Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face image super-resolution reconstructing method based on canonical correlation analysis

A canonical correlation analysis and super-resolution reconstruction technology, which is applied in the field of face image super-resolution reconstruction based on canonical correlation analysis.

Inactive Publication Date: 2009-12-30
XI AN JIAOTONG UNIV
View PDF0 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods need to assume the consistency of the internal geometric structure of the high and low resolution images of the face image, but in practice, due to the limited training data and other conditions, the consistency of the geometric structure obtained by training cannot be guaranteed. Artifacts are brought about in the reconstructed results, reducing the performance of the reconstruction

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face image super-resolution reconstructing method based on canonical correlation analysis
  • Face image super-resolution reconstructing method based on canonical correlation analysis
  • Face image super-resolution reconstructing method based on canonical correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention 1) uses a two-step method to perform super-resolution reconstruction of the frontal face, which are respectively a global face reconstruction process and a residual compensation process, wherein the global face mainly recovers the middle and low frequency information of the face image, and the residual compensation recovers high frequency information.

[0029] 2) A learning-based face super-resolution reconstruction method is adopted, so two processes of training and testing are respectively included in the process of global face reconstruction and residual compensation.

[0030] 3) In the process of global face reconstruction, first use PCA to extract the features of the face images in the training set, and obtain the corresponding CCA mapping vector, so as to convert the extracted PCA coefficients to the CCA subspace; secondly, obtain the test low-resolution The PCA coefficients of , and use the CCA mapping vector to convert it to the CCA subspace...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a face image super-resolution reconstructing method based on Canonical Correlation Analysis (CCA), which taking principal constituent analysis coefficients of a high resolution face image and a low resolution face image as two different variables with different dimensions and utilizing the CCA to extract relevant subspaces of the high resolution face image and the low resolution face image, thereby enhancing the consistency of a topological structure inside a high and low resolution image data set. In the relevant subspaces, the face image super-resolution reconstructing method can reconstruct a principal constituent analysis coefficient of a corresponding high resolution image to an input low resolution image by utilizing adjacent domain reconstructing idea, thereby reconstructing an entire face image. The invention divides a residual image into seven squares, compensates detail information by using the CCA method and the adjacent domain reconstructing idea and reconstructs the high resolution residual image. The final high resolution face image is the addition of an entire face image and the high resolution residual image.

Description

technical field [0001] The invention relates to the field of image super-resolution reconstruction, in particular to a face image super-resolution reconstruction method based on canonical correlation analysis. Background technique [0002] Image super-resolution (Super Resolution, SR) refers to the process of obtaining a high-resolution (High Resolution, HR) image from one or a series of low-resolution images (Low Resolution, LR). In recent years, video surveillance has been widely used in important places such as banks and airports. But in many cases, the resolution of face images obtained by monitoring equipment is too low to be recognized directly, so the research on face image super-resolution has practical significance. [0003] Since Baker et al. proposed the idea of ​​"Hallucinating faces" in 2000, the super-resolution of frontal face images has attracted the attention of many researchers. Baker et al. selected the horizontal and vertical derivatives of the Gaussian...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T5/50G06K9/36
Inventor 黄华何惠婷
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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