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

Face characteristic point automation calibration method based on conditional appearance model

A face feature and appearance model technology, applied in the field of image analysis, can solve the problems of slow algorithm calculation speed and inaccurate assumptions.

Inactive Publication Date: 2012-09-12
JIANGNAN UNIV
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The registration algorithm of AAM assumes that there is a simple linear relationship between the error image and the increment of the model parameters. This linear relationship can be calculated by regression or other numerical methods, but in fact this assumption is not true. Accurately, Baker et al. cited a counterexample in the literature [117], and in the process of using this difference to update the model parameters linearly, each iteration will generate a new texture, which greatly reduces the calculation speed of the algorithm.

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 characteristic point automation calibration method based on conditional appearance model
  • Face characteristic point automation calibration method based on conditional appearance model
  • Face characteristic point automation calibration method based on conditional appearance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Combine below figure 1 The specific illustrations in the present invention are further elaborated.

[0066] refer to figure 1 The flowchart in the present invention realizes the facial feature point automatic labeling method based on the conditional appearance model of the present invention. Firstly, the discrete feature point correspondence between the frontal face and the side face is established, and the discrete feature points obtained by the regression algorithm and the structured mark The mapping relationship between the fixed points is used to obtain the initial calibration result of the profile face. Then, the corresponding relationship between the key feature points of the side face and the key feature points of the front face is established, and the conditional shape model is established. According to the reverse synthesis fitting algorithm, the final calibration is obtained through continuous iterative optimization of the model parameters. result. The spec...

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, which belongs to the computer vision field, discloses a face characteristic point automation calibration method based on a conditional appearance model. The method comprises the following steps: assuming that front face calibration is known; firstly, establishing that a discrete characteristic point of the front face corresponds to the discrete characteristic point of a side face; through a mapping relation between discrete characteristic points and a structural calibration point, acquiring an initialization calibration result of the side face, wherein the mapping relation is acquired by a regression algorithm; then, establishing the conditional model between the side face calibration point and the front face calibration point, continuously carrying out iteration optimization on a model parameter according to a reverse synthesis algorithm so as to obtain a final calibration result. According to the invention, the space mapping of the discrete characteristic points and the structural calibration point is established through kernel ridge regression (KRR) so as to obtain the initial calibration of the face characteristic. A subsequent iteration frequency is reduced and calibration precision is improved. The conditional appearance model and the reverse synthesis iteration algorithm are designed. Appearance deformation searching can be avoided and a searching efficiency can be improved. Compared to a traditional active appearance model (AAM), by using the calibration method of the invention, the calibration result is more accurate.

Description

technical field [0001] The invention belongs to the technical field of image analysis, in particular to an automatic calibration method of facial feature points based on a conditional appearance model. Background technique [0002] In the field of computer vision research, locating and describing the target object is a research topic that has attracted much attention. Finding the target area of ​​interest from the image and interpreting it with the help of a computer is a basic problem in computer vision research. It is an essential and important step in the application of technology in the fields of industrial inspection, target recognition and image processing. This technique has received the attention of many researchers. For face images, although humans can easily identify the exact location of facial feature points from a face image, it is not an easy task for computers. [0003] The positioning of facial feature points is a key technology in the face recognition syst...

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): G06K9/00G06K9/62
Inventor 陈莹艾春璐化春键张龙媛
Owner JIANGNAN 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