Edge detection method based on long-short-term synaptic complementary neural network
A neuron network and edge detection technology, applied in the field of visual neural computing, can solve problems such as noise interference, ignoring pre-correlation, ignoring synaptic dynamic adjustment, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0061] Attached figure 1 , The specific implementation steps of the present invention are:
[0062] Step (1) Construct a neuron network with synaptic complementary characteristics of long and short duration, the size of which is the same as that of the image to be tested map(i,j), i=1, 2,...,M; j=1, 2,...,N , Where M and N respectively represent the length and width of the image to be tested; the neuron network includes color antagonistic weighted coding, discharge time coding, long and short duration synaptic complementary coding, and normalization layer modules;
[0063] Step (2) Considering that different color antagonistic channels have different influences on the edge detection results, the color antagonistic weighted coding module is constructed, and the color antagonistic influence factor is defined, and the weighted coding is obtained by weighting the responses of different color antagonizing channels Respond to S_result(i,j); the specific implementation process is as fol...
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