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

Refactoring method for optimizing super resolution of facial images

A technology for super-resolution reconstruction and facial image, which is applied in the field of optimized super-resolution reconstruction of facial images, which can solve the problems of insufficient image precision and degradation of face recognition performance, and achieve high-precision reconstruction and suppress glitches Effect

Inactive Publication Date: 2013-03-27
HUBEI WEIJIA TECH
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the accuracy of the image reconstructed by the existing super-resolution reconstruction method is not enough, resulting in a serious decline in the performance of face recognition.

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
  • Refactoring method for optimizing super resolution of facial images
  • Refactoring method for optimizing super resolution of facial images
  • Refactoring method for optimizing super resolution of facial images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with embodiment:

[0049] Such as figure 1 As shown, the detailed calculation steps of an optimized face image super-resolution reconstruction method in the embodiment of the present invention are described as follows:

[0050] A method for optimizing face image super-resolution reconstruction, comprising the following steps:

[0051] Step 1), first take the input low-resolution face image I and K low-resolution reference face images I with the closest Euclidean distance to the input low-resolution face image I k (x), low-resolution reference face image I k (x) The image translated by p units by the affine translation operator is I k (x+p); Preferably, K=6 is used to ensure both reconstruction accuracy and calculation speed.

[0052] Step 2), input low-resolution face image I and K low-resolution reference face images I with the closest Euclidean distance to the input low-resolution face image I in...

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 belongs to the field of refactoring of the super resolution of facial images and particularly provides a refactoring method for optimizing the super resolution of the facial images. The method includes step one, inputting a low-resolution facial image and K low-resolution reference facial image; step two, calculating a local embedding coefficient; step three, substituting a local embedding system into a refactoring model to calculate a refactored image with a high resolution; and step four, taking the image solved in the last step as an input image. The method can improve the face recognition accuracy.

Description

technical field [0001] The invention belongs to the field of image super-resolution reconstruction, in particular to a super-resolution reconstruction method for optimizing human face images. Background technique [0002] Patent No. 201210164069.9 discloses a super-resolution face recognition method based on multi-manifold discriminant analysis. In the training phase, the method obtains a multi-manifold image composed of low-resolution and high-resolution face images through multi-manifold discriminant analysis. A mapping matrix from the space to the multimanifold space of high-resolution face images. Construct the intra-class similarity graph and inter-class similarity graph in the multi-manifold space of the original high-resolution face image, use these two neighbor graphs to construct the discriminant constraint item, and optimize the cost function composed of the reconstruction constraint item and the discriminant constraint item , to get the mapping matrix. In the re...

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): G06K9/00
Inventor 不公告发明人
Owner HUBEI WEIJIA TECH
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