Hyperspectral image classification-oriented data adaptive activation function learning method

A hyperspectral image and activation function technology, which is applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of poor accuracy and achieve the effect of improving accuracy

Active Publication Date: 2019-11-12
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiency of the poor accuracy rate of existing hyperspectral image classification methods, the present invention provides a data adaptive activation function learning method for hyperspectral image classification

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
  • Hyperspectral image classification-oriented data adaptive activation function learning method
  • Hyperspectral image classification-oriented data adaptive activation function learning method
  • Hyperspectral image classification-oriented data adaptive activation function learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] CNN is a non-linear classifier with good performance, including convolutional layers, fully connected layers and activation functions. The optimization of the activation function greatly improves the computational performance of the model. Commonly used activation functions include functions such as Sigmoid, Tanh, and ReLU, among which ReLU has been widely used in various artificial neural networks due to its high performance in actual computing.

[0032] The above activation function works for any data (w represents the width of the image, h represents the height of the image, and ch represents the number of channels of the image), so the ReLU activation function can be expressed by the following formula:

[0033]

[0034] Formula (9) can also be expressed as:

[0035]

[0036] in The operation represents element multiplication, and I(X) is an indicator function used to indicate the dependence of variable X on the set, indicating that the mapping of the activ...

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 hyperspectral image classification-oriented data adaptive activation function learning method, which is used for solving the technical problem of poor accuracy of an existinghyperspectral image classification method. According to the technical scheme, spectral information and spatial information of hyperspectral data are utilized, and hyperspectral image classification is carried out by learning an activation function based on specific data. By analyzing a common activation function, it is found that the activation function can be represented in the mode that activation mapping is multiplied by input features. Therefore, activation mapping is learned by constructing a two-layer neural network. The neural network learns from two aspects of channels and spectrums,and activation functions conforming to the characteristics of the channels and the spectrums are constructed respectively, so that the image classification accuracy is improved. Tests show that on anIndian Pines data set, the classification accuracy of the activation function based on the channel and the spectrum is averagely improved by 2.17% and 4.03% respectively.

Description

technical field [0001] The invention relates to a hyperspectral image classification method, in particular to a data adaptive activation function learning method for hyperspectral image classification. Background technique [0002] Hyperspectral image (Hyperspectral Image, HSI) contains both detailed spatial information and rich spectral information, and is widely used in remote sensing fields such as terrain classification, environmental detection and geological survey. Hyperspectral image classification is an important task in hyperspectral image analysis. The purpose is to assign a defined label to each pixel, which can be simply divided into traditional machine learning methods and deep learning methods. Traditional machine learning methods include Support Vector Machine (SVM), Multinomial Logistic Regression (MLR), etc. Although these methods are simple and effective, their shallow structure prevents them from learning enough in challenging situations. useful features....

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/24G06F18/214
Inventor 魏巍李宇张锦阳王聪张艳宁
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap