Image significance detection method based on region label fusion
A technology of label fusion and detection method, applied in the field of image processing, which can solve the problems of unclear boundaries in image salient areas and not dense internal areas.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0061] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.
[0062] See figure 1 , Provide an image saliency detection method based on region tag fusion, including:
[0063] S1: Use super pixel segmentation algorithm to preprocess the image and over segment the image into several image area blocks;
[0064] S2: Use Gaussian kernel function to obtain area similarity according to the color and location information of the image area block, use the area similarity to perform spectral clustering of the super pixel area, obtain a label set for image segmentation, and save according to the label set Image boundary information;
[0065] S3: Obtain the salient features of the image, and perform the fusion of the salient features under the conditional random field model to obtain a saliency map of roughness;
...
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