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 the problems of difficult initial weight determination and long time consumption, and avoid noise and local extremum, Avoid getting stuck in locally smaller effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] Such as 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 the energy of the co-occurrence matrix, the variance of the co-occurrence matrix, the local uniformity (homogeneity) of the co-occurrence matrix, the correlation coefficient of the co-occurrence matrix, the contrast of the co-occurrence matrix, and histogram Mean ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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