Pyramid face image super-resolution reconstruction method based on regression model

A technology of super-resolution reconstruction and face image, which is applied in the field of super-resolution reconstruction of pyramidal face image based on regression model, which can solve problems such as not considering image quality, face image ghosting and influence in the process of face image degradation

Inactive Publication Date: 2018-05-29
HEBEI UNIV OF TECH
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of the present invention overcomes the problems in the prior art that the difference between the high-resolution images in the training set does not consider the influence of the difference between the high-resolution images in the training set on

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
  • Pyramid face image super-resolution reconstruction method based on regression model
  • Pyramid face image super-resolution reconstruction method based on regression model
  • Pyramid face image super-resolution reconstruction method based on regression model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] The method for super-resolution reconstruction of a pyramid face image based on a regression model of this embodiment, the specific steps are as follows:

[0106] A. Training process of low-resolution face image set and high-resolution face image set in the training set:

[0107] The first step is to expand the low-resolution face image set and high-resolution face image set in the training set:

[0108] According to the symmetry of the face image, the low-resolution face image set and the high-resolution face image set in the training set are expanded by turning left and right. The size of the image remains unchanged, and the number is expanded twice, respectively. Low-resolution face image collection And expanded high-resolution face image collection Where l represents a low-resolution image, the size is a*b pixels, h represents a high-resolution image, the size is (d*a)*(d*b) pixels, d is a multiple, the value of d is 2, and M represents an image quantity;

[0109] The se...

Embodiment 2

[0177] Except R in the third step 1 The value of is 10, R in the fourth step 1 The value of is 10, R in the seventh step 1 The value of is 10, R in the eighth step 1 The value of is 10, the R in (18.3) of the eighteenth step 2 Except for the value of 8, the others are the same as in Example 1.

Embodiment 3

[0179] Except R in the third step 1 The value of is 12, R in the fourth step 1 The value of is 12, R in the seventh step 1 The value of is 12, R in the eighth step 1 The value of is 12, the R in (18.3) of the eighteenth step 2 Except for the value of 10, the others are the same as in Example 1.

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 relates to a pyramid face image super-resolution reconstruction method based on a regression model, and relates to the enhancement or restoration of an image. The feature that images have a non-local similarity is used to search low-resolution face images in a test set in corresponding feature images thereof for similar blocks of reconstruction image blocks to obtain a position set of all similar blocks. Face image blocks in the position set of all low-resolution images in a training set are used as a low-resolution training set corresponding to the low-resolution face image blocks in the test set. The sum of the distances between feature image blocks corresponding to the low-resolution face image blocks in the test set and feature image blocks corresponding to the low-resolution face image blocks in the training set and the distances between feature image blocks corresponding to the face image blocks after the low-resolution images in the test set are interpolated and amplified and the feature image blocks corresponding to high-resolution face image blocks in the training set constitutes constraint conditions. The method overcomes many deficiencies in the face imagereconstruction process of the prior art.

Description

Technical field [0001] The technical solution of the present invention relates to image enhancement or restoration, and specifically is a super-resolution reconstruction method of a pyramid face image based on a regression model. Background technique [0002] In the process of image acquisition, due to the limitations of the imaging system and the influence of environmental factors, the acquired image and the real scene are often deviated. How to increase the spatial resolution of the image and improve the image quality has always been an important problem that the image acquisition technology is committed to solving. With the development of science and technology, the performance of the hardware equipment of the imaging system is getting better and better, but the method of improving the image quality by upgrading the hardware system requires a high cost. On the basis that the hardware level has reached a certain level, improving the image quality through software technology ha...

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): G06T3/40
CPCG06T3/4007G06T3/4076
Inventor 于明熊敏刘依郭迎春于洋师硕毕容甲
Owner HEBEI UNIV OF TECH
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