Lip characteristic and deep learning based smiling face recognition method

Abstract

The invention discloses a lip feature and deep learning based smiling face recognition method, which comprises the steps of firstly tailoring on a positive sample image containing a smiling face and a negative sample image without a smiling face so as to acquire lip image training samples, carrying out feature extraction on all lip image training samples respectively so as to acquire feature vectors corresponding to each training sample, and training a deep neural network by adopting the feature vectors of the training samples; as for an image to be recognized, acquiring a lip feature vector of a human face in the image to be recognized by adopting the same method, inputting the lip feature vector into the well trained deep neural network so as to carry out recognition, and acquiring a recognition result on whether the human face is a smiling face or not. The smiling face recognition method disclosed by the invention improves the smiling face recognition accuracy under complicated conditions by combining lip features and feature learning capacity of the deep neural network; and influences of non-Gaussian noises are suppressed through improving an overall cost function in training of the deep neural network, and the recognition accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically, relates to a smiley face recognition method based on lip features and deep learning. Background technique [0002] Facial Expression Recognition (FER), as an important part of human-computer interaction and affective computing, has attracted more and more researchers' attention. Smiley face expression is an important expression in human face, and its effective recognition can promote the development of expression recognition to a certain extent. [0003] So far, there is very little research on smiley face recognition. In 2010, Shenzhen Huawei Communication Technology Co., Ltd. applied for a patent for smile detection. Its principle is mainly to judge whether a smile is detected by the motion information of the mouth in the obtained face video. South China University of Technology conducted research on smile recognition and invented a patent for smile recognition....

AI Technical Summary

Problems solved by technology

[0004] To sum up, the traditional smiley face recognition mainly adopts the traditional feature extraction method. At the same time, it mainly conducts experiments on the facial expression database shot under specific conditions. Once the scene is transformed into a real situation, it does not have good robustness and reliability. Practicality

Images