Method for automatic photomotage of multi-face

An automatic synthesis, multi-face technology, applied in the field of face detection, can solve problems such as image deformation of face photos, and achieve the effect of high success rate, uniform color and clear facial features

Inactive Publication Date: 2009-07-15
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The synthesis of face photos involves the problem of image deformation

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 automatic photomotage of multi-face
  • Method for automatic photomotage of multi-face
  • Method for automatic photomotage of multi-face

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solution of the present invention will be further described in conjunction with specific implementation below.

[0034] The implementation uses the actual photographs of faces taken as the training library to build the AAM model, which is the preparatory work before implementing the following technical solutions.

[0035] The specific implementation process of the technical solution is as follows:

[0036] 1) Initially locate the face in the input photo, mark the rectangular area containing the face, and discard other parts of the photo. In this step, use Adaboost to perform face detection on the input photo to find out the rectangular area where the face is located. This area is not close to the edge of the face, but it can be slightly larger than the face, but the face is guaranteed to be included in the area. Crop the photo to keep only the rectangular area, and the obtained photo will enter the subsequent processing. If there is a large non-face area...

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 for automatically synthesizing multiple face photos. The method of the present invention is to automatically locate the outline and facial features of the human face through feature point tracking, and accordingly synthesize multiple photos into one. Without manual assistance, for each input photo, the present invention initially locates the position of the face in the photo, and then uses the multiple constraints of the positioned global and local information of the face to accurately mark the outer contour and facial features. On this basis, color adjustment is automatically performed on each photo to unify the color. Then through the deformation algorithm and the interpolation synthesis of each pixel color, a clear and real face photo with the characteristics of each input photo is obtained. The invention has the characteristics of high success rate, low hardware requirements, clear and natural results, etc., and can meet the application requirements on common hardware.

Description

technical field [0001] The invention relates to the technical fields of face detection, feature point tracking, multi-image synthesis and the like, in particular to an automatic synthesis method of a plurality of face photos. Background technique [0002] With the development of computer vision and the rapid improvement of hardware speed, some theories and methods of computer vision have reached the level of practical application under common hardware conditions. In recent years, some commercial software and services based on computer vision have gradually appeared and promoted to the public. The method of the present invention utilizes human face detection and feature point tracking, which are more researched in the field of computer vision, to realize the synthesis of multiple human face photos. [0003] Face detection and tracking of facial feature points is an unsolved problem in the field of computer vision, and it is also an important technology in applications such a...

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): G06T7/40G06K9/00
Inventor 陈纯卜佳俊庞晨宋明黎王栋
Owner ZHEJIANG 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