Face image-picture generating method based on sparse representation

A technology of sparse representation and sparse representation of coefficients, applied in the field of image processing, can solve the problems of low definition and fuzzy details of pseudo-photo results

Inactive Publication Date: 2011-01-26
XIDIAN UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Also due to the use of K-nearest neighbors, the resulting pseudo-photo results have low definition and blurred details

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 image-picture generating method based on sparse representation
  • Face image-picture generating method based on sparse representation
  • Face image-picture generating method based on sparse representation

Examples

Experimental program
Comparison scheme
Effect test

example

[0058] 1. A method of generating pseudo-portraits from face photos based on sparse representation

[0059] refer to figure 1 , the specific steps of the false image generation method of the present invention are as follows:

[0060] The first step is to divide the training sample set and the test sample set;

[0061] Divide the portrait-photo pair set into a training sample set and a test sample set, wherein the training sample set includes a training portrait set and a training photo set, the test sample set refers to a test photo set, and a photo in the test photo set is selected as a test photo P .

[0062] In the second step, according to the training sample set and the test photo P, an initial pseudo-portrait is generated using a pseudo-nonlinear method or an embedded hidden Markov model method For specific methods, please refer to "Liu Q S, Tang X O.A Nonlinear approach for face sketch synthesis and recognition.IEEE International Conference on Computer Vision and Pat...

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-picture generating method based on sparse representation, which mainly solves the problems of low definition and blurry details of a pseudo image and a pseudo picture generated in the traditional method. The face image-picture generating method comprises the following implementation processes of: generating an initial pseudo image and an initial pseudo picture by using the traditional pseudo image and pseudo picture generating method; blocking all images and then training an image block dictionary and a picture block dictionary by utilizing a training sample set; synthesizing high definition characteristics information according to an input test picture block or an input test image block by utilizing the two dictionaries; adding the obtained high definition characteristics information and the corresponding initial pseudo image block or the initial pseudo picture block to obtain a final pseudo image block or a pseudo picture block with high definition; and fusing all pseudo images and pseudo pictures with high definition to obtain a complete pseudo image or a complete pseudo picture. Compared with the prior art, the generated pseudo image and pseudo picture have the advantages of high definition and obvious details and can be used for face identification and face retrieval.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to face portrait-photo generation, and can be used for retrieval and recognition of human faces in the fields of criminal investigation and anti-terrorism. Background technique [0002] With the advent of the information age, people feel more and more the importance of information security. Identification and authentication technology is an effective means to ensure information security, and it has developed more and more rapidly in recent years. Face-based identification and authentication technology is one of the most convenient and effective authentication technologies, so face recognition has attracted much attention in recent years. Due to the different imaging methods, face images can have many examples, such as photos, portraits, etc., so face recognition is not limited to the recognition of face photos. Correspondingly, there are two main ways of face recognition based o...

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): G06T11/00G06K9/00G06K9/62
Inventor 高新波王楠楠李洁王斌张杰伟邓成韩冠肖冰
Owner XIDIAN UNIV
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