Face microexpression recognition method

A recognition method and micro-expression technology, applied in the field of recognition graphics, can solve problems such as low recognition performance, and achieve the effect of simplifying the iterative process, reducing dimensions, and improving accuracy

CN104298981AInactive Publication Date: 2015-01-21HEBEI UNIV OF TECH
3 Cites 24 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2015-01-21
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 face microexpression recognition method and relates to a method for recognizing graphs with electronic equipment. The method comprises the steps that after a face microexpression image sequence is preprocessed, the Birnbaum-Saunders distribution curve is used for building a regression model, then the CBP-TOP algorithm is used for extracting dynamic space-time texture features of the face microexpression sequence, and finally a classier is used for training and prediction. The defect that an existing face microexpression recognition method is sensitive to small features such as bright points, edges and white noise of a face microexpression image, thereby being low in recognition performance is overcome.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The technical solution of the present invention relates to a method for recognizing graphics using electronic equipment, in particular to a method for recognizing micro-expressions on human faces. Background technique

[0002] Micro-expression is the process of human's internal emotional information processing. It cannot be forged and is not controlled by consciousness. It is an effective clue to identify lies and can be widely used in security, judicial, clinical and other fields. But microexpressions are short-lived and difficult to recognize. Even with a well-trained human, when it comes to microexpression recognition, the accuracy rate is only about 40%. Therefore, it is very necessary to develop a micro-expression recognition system and realize computer automatic recognition of micro-expressions, both for the mechanism research and practical application of micro-expressions.

[0003] At present, many teams at home and abroad are conducting micro...

Examples

Embodiment 1

[0065] The recognition method of micro-expression of human face is a recognition method of micro-expression of human face using CBP-TOP algorithm to extract the dynamic spatio-temporal texture feature of micro-expression sequence, and the specific steps are as follows:

[0066] The first step, face micro-expression image preprocessing:

[0067] Use the Adaboost algorithm to detect and crop the face in the micro-expression image, and use the bilinear difference algorithm to normalize the size of the image. After the pre-processing of the face micro-expression image, the size of the face micro-expression image is 180× 180 pixels; the result of face micro-expression image preprocessing in this step is as above figure 2 Examples are shown.

[0068] The second step is face micro-expression detection:

[0069] Use the Birnbaum-Saunders distribution curve to establish a regression model for marking the micro-expression image sequence of the human face, including the start frame Ap...