Method for super-resolution reconstruction of facial image on basis of sample learning

A super-resolution reconstruction and sample image technology, applied in the field of image processing, can solve the problems of local reconstruction that does not fully consider the face structure, low similarity, loss of information, etc., to improve the effect, increase the speed, and improve the super-resolution Effect

Inactive Publication Date: 2010-10-27
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The feature of this method is that the obtained image is smooth and has better visual effects; but it also has obvious shortcomings, such as the loss of a large amount of information during global reconstruction, which makes the similarity between the reconstruction result and the input image low.
In addition, its local reconstruction does not fully consider the structure of the face, so there is still a lot of room for improvement in the effect and efficiency of the algorithm

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
  • Method for super-resolution reconstruction of facial image on basis of sample learning
  • Method for super-resolution reconstruction of facial image on basis of sample learning
  • Method for super-resolution reconstruction of facial image on basis of sample learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0028] Based on the present invention, as figure 1 Show the flow chart of face image super-resolution reconstruction method, comprise steps as follows:

[0029] Step S1: Enter the training part, first set up a sample image set {I H} m , where I H Represents a sample image, and the i-th sample image in the sample image set is expressed as 1≤i≤m, use the face calibration algorithm or manually calibrate the face structure in the m sample images, obtain the face features of each sample image, and perform alignment processing on the m sample images according to the face features, Make the same facial features be located in roughly the same position in the sample image;

[0030] Step S2: Using the formula For the i-th s...

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 provides a method for the super-resolution reconstruction of a facial image on the basis of sample learning, in particular to a method for the super-resolution reconstruction based on sample learning and targeted on the optimization of facial structural characteristics. The method of the invention is characterized by comprising the following processing steps of: (1) dividing the method into a training part and a super-resolution reconstruction part; (2) calibrating and blocking the inputted image; (3) searching for a residual facial image by neighborhood in the database acquired in training according to the calibration result; and (4) calculating the inputted image by using the residual facial image. Accordingly, the algorithm provided by the invention is particularly suitable for the super-resolution processing for facial images; and the method has the characteristics of high processing rate and strong robustness and maintains the better effect at the same time.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a face image super-resolution reconstruction method based on sample learning, in particular to a method of using sample learning to perform super-resolution reconstruction on low-resolution face images to obtain high-resolution faces images, and optimize for facial features. Background technique [0002] The goal of face image super-resolution reconstruction technology is to enhance the face image to be super-resolution. Although the existing image interpolation algorithm can enlarge the image relatively smoothly, but because the interpolation algorithm cannot restore the information lost when the image is reduced, Therefore, the enlarged image is blurred and has little use value. [0003] Face image super-resolution reconstruction technology can be mainly adapted to the following situations: [0004] 1. Enlarge the photos stored in the existing IC card for easy viewing ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/50G06K9/66
Inventor 王欣刚安闻川刘东昌
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap