Mouth opening/closing state detection method based on deep learning

Abstract

The invention discloses a mouth opening / closing state detection method based on deep learning. The method mainly comprises a data preprocessing portion, a feature extraction portion, a feature classification portion and an error calculation portion. The method is mainly characterized by, through full utilization of the capability in extracting high-level features of a depth convolution nerve network, extracting robust features capable of coping with irregular noise, larger illumination change and the cases of hostile attack and the like by sheltering the mouth key part, which occur frequently in the practical application scene; carrying out classification on the extracted features by utilizing a full connection layer; and adjusting parameters through error calculation and through a stochastic gradient descent method to reduce errors, and allowing the detection method to be able to have a capability of identifying mouth opening / closing state automatically. Besides, the method can ensure both the required computing resources and storage space do not generate great fluctuation due to change of resolution of an image to be detected. The method is convenient to operate, simple and easy to use, higher in precision and safer and more reliable.

Description

Technical field [0001] The present invention belongs to the technical fields of image processing, pattern recognition, software engineering, etc., and in particular relates to a method for detecting the open and closed state of the mouth based on deep learning, and has the advantages of common in reality scenes where there is interference of light changes and partial occlusion of key parts of the face Very adaptable. Background technique [0002] The face is the most important appearance feature of a person, and face recognition technology has a wide range of applications in current popular application fields such as identity authentication and security protection, and has a very broad prospect. However, human faces are easily copied using photos, videos, etc., so the impersonation of the faces of legitimate users is an important threat to the security of the face recognition and authentication system. Therefore, an indispensable part of the existing face recognition system is t...

AI Technical Summary

Problems solved by technology

[0003] In order to ensure the accuracy of detection, the face recognition system needs to have strong robustness to various disturbances in real life scenes. The robustness of scenes with illumination changes, pose changes, partial occlusions, and random noise still needs to be further improved to meet practical applications.

[0004] Since the traditional living body detection method cannot meet the demand for high-precision real-time living body detection in practical applications, the present invention proposes a high-precision mouth opening and closing state detection method that can be applied to interactive living body detection

Images