Method for converting seabed sonar image into acoustic substrate classification based on wavelet neutral network

A technology of wavelet neural network and image conversion, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as time-consuming and difficult to determine initial weights, and avoid noise and local extremum, Avoid getting stuck in locally smaller effects

Active Publication Date: 2013-05-01
SECOND INST OF OCEANOGRAPHY MNR
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the substrate classification of artificial neural network has the disadvantages of being easy to fall into local minimum, taking a long time and difficult to determine the initial weight.

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
  • Method for converting seabed sonar image into acoustic substrate classification based on wavelet neutral network
  • Method for converting seabed sonar image into acoustic substrate classification based on wavelet neutral network
  • Method for converting seabed sonar image into acoustic substrate classification based on wavelet neutral network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] like figure 1 , figure 2 As shown, the wavelet neural network-based seabed sonar image described in this embodiment is converted into an acoustic bottom class method, including the following steps:

[0033] a) Read the corrected sonar image, convert it into a grayscale image, and then normalize the image, and return the grayscale value of the grayscale image to the range of 0 to 1; matrix the image, Convert the gray value of the image to a value that can be directly calculated by arithmetic, then segment the image, divide the sonar image into several unit images and save them;

[0034] b) Calculate and save the eigenvalues ​​of the unit images based on the obtained unit images. The eigenvalues ​​include co-occurrence matrix energy, co-occurrence matrix variance, co-occurrence matrix local uniformity (homogeneity), co-occurrence matrix correlation coefficient, co-occurrence matrix contrast, and histogram Mean (first moment), histogram standard deviation, histogram sm...

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 a method for converting a seabed sonar image into an acoustic substrate classification based on a wavelet neutral network. In the method, an algorithm of a genetic wavelet neutral network is utilized to perform local analyzing; network initial parameters are optimized through a genetic algorithm, so as to avoid trapping in small local, and effectively avoiding noise and local extreme value, and the conversion between the seabed sonar image and the acoustic substrate classification is more precise and reliable, thus, the method provided by the invention has significant practical value in seabed substrate classification.

Description

technical field [0001] The invention relates to methods such as artificial neural network, wavelet analysis, genetic algorithm and principal component analysis, and is an image conversion method, especially a method for converting seabed sonar images into acoustic substrate categories based on wavelet neural network. Background technique [0002] The traditional method of seabed sediment classification is geological sampling. Although it is accurate, the work efficiency is low and the cost is high. It is impossible to classify large-scale seabed sediments. A fast and effective sediment classification method is currently needed. Seabed substrate classification methods have been developed so far, including Bayesian classification, statistical analysis, texture analysis, artificial neural network and fractal, wavelet decomposition and Fourier transform, among which artificial neural network has been a hot research topic in recent years, such as BP, SOM, LVQ and ART have carried...

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): G06K9/66G06N3/08
Inventor 熊明宽吴自银李守军尚继宏
Owner SECOND INST OF OCEANOGRAPHY MNR
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