Sign language recognition method and device based on neural network model, equipment and medium

Abstract

The embodiment of the invention relates to the field of artificial intelligence, and discloses a sign language recognition method and device based on a neural network model, equipment and a medium. The method comprises the following steps of: obtaining to-be-recognized sign language information input by a user and collected by a shooting device, the sign language information comprising conversion mode sign language information and the to-be-recognized sign language information; inputting the sign language information into a pre-trained sign language recognition model to obtain first sign language semantic text information corresponding to the conversion mode sign language information and second sign language semantic text information corresponding to the to-be-recognized sign language information; determining a target language mode corresponding to the conversion mode sign language information according to the first sign language semantic text information; and converting the second sign language semantic text information into one or more of voice, characters and sign languages corresponding to the target language mode. Efficient and intelligent sign language recognition is achieved, and the sign language recognition flexibility is improved. The invention relates to a block chain technology, for example, sign language information can be written into a block chain so as to be used for scenes such as data evidence obtaining.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a sign language recognition method, device, equipment and medium based on a neural network model. Background technique [0002] At present, there are various applications (apps) for sign language recognition on the market, but the audience of these apps should be those who need to use sign language, need to understand sign language, or are only interested in sign language. In some scenes of life, users who do not understand sign language also need to communicate with people who can only express through sign language in real time, and this is a high probability event. However, because different users are proficient in different languages ​​or language methods, the sign language translated by the existing sign language recognition app does not necessarily meet the language needs of some users, that is to say, it may not be understood or read by some users. Understand...

AI Technical Summary

Problems solved by technology

However, because different users are proficient in different languages ​​or language methods, the sign language translated by the existing sign language recognition app does not necessarily meet the language needs of some users, that is to say, it may not be understood or read by some users. Understand the languages ​​of existing app translations

For example, assume that a user who does not understand sign language only understands French, and an app about sign language recognition translates the sign language user's sign language into Chinese, so that the user who does not understand sign language does not understand the content translated by the app, and does not understand the sign language of the other party. what causes ineffective communication

Images