Face image super-resolution reconstruction method based on two-dimensional multi-set partial least squares
A technology of super-resolution reconstruction and partial least squares method, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problem of joint learning of multiple views that has not received widespread attention, and cannot effectively use the correlation relationship of different resolution views. Time-consuming efficiency and other issues
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0054] Such as figure 1 The shown face image super-resolution reconstruction method based on two-dimensional multi-set partial least squares is characterized in that, comprising the following steps:
[0055] Step 1 In the training phase, the training set is used to learn the potential correlation between views of different resolutions, the high-frequency images of different views in the training set and their corresponding low-resolution images are divided into overlapping image blocks, and two-dimensional multi-set The partial least squares method extracts the features of the two-dimensional image block, calculates the two-dimensional multi-set partial least squares projection matrix, and projects the two-dimensional image block to the two-dimensional multi-set partial least squares subspace;
[0056] Calculating the two-dimensional multi-set partial least squares projection matrix in step 1 includes the following steps:
[0057] (1) For m views Figure II dimensional cente...
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