervised LDA combined feature extraction method is proposed, firstly, band clustering grouping PCA dimension reduction is adopted to carry out dimension reduction processing on the preprocessed image, spectral features are extracted through semi-supervised LDA, then a two-dimensional Gabor filter is utilized to extract spatial features, and the features are combined to serve as classification features of the image; and finally, a support vector machine is adopted to realize medicine foreign matter detection and output foreign matter categories. According to the invention, a PCA and LDA secondary dimension reduction method is provided, so that spectral features which are more beneficial to subsequent classification operation can be extracted; and meanwhile, the semi-supervised LDA is introduced to reduce the dependence on label data, and high-accuracy detection of foreign matters under a small number of label data samples is realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for hyperspectral classification and detection of medical foreign matter. Background technique [0002] In recent years, my country's pharmaceutical market has developed rapidly, and the market size has increased from 1,220.7 billion yuan in 2015 to 1,633 billion yuan in 2019, with a compound annual growth rate of 7.5%. It is expected to further grow at a compound annual growth rate of 6.8% from 2020 to 2021 Maintain growth and reach 1,305.7 billion yuan in 2021. At the same time, medical safety, as the cornerstone of the development of the pharmaceutical industry and an important guarantee for the health of the people, has also attracted more and more attention from inside and outside the industry. In the process of pharmaceutical production, various and weak foreign objects such as glass, debris, stones, hair, and rubber crumbs often appear, which bring potent...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention proposes a hyperspectral classification detection method for medical foreign matter, which is based on band clustering and grouping PCA dimensionality reduction + semi-supervised LDA spectral feature extraction to solve the problem that the existing PCA algorithm cannot extract more separable features At the same time, the semi-supervised LDA algorithm solves the problem of relatively few label samples

Images