Intelligent facial expression recognition method and system based on face attribute analysis

A technology of facial expression recognition and facial expression, which is applied in the field of facial expression recognition, can solve the problem of not taking into account the changes in attributes such as gender and age of the face, and achieve good implementability

A technology of facial expression recognition and facial expression, which is applied in the field of facial expression recognition, can solve the problem of not taking into account the changes in attributes such as gender and age of the face, and achieve good implementability

CN111523367AActive Publication Date: 2020-08-11HUBEI UNIV OF SCI & TECH

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent facial expression recognition method and system based on face attribute analysis
  • Intelligent facial expression recognition method and system based on face attribute analysis
  • Intelligent facial expression recognition method and system based on face attribute analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Below in conjunction with specific embodiment, the present invention will be further described:

[0058] In order to make the purpose, technical solutions and advantages of the present invention clearer and clearer, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0059] Among them, the facial expression recognition method is:

[0060] (1) Facial expression recognition model training. The training set S is divided into N subsets according to the face attribute categories, and each subset is used for training to generate a set of conditional random forests for facial expression classification.

[0061] (2) Facial expression recognition. First, using the face attribute random forest T A Attribute estimation on test face images. Then, accordi...

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 provides a face expression recognition method and a face expression recognition system under face attribute constraints. The face expression recognition method comprises the following steps of: (1) training a face expression recognition model, wherein training set is divided into subsets according to face attribute categories, and each subset is subjected to training to generate a set of conditional random forests for face expression classification; and (2) carrying out face expression recognition, which is implemented by: firstly, performing attribute estimation on a test face image by using a face attribute random forest; secondly, randomly selecting a corresponding number of decision trees from a conditional random forest to dynamically construct a facial expression recognition random forest according to an attribute estimation result; and finally, performing facial expression classification recognition according to the constructed facial expression recognition randomforest. The face expression recognition method and the face expression recognition system eliminate the influence of attribute change factors such as the gender and the age of the human face on humanface expression recognition, and solve the problem of interference of factors such as different genders and ages in human face expression recognition through adopting the provided attribute constraintrandom forest human face expression recognition method.

Description

technical field [0001] The invention belongs to the field of image processing and pattern recognition, and in particular relates to a technical method and system for facial expression recognition. Background technique [0002] Facial expression recognition, like face recognition, is a hot research field with a wide range of application scenarios. For example, it can be applied to safe driving, health care, video conferencing, virtual reality and cognitive science. As early as in the twentieth century, Ekman and Friesen designed six basic emotions (anger, disgust, fear, happiness, sadness and surprise) based on cross-cultural and cross-regional research. They pointed out that humans with different cultural backgrounds have the same basic emotional expressions . However, recent advanced research in neuroscience and psychology has shown that the six basic human emotional expressions are related to specific cultural backgrounds and are not universal. At the same time, the inv...

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
11 Aug 2020
Publication
CN111523367A
IPC
G06K9/00; G06K9/62; G06N3/04; G06N3/08
CPC
G06N3/08; G06V40/171; G06V40/174; G06V40/172; G06N3/045; G06F18/24323
Inventors
廖海斌; 徐斌