Lip language recognition method and device, storage medium and mobile terminal

Abstract

An embodiment of the invention discloses a lip language recognition method and device, a storage medium and a mobile terminal. The method comprises the steps as follows: when detecting that a lip language recognition event is triggered, acquiring at least one 3D lip image of a current user through a 3D camera; inputting the at least one 3D lip image into a pre-trained lip language recognition model; determining lip language information corresponding to the 3D lip image according to an output result of the lip language recognition model; providing the lip language information for the current user. With the adoption of the technical scheme, simple and rapid lip language recognition can be performed on 3D lip images through the pre-constructed lip language recognition model, the lip languagerecognition accuracy is further improved, the human-machine interaction experience of the user is effectively improved, and the demand of the user is better met.

Description

technical field [0001] The embodiments of the present application relate to the field of information processing technologies, and in particular to lip recognition methods, devices, storage media and mobile terminals. Background technique [0002] With the rapid development of electronic technology and the improvement of people's living standards, terminals such as smart phones and tablet computers have become an indispensable part of people's lives. At the same time, it is becoming more and more important to perform human-computer interaction (Human-Computer Interaction, HCI) with terminal equipment more humanely. [0003] However, at present, most terminal devices rely on keyboard input, handwriting input, and voice input to perform human-computer interaction, which is not convenient in many cases and cannot well reduce the interference of the external environment on users. For example, if voice input is performed in a relatively noisy environment, the voice recognition ac...

AI Technical Summary

Problems solved by technology

[0003] However, at present, most terminal devices rely on keyboard input, handwriting input, and voice input to perform human-computer interaction, which is not convenient in many cases and cannot well reduce the interference of the external environment on users.

For example, if voice input is performed in a noisy environment, the voice recognition accuracy is low, the effect is poor, and the user's privacy is easily leaked

Images