Neural network real-time sign language translation system equipment

Abstract

Neural network real-time sign language translation system equipment belongs to the technical field of sign language translation. The equipment can translate sign language actions made by a device user into written characters in real time and display the written characters on a mobile phone APP, and is used for helping deaf-mutes to reduce the difficulty of communication with people. The equipment comprises a main control module, a gesture module, a communication module and a terminal module. The main control module is used for collecting signals from the gesture module, and the signals are transmitted to the terminal module through the communication module after the signals are processed by a neural network sign language recognition algorithm. The gesture module is used for collecting sign language action data of the device user, is composed of a bending sensor for collecting data when fingers bend and an MPU6050 chip module for detecting the orientation of a palm, and is connected with the main control module through a connecting circuit. The communication module adopts an HC-05 Bluetooth module working in a half-duplex mode, is connected with an I / O port of the main control module through a UART interface and serves as a data transmission channel. The terminal module adopts the form of a mobile phone App with a Bluetooth function, receives the signalS processed by the main control module through the communication module, and obtains a final recognition translation result which is displayed on a mobile phone screen in the form of written characters.

Description

technical field [0001] The patent of the invention belongs to the technical field of sign language translation, and in particular relates to a neural network real-time sign language translation system equipment. Background technique [0002] According to statistics in recent years, there are more than 20 million people with hearing impairment in my country, and this number has expanded to about 70 million people in the world. Insufficiencies and challenges. Researchers have studied the potential development space of input sensors such as data gloves or special cameras. Although the former performs well in recognition, it is difficult to be widely used because it is difficult to wear and too expensive. While webcams or stereo cameras can guarantee the accuracy and speed of tracking hand movements, it is difficult to handle complex backgrounds and lighting. Contents of the invention [0003] The present invention provides a neural network real-time sign language translation ...

AI Technical Summary

Problems solved by technology

[0002] According to statistics in recent years, there are more than 20 million people with hearing impairment in my country, and this number has expanded to about 70 million people in the world. Inadequacies and challenges. Researchers have studied the potential development space of input sensors such as data gloves or special cameras. Although the former performs well in recognition, it is difficult to put into widespread use because it is difficult to wear and too expensive.

While webcams or stereo cameras can guarantee the accuracy and speed of tracking hand movements, it is difficult to deal with complex backgrounds and lighting.

Images