Precise image semantic segmentation and optimization method using interaction means
An optimization method and semantic segmentation technology, applied in the field of image processing, can solve the problems of less accurate information, affecting the segmentation effect, and unable to remove redundancy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] like figure 2 As shown, this embodiment involves an image semantically accurate segmentation and optimization method using interactive means. By obtaining four demarcation points input by the user, a sub-image containing the target area is cut out from the original image and preprocessed. Input the trained convolutional neural network for semantic segmentation to obtain preliminary segmentation results; then, use the position and color information of the pixels in the image to construct a fully connected conditional random field, use the underlying features to optimize the segmentation results and display them, and wait for the user to check the effect And click on the segmentation error area to clarify the front and back background of the corresponding area, the algorithm is updated and the conditional random field model is calculated, and the area that the user is not satisfied with is corrected until the interaction is terminated, and the segmentation result is saved...
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