Hyperspectral image classification method based on linear regression Fisher discrimination dictionary learning (LRFDDL)

A hyperspectral image, linear regression technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of dimensionality disaster data uncertainty and so on

CN103971123AActive Publication Date: 2014-08-06南京词酷网络信息技术有限公司
3 Cites 29 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2014-08-06

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a hyperspectral image classification method based on linear regression Fisher discrimination dictionary learning (LRFDDL). The method includes the following steps that the textural features and the spectral features of each hyperspectral image are fused and normalized; a dictionary and a linear classifier are obtained by learning through an LRFDDL algorithm; model prediction is conducted. According to the hyperspectral image classification method based on LRFDDL, the LRFDDL algorithm is applied to hyperspectral image classification, so that the classification accuracy of the hyperspectral images is improved; in addition, the textural features of the hyperspectral images are added into the classification, and thus the classification effect of the hyperspectral images is further improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of hyperspectral image processing, in particular to a hyperspectral image classification method based on linear regression and Fisher discriminant dictionary learning. Background technique

[0002] Hyperspectral remote sensing image (Hyperspectral Image, HSI) usually refers to the spectral resolution in 10 -2 A set of spectral images within the magnitude range of λ (where λ represents wavelength), generally includes dozens or even hundreds of spectral bands. In the ultraviolet to mid-infrared light region, the hyperspectral sensor uses electromagnetic waves with continuous wavelengths and equal intervals to image the target area and obtain spectral information and corresponding spatial information of ground targets. The key point that hyperspectral remote sensing images are different from traditional multispectral images is that they have more narrow-band imaging, which provides richer ground object information, espe...

Examples

Embodiment Construction

[0052] Such as figure 1As shown, the present invention discloses a method for classifying hyperspectral images based on linear regression and Fisher discriminant dictionary learning, including the following steps:

[0053] Step 1, fusion of texture features and spectral features, and normalization processing: firstly use PCA to linearly transform the hyperspectral image and obtain the first principal component, then use Gabor wavelet transform to extract the texture features of the first principal component, and finally fuse the high The texture features and spectral features of the spectral image, and unitize the feature vector of each pixel;

[0054] Step 2, use LRFDDL to learn the dictionary and classifier: update the dictionary, sparse coding and classifier iteratively, until the iteration termination condition is met and output the learned dictionary and classifier;

[0055] Step 3, model prediction: use the learned dictionary to obtain the sparse coding of the pixels to...