Multi-scale segmentation-based saliency detection method
A multi-scale segmentation and salience technology, applied in image analysis, image data processing, instruments, etc., to achieve the effect of good texture and noise information
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] A salient target detection method based on multi-scale segmentation, including:
[0042] Step 1: Use bilateral filtering parameters to perform bilateral filtering and smoothing processing on the input image to obtain a smooth image, and perform superpixel segmentation on the smooth image with different segmentation scales; calculate the global smoothness according to all the superpixels obtained by segmentation; calculate the global smoothness Combining with the bilateral filtering parameters, construct an adaptive algorithm function aiming at the segmentation effect, solve the bilateral filtering parameters at different scales, and obtain the optimal superpixel points in the smooth image;
[0043] Step 2: Use the target likelihood map technique to obtain the initial foreground seed, and use the boundary of the image as the initial background seed, select the background seed and the foreground seed from the initial foreground seed and the initial background seed through ...
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