Mouth angle coordinate average value change-based smiling face recognition method

Abstract

The invention discloses a mouth angle coordinate average value change-based smiling face recognition method. The method comprises the following steps of: (1) face detection; (2) HOG feature extraction; (3) Gabor feature extraction; (4) a support vector machine; (5) a mouth angle coordinate method; according to the method, firstly, a Shi & Tomasi corner detection algorithm is adopted to carry out corner detection on the mouth, and then smiling face recognition is carried out through a method of calculating the coordinate average value of the mouth. Experimental results show that the correct rate of smiling face recognition based on the mouth angle coordinate method is 92% and is higher than that of a Gabor and HOG feature extraction method.

Description

Technical field: [0001] The invention relates to a smiling face recognition method based on the change of the average value of mouth corner coordinates. Background technique [0002] Facial expression is formed by the movement of facial muscles and is the observable expression of emotional changes on the face. Changes in facial expressions can reveal people's psychological activities and adjust people's social behavior. With the rise of the service robot industry, pattern recognition has gradually entered the public's field of vision, and people's research on expressions has gradually increased. Among them, smile recognition technology is widely used in smart devices such as robot vision and digital cameras. [0003] In recent years, researchers have proposed a variety of methods for smile detection. For example, Shenzhen Huawei Technology Co., Ltd. has obtained the patent right for the invention of smile detection. The principle is to judge whether a smile is detected bas...

AI Technical Summary

Problems solved by technology

[0003] In recent years, researchers have proposed a variety of methods for smile detection. For example, Shenzhen Huawei Technology Co., Ltd. has obtained the patent right for the invention of smile detection. The principle is to judge whether a smile is detected based on the movement information of the mouth in the acquired face video. ; South China University of Technology has obtained the patent authorization for the invention of smile recognition for its research on smile recognition. The patent mainly uses the gradient histogram feature (Histogram of Gradient, HOG) to classify smiles, and divides face pictures into two categories: smiling and non-smiling; He Cong used a high-level simulated biological vision method to realize the recognition and classification of smiling faces. This method is mainly based on bio-inspired features for feature extraction and classification of smiling faces; Chen Jun studied smiley face recognition in real environments based on bio-inspired features , Constructed a smiley face classification system that conforms to the human recognition mechanism; Guo Lihua et al. used PHOG features and clustering feature selection for smiley face recognition; Yan Xinping combined LBP features and HOG features for smiley face recognition research, but the results were not ideal

Images