Facial Expression Recognition Method
A facial expression recognition and facial expression technology, which is applied in character and pattern recognition, instruments, calculations, etc., can solve the problem of inconspicuous extraction effect, achieve strong identification and differentiation, high expression recognition rate, and improve calculation efficiency effect
Active Publication Date: 2020-11-13
NANCHANG HANGKONG UNIVERSITY
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem to be solved by the present invention is to adopt the method of multi-feature fusion and then data dimensionality reduction for the situation where the effect of single feature extraction is not obvious, to fuse effective identification information of multiple features, to realize effective compression of information, and to improve calculation efficiency
Method used
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
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0032] figure 1 It is an algorithm flow chart of expression recognition method based on MB-LBP unified mode histogram and HOG feature fusion, mainly including:
[0033] 1. The facial expression image is geometrically corrected, and the size normalization preprocessing is used to normalize the facial expression image into a 64×64 image;
[0034] 2. Perform MB-LBP unified mode histogram feature extraction on the normalized facial expression image.
[0035] (1) In the normalized Jaffe Japanese female expression library (such as figure 2 shown), the expression images are divided into six categories, which are anger (AN), disgust (DI), fear (FE), happiness (HA), sadness (SA) and surprise (SU). Among them, there are 31 images of angry expressions, 29 images of disgusted expressions, 32 images of scared expressions, 31 images o...
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
Login to View More Abstract
The invention discloses a facial expression recognition method, which uses a multi-scale parameter MB‑LBP operator to extract texture features of facial expression images, and performs pixel histogram statistics in a unified mode; performs HOG feature extraction on human face image samples ;Concatenation feature fusion of MB‑LBP features and HOG features in the same mode; in the fused feature space, randomly extract training samples, and use the remaining samples as test samples; use training samples to perform PCA dimension reduction calculations to obtain projection matrices W, the training sample is projected into the low-dimensional subspace to obtain the feature representation of the expression image in the low-dimensional subspace; the test sample is projected into the low-dimensional subspace through the projection matrix W, and the sparse representation classifier is used to classify the features of the test sample. Classification, to obtain the category to which the test sample belongs. Expression features with texture and shape information are expressed in a lower dimension, which achieves a higher expression recognition rate and higher recognition accuracy.
Description
technical field [0001] The invention belongs to image classification technology, in particular to a facial expression recognition method based on the fusion of MB-LBP unified mode histogram and HOG feature. Background technique [0002] Expression is one of the important ways to convey emotion in interpersonal communication. Facial expression recognition refers to the use of computer to extract facial expression features from detected faces, so that the computer can understand and process human facial expressions according to human thinking and understanding. , and can respond according to people's needs, and establish a friendly and intelligent human-computer interaction environment. This research is a hotspot at the forefront of interdisciplinary research in image processing, pattern recognition, psychology, affective computing, and computer vision. [0003] Facial expression recognition is mainly composed of three parts: face detection, expression feature extraction and ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
Inventor 王艳黎明张君
Owner NANCHANG HANGKONG UNIVERSITY