Method for detecting image significance
An image and saliency technology, applied in the field of image saliency detection, can solve problems such as difficult to highlight, difficult to highlight targets, and easy to lose target information.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0040] Step 1: Detect Harris points for a given image. Due to the observation of general image complexity, we detect 30 interest points for each image.
[0041] Step 2: Since some of the detected interest points will be background interest points, we remove the interest points on the image boundary, that is, remove the interest points within 26 pixels from the image boundary to obtain a more stable points of interest, if attached figure 2 (b) shown.
[0042] Step 3: Connect the obtained interest points into the largest convex polygon, which is defined as a convex hull, as shown in the attached figure 2 As shown in (c), the outside of the convex hull is considered to be the foreground, and the inside is considered to be the background.
[0043] Step 4: Use the SLIC toolbox to over-segment the image to obtain the superpixels of the image. Each image is over-segmented to obtain 200 superpixels, as shown in the attached figure 2 (d) shown.
[0044] Step 5: Determine the int...
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