Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image classification method based on three-side filter and stacked sparse autocoder

A technology of sparse autoencoder and classification method, applied in instrument, character and pattern recognition, computational model, etc., can solve problems such as inability to effectively extract high-order features of spectral data

Active Publication Date: 2017-03-15
HARBIN ENG UNIV
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these classifiers cannot effectively extract high-order features of spectral data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image classification method based on three-side filter and stacked sparse autocoder
  • Image classification method based on three-side filter and stacked sparse autocoder
  • Image classification method based on three-side filter and stacked sparse autocoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The following examples describe the present invention in more detail.

[0075] First, smooth hyperspectral images are obtained using a trilateral filter before performing hyperspectral image classification. Extract the spectral-spatial features of pixels while filtering out Gaussian, speckle and impulse noise of degraded images.

[0076] Second, a modified stacked sparse autoencoder (SSA) is used for high-order feature extraction.

[0077] Finally, a random forest classifier is used for supervised fine-tuning of the network and classification.

[0078] The classification method of the joint trilateral filter and stack sparse autoencoder proposed by the present invention is not only suitable for classifying hyperspectral images, but also can classify other images. It has strong portability and is easier to meet the needs of image classification.

[0079] The present invention specifically includes:

[0080] 1. The present invention proposes to use a trilateral filter...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an image classification method based on a three-side filter and a stacked sparse autocoder. The method comprises: a smooth image is obtained by using a three-side filter, and Gaussian, speckle, pulse noises of a degraded image are filtered while a spectral-spatial feature of a pixel of the image is extracted; high-order feature extraction is carried out by using an improved stacked sparse autocoder; and supervised network fine tuning and classification are carried out by using a random forest classifier. According to the method provided by the invention, the improved stacked sparse autocoder and the random forest classifier are introduced into the hyperspectral data classification to form depth learning architecture; the improved stacked sparse autocoder can extract abstract and useful underlying features of spectroscopic data layer by layer, thereby improving the classification performance of the spectroscopic data. The method is not only suitable for hyperspectral image classification but also suitable for other image classification and has high transportability; and the image classification demand can be satisfied easily.

Description

technical field [0001] The invention relates to an image classification method, in particular to a hyperspectral image classification method combining trilateral filter and deep learning theory. Background technique [0002] Hyperspectral remote sensing uses many narrow electromagnetic bands to obtain image data from objects of interest. Generally, tens to hundreds of continuous bands are set from visible light to thermal infrared bands, and its spectral resolution can be as high as nanometers. For each recorded pixel, the rich spectral information can provide a complete spectral description and characteristics of the observed surface, so it can be regarded as an effective tool in material discrimination. At present, hyperspectral imaging has become an important means of remote sensing imaging detection, and its essence is that it can provide both spatial information of ground object distribution and spectral information of higher resolution. Although hyperspectral image da...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06K9/46G06N3/00G06K9/00
CPCG06N3/006G06V20/194G06V20/13G06V10/58G06V10/40G06F18/2136G06F18/2415
Inventor 赵春晖万晓青闫奕名赵艮平黄湘松
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products