High-spectrum image classification method based on linear prediction cepstrum coefficient

Abstract

The invention discloses a high-spectrum image classification method based on linear prediction cepstrum coefficient, and solves the shortages in the prior that the complexity is high, real-time capability is bad, Huges phenomenon exists, prior information of a sample is needed, and wide application is difficult to realize. The method provided by the invention applies the linear prediction cepstrum coefficient in voice signal identification in spectrum data of a spectrum image and comprises the following steps: firstly, performing spectrum noise filtering on the high-spectrum data; secondly, performing pre-emphasis on the spectrum data subjected to the noise filtering for enhancing characteristics of the spectrum data; after that, utilizing Levinson-Durbin algorithm for solving a linear prediction coefficient and converting the linear prediction coefficient to the linear prediction cepstrum coefficient; and finally, matching the linear prediction cepstrum coefficient, and performing description with vector quantity included angles, wherein the smaller the included angles, the higher the similarity between classification results and standard surface configurations is. The method provided by the invention has the advantages of low complexity, high real-time capability, good classification effect and no-prior-information for the sample, and can be applied in aspects such as surface features classification and mineral identification of the high-spectrum image, etc.

Description

technical field [0001] The invention belongs to the technical field of remote sensing data processing or pattern recognition, and in particular relates to spectral data classification of hyperspectral images, which can be used for remote sensing object type identification, mineral composition identification and the like. Background technique [0002] With the advancement of remote sensing technology, hyperspectral remote sensing that can simultaneously record ground spatial distribution information and spectral information has emerged. The emergence of hyperspectral remote sensing also puts forward new requirements for hyperspectral image processing. The salient feature of hyperspectral images is that there are many imaging bands, narrow band ranges, and the bands are connected to each other, which provides a physical basis for the fine identification of ground object types. Therefore, the study of spectral classification technology suitable for hyperspectral image character...

AI Technical Summary

Problems solved by technology

However, since this method requires two matrix transformations, it has the disadvantages of high algorithm complexity and poor real-time performance.

[0007] The LDA method is a transformation method based on prior information. Because its transformation results depend on the rationality of sample selection, it is difficult to be widely used.

Images