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

Human face light alignment method based on secondary multiple light mould

A quadratic polynomial, lighting model technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of not achieving the visual effect of the face, limiting the scope of application, etc.

Inactive Publication Date: 2007-10-03
SUN YAT SEN UNIV
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, the illumination components decomposed by the LTV model still contain a lot of useful information for face recognition, and these components are not used for face recognition in the illumination processing algorithm based on the LTV model.
In addition, this method only extracts illumination invariants for face recognition, and does not achieve a real improvement in the visual effect of faces, which also limits the scope of application of this method.

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
  • Human face light alignment method based on secondary multiple light mould
  • Human face light alignment method based on secondary multiple light mould
  • Human face light alignment method based on secondary multiple light mould

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] Fig. 1 shows the operation process of the present invention, as seen from Fig. 1, this face illumination alignment method based on quadratic polynomial illumination model, comprises the following steps:

[0039] (1) Normalize the shape of all training images and target images, that is, for each image, first manually take the coordinates of three feature points (the center point of the two eyes and the center point of the mouth), and rotate them so that The two eyes of each face are in a horizontal position, and then the double interpolation algorithm is used to stretch the image so that the three feature points are located at a fixed position in the image, and finally the image is cropped to the same size (see Figure 2).

[0040] (2) Training coefficient matrix A i and B i , i=2...,64. The front face in the Yale B library is trained using the least squares model ②, and the illumination component L of each image is decomposed by the LTV model (see Figure 3).

[0041] ...

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 discloses a human face illumination alignment method based on quadratic polynomial illumination model. Said method includes the following steps: (1), creating illumination model; (2), shape-normalizing all the training images and target images; (3), training coefficient matrix A; and B;, in with i=2,...., 64; (4), decomposing target human face image; (5) illumination-type estimating target human face image; (6), aligning and correcting illumination components of target human face image; and (7), reconstructing target human face image.

Description

technical field [0001] The present invention relates to a human face illumination alignment method, in particular to a human face illumination alignment method based on a quadratic polynomial illumination model. Background technique [0002] Face technology is widely used in public security systems, identity verification, virtual games, etc., but the problem of illumination is one of the main reasons that have plagued the practical application of this technology for a long time. Uneven illumination not only affects the visual effect, but also seriously affects the face recognition rate. In the past two decades, a variety of lighting processing techniques have been proposed for face technology, but most of them are not yet practical or can not meet the requirements of various applications. [0003] Terrence Chen et al. proposed an illumination processing algorithm based on the LTV model in 2006, that is, using a full variation model in the logarithm...

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): G06K9/00
Inventor 赖剑煌谢晓华郑伟诗
Owner SUN YAT SEN UNIV