Hidden Markov model based face geometrical feature identification method

A hidden Markov and geometric feature technology, applied in the field of face recognition, can solve the problems of low recognition rate, low recognition accuracy, high interdependence of matching parameters, etc., to achieve the effect of ensuring accuracy and scientificity
CN105160331AInactive Publication Date: 2015-12-16镇江锐捷信息科技有限公司
3 Cites 13 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
镇江锐捷信息科技有限公司
Publication Date
2015-12-16
Estimated Expiration
Not applicable · inactive patent

Smart Images

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

Abstract

The invention discloses a hidden Markov model based face geometrical feature identification method. The method comprises: performing graying and histogram equalization on a face image and obtaining a face frame region of a face by utilizing a classifier; setting a shrinkage coefficient of the face frame region, shrinking the face frame region, and intercepting an eye region, a nose region and a mouth region in the face frame region by utilizing the classifier; extracting and recording feature information; and comparing the obtained feature information with feature information stored in a database, to obtain the comprehensive matching rate. Comparative matching is performed by utilizing length and angle ratios of parts of the face, so that the influence caused by non-rigid and illumination conditions of the face is greatly reduced, the influence caused by change of the length and angle ratios of the parts of the face along with change of age and weight of people is avoided, and the accuracy and scientificity of matching are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of face recognition, in particular to a face geometric feature recognition method based on a hidden Markov model. Background technique

[0002] In today's society, all parties are eager to perform identity verification quickly and effectively. Because of its own stability and differences, biometric features have become the main means of identity verification. There are many related studies. Among them, face recognition is a relatively mature technology. into people's daily life. Compared with the use of retinal recognition, fingerprint recognition and other human biometrics for identity verification, face recognition technology is intuitive, friendly and convenient. It is getting more and more attention and favor, and has a wide range of application prospects.

[0003] Human facial features are very rich. In addition to shape and expression, there are also feature distributions of facial features. By studyi...

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