A Contour Detection Method Based on Computational Model of Primary Visual Pathway
A computing model and contour detection technology, applied to biological neural network models, measuring devices, instruments, etc., can solve the problems of effectively expressing unfavorable image contours and ignoring information correlation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0033] Step (1) extracts primary contour responses for multi-scale feature fusion. Considering the requirement of multi-directional boundary information extraction, the present invention introduces a two-dimensional Gaussian derivative function shown in formula (9) to simulate the classical receptive field characteristics of retinal ganglion cells.
[0034]
[0035] Among them, (x, y) represents the coordinates of the pixel position, θ represents the orientation angle, and its value range is θ∈[0, π). The mean square error σ and the spatial size ratio γ determine the scale and ellipticity of the classical receptive field, respectively, where γ is set to 0.5.
[0036]Although traditional visual perception methods consider the multi-scale factors of the classical receptive field, they do not pay attention to the information correlation between each scale. Therefore, the present invention first aims at a certain scale σ of the classical receptive field i (i=1,2,...,2k+1), ca...
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