Face repairing method based on advanced features

A repair method and advanced technology, applied in the field of image processing, can solve the problem that the image cannot get a better repair effect, and achieve the effect of ensuring the effect of fast repair and optimization.

Active Publication Date: 2019-02-19
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF9 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Image inpainting can be well applied to image editing and repairing damaged photo areas. Traditional image inpainting methods generally use the principle of symmetry to achieve repairing. For example, when the right eye area of ​​​​a face image is damaged, it can be repaired with reference to the left eye. For the right eye, when the left half of the mouth corner of a face image is damaged, it can be repaired by referring to the right half of the mouth corner, but when the image is missing in a large area, the existing methods cannot get a good repair effect
Therefore, repairing large areas of missing images (the main research object is face images) is still a challenging research topic

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 repairing method based on advanced features
  • Face repairing method based on advanced features
  • Face repairing method based on advanced features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0058] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as limiting the invention, its application or uses.

[0059] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the description.

[0060] In all examples shown and discussed herein, any specific values ​​should be construed as exemplary only, and not as limitations. Therefore, other instances of the exemplary embodiment may have diffe...

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 repairing method based on advanced features, which comprises the following steps: obtaining a damaged face image; outputting the damaged face image into two axisymmetricimage matrices; determining a breakage region in each of the image matrices; detecting whether an area symmetrical to the damaged area is damaged or not; if so, extracting advanced features of the damaged face image; obtaining reference data sets; acquiring, from the reference data set, a face image identical to a high-level feature of the damaged face image as a reference face image; obtaining asimulated face image according to the face image simulation in the reference data set; extracting data corresponding to the damaged area from the simulated face image to obtain initial repair data; optimizing the initial repair data to obtain repair data; repairing the damaged face image by using the repairing data, and generating the repaired face image. The invention improves the repairing effect of the damaged face image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically, relates to a face restoration method based on advanced features. Background technique [0002] Image inpainting is an important part of digital image processing research, and its purpose is to repair the damaged or lost part according to the information of the undamaged part. Image inpainting is mainly divided into two categories: image inpainting and image completion. Image inpainting is mainly aimed at repairing images caused by noise in the image or traces other than noise. The main work is to correct false images. Or corrupt data or remove unnecessary objects, image completion is mainly to complete the missing content of the image. [0003] Image repair is mainly divided into content and texture repair. The texture information of the damaged area is learned from the images around the damage, and then the content information of the damaged or missing part is as...

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
CPCG06T5/005G06T2207/20081G06T2207/30201
Inventor 刘瑞军李善玺师于茜王向上
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
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