Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Robust face registration via multi-face prototypes synthesis

一种面部、原型的技术,应用在计算机零部件、图像数据处理、仪器等方向

Inactive Publication Date: 2005-06-08
AGENCY FOR SCI TECH & RES
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, various conditions and situations can still produce less promising results, thus requiring alternative methods to improve facial recognition

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
  • Robust face registration via multi-face prototypes synthesis
  • Robust face registration via multi-face prototypes synthesis
  • Robust face registration via multi-face prototypes synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Since accurate face recognition is difficult to achieve due to eg changing lighting conditions, the present invention proposes a method or system relying on a stronger registration process.

[0024] Most existing systems capture an image of a person and store the image for later comparison. In the present invention, during the process of registering a person's face, the system automatically synthesizes multiple (multiple) facial prototypes. These facial prototypes represent the likely appearance of the initial face under various lighting conditions, various expressions, and various facial orientations, as well as various errors of the facial localization system. The system obtains for each face a set of faces that can cover the possible appearances that face can have.

[0025] After generating the plurality of facial prototypes, data analysis can be applied, such as dimension reduction (principal component analysis), feature extraction, automatic clustering, self-orga...

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

A face recognition and / or vertification system including the step of registering a persons actual face wherein a image of the actual face is captured and synthesized to create a plurality of face prototypes, and wherein the face prototypes are stored for later analysis and comparison with a captured image to be recoginsed or verified.

Description

technical field [0001] The present invention is directed generally to facial recognition and facial verification systems, and in particular to a facial prototyping system capable of generating realistic templates and providing a system for more robust registration of faces. Background technique [0002] The traditional approach to facial recognition is to store images of people's faces and then provide facial matching algorithms that are robust enough to handle changing lighting conditions, facial expressions, facial orientation, glasses, beards, beards, and facial hair, etc. [0003] In the field of facial recognition technology, research has focused almost exclusively on developing algorithms that are invariant to lighting conditions, facial expressions, and facial orientation. Such systems obtain simple databases at the expense of complex matching algorithms or families of algorithms. Alternatively, face recognition systems based on facial template matching and neural ne...

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): G06T7/00G06K9/00G06K9/32G06K9/46G06T1/00
CPCG06V40/172
Inventor 罗伯托·马里亚尼
Owner AGENCY FOR SCI TECH & RES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products