Multi-gesture and cross-age oriented face image authentication method

A technology of face image and authentication method, which is applied in the field of face image processing, and can solve the problems of recognition rate impact, impact recognition, etc.

CN102663413BInactive Publication Date: 2013-11-27中盾信安科技(江苏)有限公司
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2013-11-27
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multi-gesture and cross-age oriented face image authetication method. The method comprises the following steps of: rapidly detecting a face, performing key point positioning, performing face alignment, performing non-face area filtration, extracting the face features by blocks, performing feature dimension reduction and performing model prediction. The method provided by the invention can perform the face alignment, realize the automatic remediation for a multi-gesture face image, and improves the accuracy rate of the algorithm, furthermore, the feature extraction and dimension reduction modules provided by the invnetion have robustness for aging changes of the face, thus having high use value.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of face image processing, in particular to a multi-pose and cross-age face image authentication method. Background technique

[0002] With the continuous advancement of science and technology and the urgent need for fast and effective automatic identity verification in all aspects of society, biometric identification technology has been developed and applied rapidly in recent decades, among which face recognition technology has attracted a large number of researchers. . Face recognition technology is widely used, such as assisting the public security department in criminal investigation and solving cases, automatic identity verification by machines, video surveillance tracking and recognition, facial expression analysis and so on. At present, many countries have launched research on face recognition. Despite the rapid development of face recognition research, there are still some problems in the current face recogni...

Examples

Embodiment

[0086] This embodiment includes the following parts:

[0087] 1. Fast face detection:

[0088] The face detection part uses a fast face detection algorithm to meet the requirements of quickly and accurately finding out the face area in the target picture.

[0089] This algorithm is a learning algorithm based on Haar-like features. In order to quickly calculate the eigenvalues ​​of Haar-like features, an integral map is introduced. Only one integral map is calculated for an image, and the eigenvalue of any Haar-like feature can be quickly obtained by simple addition and subtraction using the integral map. . For a point p1(p in the image x ,p y ), the integral map of the point is defined as from the image coordinate (0, 0) to the coordinate (p x ,p y The sum of pixel values ​​in the rectangular area of ​​):

[0090] S P 1 = Σ m = ...