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

Method for detecting moving human face

A technology of moving images and facial features, applied in the field of computer vision, can solve the problems of slow detection speed, inability to verify and correct retrieval results, and inability to use moving images, so as to achieve the effect of improving detection speed.

Inactive Publication Date: 2001-12-12
TSINGHUA UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main disadvantages of this method are: (1) due to the lack of full use of the prior knowledge of the face, therefore, the amount of calculation is large, the detection speed is slow, and it is not suitable for real-time application environments such as visual communication and non-contact computer operation; (2) Since only the information provided by a single still image is used, the retrieval results cannot be verified and corrected; (3) only the feature points on a single image can be retrieved, and cannot be used for moving images

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 detecting moving human face
  • Method for detecting moving human face
  • Method for detecting moving human face

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] 1. Geometric calibration

[0016] Take 100-300 face images of different genders, ages, poses and lighting to form a training set. Through a homogeneous transformation, the eye geometry of the images in the training set is calibrated so that the size and position of the eyes in these images are exactly the same. In the next step, the same geometric calibration is performed on the eyes in the tested face images, so that the relative positions of the two pupils of the eyes remain unchanged in the training set images and the test images.

[0017] Suppose the original image is I(x,y), and the positions of the two pupils are known to be E L (x L ,y L ) and E R (x R ,y R ), the angle between the line connecting the pupils and the horizontal axis is θ. Now transform the image I(x,y) into I′(x,y) through homogeneous transformation (Equation 1), so that the positions of the two pupils are E L0 (x L0 ,y L0 ) and E R0 (x R0 ,y R0 ). E. L0 (x L0 ,y L0 ) and E R0 (x...

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 present invention relates to detection method of human face characteristics of motion image, firstly, take picture of human face image to construct discipline collection, then proceed principal component analysis, Hough conversion etc. to make its position and size coinside with the eye in discipline collection iamge, then project onto space of above mentioned characteristic eye, finally, take the eye being selected with minimum error between original eye and its projection as the detection result, and use integral projection to obtain precision position of mouth, nostril and apex nasi. Compared with existent method, the detection speed raises 225 times and accuracy increased by 1.27%.

Description

Technical field: [0001] The invention relates to a face feature detection method of moving images, which belongs to the technical field of computer vision. Background technique: [0002] Existing face feature detection methods are based on still images. In "Robust Face Feature Detection Based on Generalized Symmetry" (Proceedings of the 11th International Conference on Pattern Recognition, 1992, pp.117-120), the authors D.Reisfeld and Y.Yeshura proposed a A typical still image face feature detection method. The principle of this method is: according to the local and global symmetry of the face, first define a complex measure of symmetry (called the degree of symmetry), and then iteratively calculate the degree of symmetry for each edge point in the image through the energy function , the point with the largest symmetry degree is considered as a feature point. This method can detect pupils and mouth corners in human faces, with a correct rate of about 95%, and the detectio...

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): A61B5/1171G06F17/00G06K9/62
Inventor 徐光彭振云
Owner TSINGHUA UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com