Unlock instant, AI-driven research and patent intelligence for your innovation.

Mouth-corner positioning method

A positioning method and technology for the corners of the mouth, which can be used in instruments, character and pattern recognition, computer parts, etc.

Inactive Publication Date: 2005-12-21
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in most cases, due to the influence of complex background and lighting, it is very difficult to locate the corner of the mouth only relying on a certain color space, grayscale and edge
[0003] After searching the prior art literature, it was found that Rein-Lien Hsu et al. (Rein-Lien Hsu, Mohamed Abdel-Mottaleb, Anil K. Jain Face Detection in Color Images Institute of Electrical and Electronics Engineers Pattern Analysis and Machine Learning VOL 24, NO.5.MAY 2002) has given the distribution of each component of the mouth area in the YCbCr color space through the statistics of a large number of samples, and roughly locates the position of the mouth according to the distribution of these components, but cannot give the precise positioning of the corner of the mouth

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
  • Mouth-corner positioning method
  • Mouth-corner positioning method
  • Mouth-corner positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] The face images used in this embodiment are from the face image library jointly taken by Shanghai Jiaotong University and Fudan University School of Medicine, and the implementation process is as follows:

[0025] (1) Convert the original image to the YCbCr space and perform corresponding processing, calculate the result of dividing the Cr component by the Cb component for each pixel in the image, and record it as Cr_div_Cb, and calculate the square of the Cr component at the same time, record it as Cr_mul_Cr, for each After performing such operations on each pixel, two matrices are obtained: Cr_div_Cb, Cr_mul_Cr, and then the two matrices are normalized, that is, the maximum value of the matrix is ​​calculated, and then each element in the matrix is ​​divided by this maximum Value, so two normalized matrices are obtained, Cr-_div_Cb, Cr_mul_Cr. Then calculate a constant K, K=0.95*mean(Cr_mul_Cr) / mean(Cr-_div_Cb), where mean means to find the average value of the matrix...

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

Base on color distributed on lip, the method obtains probable position of mouth area. Next, histogram of the said area is analyzed, and treatment of threshold value is carried out for the area so as to obtain binary image. Then, two times of erosion operation are carried out for the binary image, and analysis of connected region is carried out for the eroded image. Two times of expansion operation are carried out for the largest connected region. Finally, analyzing expanded image so as to locate position of corners of the mouth accurately. The invention gives position of corners of the mouth accurately so as to raise accurate to identify human face and emotional expression.

Description

technical field [0001] The invention relates to a method belonging to the technical fields of digital image processing and pattern recognition, in particular, a mouth corner positioning method. Background technique [0002] Face feature point detection is a key technology in applications such as face recognition, expression recognition, gender recognition, and age estimation. The accuracy of feature point location directly affects the accuracy of recognition, and the mouth corner feature is very important in face features. . Therefore, accurately locating the position of the corner of the mouth can greatly improve the accuracy of recognition. The current location of mouth corners is mainly based on the distribution of lip colors in different color spaces, the analysis of image grayscale and image edges. But in most cases, due to the influence of complex background and lighting, it is very difficult to locate the mouth corner only relying on a certain color space, grayscale...

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): G06K9/00
Inventor 杜春华杨杰
Owner SHANGHAI JIAO TONG UNIV