Method for generating novel human face by combining active grid and human face recognition

A technology of face recognition and grid, which is applied in the field of face recognition and image processing, can solve problems such as high efficiency, large batch processing, and inability to be widely used, and achieve realistic effects, clear methods, intuitive and clear Effect

Inactive Publication Date: 2008-11-19
上海中科计算技术研究所 +1
View PDF0 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The current face transformation is basically obtained by manual adjustment by artists through software. The final effect depen...

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
  • Method for generating novel human face by combining active grid and human face recognition
  • Method for generating novel human face by combining active grid and human face recognition
  • Method for generating novel human face by combining active grid and human face recognition

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0032] Example 1: Face age transformation

[0033] In the face age transformation system, the user inputs a photo, uses the face feature point standard defined by MPEG-4 as a template, uses the human-computer interaction mode, and finds the accurate active grid of the face through ASM and elastic map matching. . Compared with the local facial feature point positioning method, the active shape model (ActiveShape Models, ASM) method can locate many facial feature points at the same time, with fast speed and high precision. However, the ASM method is very sensitive to the initial position of the model. If the position of the feature point in the initial model is close to the position of the actual feature point, the ASM method will find all the feature points very quickly and accurately, but if the initial position is far away from the position of the actual feature point, the ASM method will Often may give a wrong location and cannot be used for identification. Therefore, on t...

example 2

[0034] Example 2: Making similar faces of celebrities

[0035]In the celebrity similar face making system, users can input their own photos and the photos of celebrities they want to transform. The method is the same as the feature point positioning method of the face age transformation system. The system automatically locates the feature points of the two photos. Make statistics on the feature point sets of the five parts of the mouth, eyes, eyebrows, nose, and face shape in the face database, obtain the average features of these five parts of the face, calculate the distance between the star face and the average point set, and the part with the largest distance is It can best reflect the most obvious features of the star's face, and replace this part with the user's photo by using the seamless stitching technology in the system, so as to obtain a face photo with star characteristics to achieve the effect of entertainment.

example 3

[0036] Example 3: Predicting children's faces from parents' photos

[0037] In the child face prediction system, the user can input two photos of a man and a woman, and the system automatically locates the feature points of the two photos in the same way as the feature point positioning method of the face age transformation system. For example, in the search method in the face age transformation system, a female photo or a male photo can be selected to search in the child database to obtain the most similar child. According to the method of counting the obvious features in the celebrity similar face making system, the most obvious features in the male and female photos are seamlessly stitched together with the children's photos, so as to obtain the children's photos with both father's characteristics and mother's characteristics, to achieve entertainment Effect.

[0038] The invention realizes a method for generating a new face by combining active grid and face recognition. G...

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 method which uses active mesh to combine with human face recognition to generate a new face; the method comprises the following steps: establishing a human face image database; based on the active mesh of human face, acquiring the feature points inputted into the human face image; searching in the human face image database for a similar face; using the seamless splicing technology for texture mapping so as to obtain a new human face. The face changing technology described by the invention is based on biological features and can realize facial expression changing, age transformation and role transformation of portraits in a fully automated way and can be widely applied to special effects in movie production and internet photo synthesis. The method retains the key biological features of the portrait to facilitate visual identification of identity. At the same time, the method uses a computer for image processing to obtain visual effects under given conditions and finally enables the processed human face image to have familiar features and expected artistic effects. The method has low computational complexity, clear and intuitive means and life-like effects.

Description

technical field [0001] The invention relates to a face recognition and image processing technology, in particular to a method for generating a new face by combining active grid and face recognition. Background technique [0002] With the development of image processing technology, face image has become a new research topic. The transformation of a human face image into another meaningful image has attracted people's attention due to its wide application prospects. [0003] For example, in the process of solving criminal cases, perpetrators often disguise themselves to avoid the attention of the police, and when a criminal suspect has been hiding for many years and then disguised, it is even more difficult for the police to identify him. If a face recognition database can be established, and the face image of the criminal can be transformed into the appearance after many years according to age matching, it will obviously be of great help to criminal investigation. Similarly...

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): G06T5/00G06K9/00
Inventor 崔国勤谢晨陈立珍杨立志高岩
Owner 上海中科计算技术研究所
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