Face portrait synthesis method based on adaptive representation

A face portrait and synthesis method technology, applied in the field of image processing, can solve the problems of low definition of synthesis results, blurred synthesis results, blurred details, etc., and achieve the effect of clear synthesis results

Active Publication Date: 2018-08-10
深圳爱莫科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that because the number of neighbors is fixed, the synthesis result has defects of low definition and blurred details.
However, the disadvantage of this method is that only one training image block is selected for each photo block position for image synthesis, resulting in block effects and missing details in the synthesis results.
However, the disadvantage of this method is that it ignores the relationship between adjacent image blocks, resulting in blurring and block effects in the synthesis results.

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 portrait synthesis method based on adaptive representation
  • Face portrait synthesis method based on adaptive representation
  • Face portrait synthesis method based on adaptive representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The core idea of ​​the present invention is to propose a face portrait synthesis method through the idea of ​​adaptive representation, so that different face regions are synthesized with different features, and the image quality of the synthesis result is improved.

[0027] Reference figure 1 , The implementation steps of the present invention are as follows:

[0028] Step 1. Select test photo P Te .

[0029] Divide the training library and the test library from the portrait-photo N pair database, and select a photo from the test library as the test photo P Te .

[0030] Step 2. Obtain two training photo block dictionaries D p1 And D p2 .

[0031] 2a) Perform Gaussian difference filtering on the photos in the training library:

[0032] 2a1) Construct two Gaussian functions with different scale values ​​σ:

[0033]

[0034] Among them, G(x,y,σ) represents the Gaussian function under the σ scale value, and x and y represent the horizontal and vertical coordinate values ​​correspondi...

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 image synthesis method based on adaptive expression. By using the method, problems that synthesized image definition is low and details are not complete in an existing method are solved. The method comprises the following steps of firstly, processing a database, carrying out image filtering on all the images, then partitioning the images and extracting an image block characteristic so as to obtain one training image block dictionary and two photograph block dictionaries; secondly, testing whether a photograph block includes edge information or face characteristic information, according to that, selecting different dictionaries and searching a neighbor block; and finally, using a Markov network model to obtain image blocks to be synthesized, fusing all the image blocks to be synthesized and acquiring the synthesized image. Compared to the prior art, by using the method, a synthesis result possesses high definition and complete details and can be used for face retrieval and identification.

Description

Technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a face portrait synthesis method in the technical field of pattern recognition and computer vision, and can be used for face retrieval and recognition in criminal investigation and solving cases. Background technique [0002] With the development of modern society and multimedia, more and more video images of people are recorded. How to identify and authenticate a person's identity based on the existing images has become one of the problems that need to be solved. Among them, face recognition has The characteristics of directness, friendliness and convenience have been widely studied and applied. One of the important applications of face recognition technology is to assist the police in solving crimes. However, in many cases, it is difficult to obtain the photos of some serious suspects, or the obtained photos are not frontal or unevenly lit. Then the police ca...

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 Patents(China)
IPC IPC(8): G06T5/50
CPCG06T5/50G06T2207/20221G06T2207/20224G06T2207/30201
Inventor 王楠楠于昕晔高新波彭春蕾李洁査文锦孙雷雨张宇航朱明瑞曹兵马卓奇
Owner 深圳爱莫科技有限公司
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