Method for regulating human face image illumination based on multilevel wavelet disintegrating and spline interpolation

A face image and spline interpolation technology, applied in the field of image processing, can solve the problems of large collection and limit the application of real-time face recognition system, achieve the effect of effective lighting conditions and reduce the impact of performance deterioration

Inactive Publication Date: 2008-06-18
CHONGQING UNIV +1
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this type of method can achieve good results, it needs to collect a large number of face image samples under different lighting conditions and the calculation is time-consuming, which limits its application in real-time face recognition systems.
The second type of method is to extract face features that are not sensitive to illumination changes, but how to obtain face features that are not sensitive to illumination is the difficulty of this type of 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
  • Method for regulating human face image illumination based on multilevel wavelet disintegrating and spline interpolation
  • Method for regulating human face image illumination based on multilevel wavelet disintegrating and spline interpolation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0025] Fig. 1 is a block flow diagram of the method of the present invention. A known face image of size M×N affected by illumination can be expressed as:

[0026] G'(m,n)=F(m,n)□G(m,n)+B(m,n) (m=1,...,M,n=1,...N)

[0027] Among them, F(m, n) and B(m, n) represent the gain noise and background noise mixed in due to illumination changes, respectively, and G(m, n) represents the face image under normal illumination. The illumination adjustment of the known image according to the method of the present invention is carried out according to the following steps:

[0028] (1) Perform multi-level wavelet transform on the input known face image G′(m, n) to estimate the background noise image A at low resolution J

[0029] As shown in Figure 2, it is a schematic diagram of image multilevel wavelet decomposition. A first-level wavelet decomposition of the fac...

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 relates to an adjustment method of light on human face, based on multi-level wavelet decomposition and spline interpolation, pertaining to the technical field of image processing. Illumination variations can add into an image with two noises that are background noise and gain noise. The invention, by taking advantages of direct decomposition multi-level wavelet and spline interpolation, estimates and removes the background noise and the gain noise; the background noise belongs to additive noise, which is estimated and removed through the direct multi-level wavelet decomposition and the spline interpolation; while, the gain noise pertains to multiplicative noise; through logarithmic transformation of the imagines removed background noise and by taking advantage of the decomposition multi-level wavelet and the spline interpolation, the gain noise is removed. The invention has the advantages that the invention can quickly and effectively estimate picture illumination situation, remove the background noise and gain noise introduced by illumination as much as possible, and effectively adjust human face image under different illumination conditions. The method of the invention can be applied to real-time human face identification system under illumination variations and can reduce the influence of human face identification system performance caused by illumination variations.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a face image illumination adjustment method based on multilevel wavelet decomposition and spline interpolation. The method can be directly applied to a real-time face recognition system under illumination changing conditions. Background technique [0002] As a non-contact and friendly biometric identification method, face recognition has great application potential in user authentication in confidential places, security monitoring in banks and residential quarters, public security criminal investigation, human-computer interaction and other fields. But it is precisely because of the non-contact feature of face recognition that the face image of the same person is extremely vulnerable to the influence of the surrounding environment, especially the influence of lighting changes. Studies have shown that the change of face image due to the influence of illumination is even gre...

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): G06K9/40G06K9/00
Inventor 龚卫国辜小花李伟红杨利平李正浩刘燕飞
Owner CHONGQING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap