Face image recognition method, device and equipment based on fuzzy theory

A face image and fuzzy theory technology, applied in the field of biometrics, can solve problems such as slow recognition speed
CN110348386AActive Publication Date: 2019-10-18GUANGDONG UNIV OF TECH

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
GUANGDONG UNIV OF TECH
Publication Date
2019-10-18

Smart Images

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

Abstract

The invention discloses a face image recognition method based on a fuzzy theory, and the method comprises the steps: obtaining training face images with different identity labels, and carrying out thesegmentation of the training face images to obtain training sub-images; calculating a similar distance and a heterogeneous distance between each training sub-image and the training face image, and constructing a fuzzy membership matrix by using the similar distance and the heterogeneous distance; obtaining a to-be-recognized image, segmenting the to-be-recognized image to obtain to-be-recognizedsub-images, and obtaining neighbor sub-images of the to-be-recognized sub-images; obtaining subimage class membership of the to-be-identified subimage by using the fuzzy membership matrix and the neighbor subimage, and determining the identity of the to-be-identified subimage by using the subimage class membership. According to the method, the robustness of a face recognition algorithm is improved, so that the recognition speed is increased, and the problem of low recognition speed in the prior art is solved. The invention also provides a face image recognition device and equipment based on the fuzzy theory, and a computer readable storage medium, which also have the above beneficial effects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The present invention relates to the technical field of biological recognition, and in particular to a method, device, equipment and computer-readable storage medium for facial image recognition based on fuzzy theory. Background technique

[0002] In recent years, the rapid development of biometric technology, face recognition, fingerprint unlocking, voice wake-up and other technologies have been applied in many fields. Among them, face recognition has the characteristics of no contact and good concealment, which makes the face recognition technology more widely used.

[0003] The existing face recognition technology needs to collect in advance training face images with different identification tags (face images of different people are face images with different labels), and after preprocessing the training images, use principal component analysis ( Principal components analysis (PCA), linear discriminant analysis (LDA), Histogram of oriented gradient (HOG) ...

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