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

High spectral image classification method based on morphological characteristics and dictionary learning

A hyperspectral image and morphological feature technology, applied in the field of hyperspectral image classification, can solve the problems of few samples and high dimensionality

Inactive Publication Date: 2016-12-07
NANJING UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the characteristics of high dimensionality and few samples of hyperspectral images, traditional hyperspectral image classification methods only consider the spectral characteristics and ignore the spatial characteristics of images, and there is a natural "interference" between digital storage of images and human semantic understanding. Semantic gap" problem, efficient and reliable hyperspectral image classification is still full of challenges

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
  • High spectral image classification method based on morphological characteristics and dictionary learning
  • High spectral image classification method based on morphological characteristics and dictionary learning
  • High spectral image classification method based on morphological characteristics and dictionary learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] This embodiment includes the following parts:

[0076] 1. Extract the underlying features of the hyperspectral image:

[0077] Firstly, the hyperspectral image I is analyzed by kernel principal component analysis method, and the first d principal components are extracted to obtain d images with principal components as data [I 1 ,...,I d ]. Among them, d is preferably 13 in the present invention.

[0078] For each component image I i ,i=1,2,...d, define n types of sliding windows, called structural elements, where n is preferred in the present invention. Calculate the morphological profile MP(I i ):

[0079]

[0080] in is the feature of the open morphological section, and the open morphological section is obtained by using the opening operation on the same component image by using structural elements of different sizes, It is the opening operation, where R refers to the real number field, which is the result of a series of expansion operations followed by c...

Embodiment 2

[0101] figure 2 It is the image truth table sourced from the Indian Pines dataset. The vertical and horizontal coordinates are the pixels in the physical space corresponding to the hyperspectral image. Each pixel represents about 20 square meters of real geographic space. image 3 For the classification effect diagram of the method of the present invention on Indian Pines, compared with the truth table, it can be seen that the classification results of the method of the present invention are correct in most of the pixels, and only a small number of pixels will have classification errors. (Since the attached drawings are all grayscale images, figure 2 and image 3 ) Figure 4 It is the classification accuracy rate obtained on the Indian Pines data using different parameters l, where the ordinate is the classification accuracy rate, and the abscissa is the number of values ​​of l in the invention. It can be seen that as l increases, the classification accuracy rate also inc...

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 discloses a high spectral image classification method based on morphological characteristics and dictionary learning. The method comprises the following steps of extracting morphological characteristics from high spectral images, a process of dictionary learning, coding the characteristics, and classifying the images. The method is applied to the field of high spectral image classification, the structural relation of space information in the high spectral images is taken into full consideration, high-level semantic mapping is constructed on the basis of the space relation information, high-level semantic codes which can maintain the structure information of the characteristic space effectively are obtained and used for a high spectral image classification task, and the problem that semantic gaps exist between the high level meanings and bottom characteristics of the high spectral images is overcome. The method has substantial effect in high spectral image classification, and has higher application values.

Description

technical field [0001] The invention belongs to the field of image classification, in particular to a hyperspectral image classification method based on morphological features and dictionary learning. Background technique [0002] With the development of remote sensing technology and computer technology, hyperspectral remote sensing images have penetrated into various fields of society and economy. At the same time, the number of hyperspectral images is also increasing day by day. How to organize images and classify hyperspectral images has become an important research topic in the field of remote sensing information technology. Due to the characteristics of high dimensionality and few samples of hyperspectral images, traditional hyperspectral image classification methods only consider the spectral characteristics and ignore the spatial characteristics of images, and there is a natural "interference" between digital storage of images and human semantic understanding. Semant...

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
IPC IPC(8): G06K9/62
CPCG06F18/214G06F18/2411
Inventor 杨育彬王喆正
Owner NANJING 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com