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

HR (restrict restriction)-LLE (locally linear embedding) weight constraint based face image super-resolution restoration method

A face image and weight technology, applied in image enhancement, image data processing, instruments, etc., can solve problems such as error and non-isometricity, and achieve good image restoration results

Inactive Publication Date: 2014-08-06
山东网源信息技术有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the mapping from LR to HR space is a one-to-many mapping relationship, there is non-isometry in this mapping
Directly replacing the HR space weights with the weights of the LR space will introduce errors

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
  • HR (restrict restriction)-LLE (locally linear embedding) weight constraint based face image super-resolution restoration method
  • HR (restrict restriction)-LLE (locally linear embedding) weight constraint based face image super-resolution restoration method
  • HR (restrict restriction)-LLE (locally linear embedding) weight constraint based face image super-resolution restoration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The implementation examples of the present invention will be described below in conjunction with the accompanying drawings.

[0032] (1) Global HR-LLE weight constraint reconstruction

[0033] (1) Global average reconstruction weight constraint

[0034] First, two face image sample libraries need to be established, namely, the paired HR face image sample library and the corresponding LR face image sample library. In this invention, the CAS-PEAL face image library and the self-built second-generation ID card image library were selected for experiments; a total of 1470 frontal face images were selected, and they were all normalized to 140×160 pixel size as the sample library. HR face samples; downsample HR face samples by 4 times to generate corresponding LR face samples.

[0035] Using the traditional LLE-based weight solution method to calculate each LR face sample relative to its K 1 The reconstruction weight of the nearest neighbor sample, as shown in formula (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 belongs to the filed of digital image processing and particularly relates to an HR (restrict restriction)-LLE (locally linear embedding) weight constraint based face image super-resolution restoration method. The restoration method includes: calculating a great many of HR face samples and average restoration weight constraint, relative to neighboring samples, of residual HR faces; during restoration, subjecting traditional LLE based face super-resolution restoration weight calculation method to weight constraint. The restoration method includes overall restoration and local detail compensation. The overall restoration aims to restore basic characteristics of a standard face as required, and the local detail compensation aims to restore the face image so as to enable the face to be provided with personality characteristics different from other faces. The HR-LLE weight constraint is added in the method in estimating the LLE based restoration weight of the target HR image, so that the weight is closer to the true restoration weight of the HR image in 12 norms. By the method, better image restoration results can be acquired.

Description

technical field [0001] The invention belongs to the field of digital image processing, in particular to a human face image super-resolution restoration method based on HR-LLE weight constraints. Background technique [0002] In recent years, technologies such as face detection and recognition have played an increasingly important role in multimedia applications such as video surveillance, mobile terminals, and network retrieval. The quality of face images has a great influence on the performance of these multimedia applications. However, due to the influence of image acquisition equipment and acquisition environment, especially in uncontrollable natural environments, the quality of acquired face images is usually poor, and it is difficult to be directly applied to subsequent detection and recognition. It is particularly important to use super-resolution restoration (SuperResolution, SR) technology to improve the quality of face images after face image collection. [0003] ...

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): G06T5/00
Inventor 李晓光魏振利卓力
Owner 山东网源信息技术有限公司
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