Handwritten letter recognizing method and system based on WiFi

Abstract

The invention discloses a handwritten letter recognizing method and system based on WiFi. The method includes the following steps of A1, collecting WiFi signals for reflecting environment state changes through a data collecting module when a user writes handwritten letters between an AP and an STP; A2, extracting channel state information from the WiFi signals; A3, conducting phase unwinding and phase correcting operations on the channel state information; A4, inputting data into a convolutional neural network, wherein the convolutional neural network comprises an input layer, an Inception module, a depth connecting layer, a batch standardization layer, a ReLU layer, an average pooling layer, a dropout layer, a full-connection layer, a softmax layer and a classification layer, and the network is trained through a momentum gradient descending method; A5, applying a trained convolutional neural network model to handwritten letter recognizing. The limitation that a wearable device needs to be carried during traditional action recognition and the risk of privacy leakage are overcome. Action recognition is conducted by means of the improved convolutional neural network, and the recognizing precision is improved.

Description

technical field [0001] The invention belongs to the technical field of intelligent perception and human-computer interaction, and in particular relates to a recognition technology based on small-scale actions, which combines wireless channel state information to perceive environmental changes and multi-scale characteristics of convolutional neural networks to realize WiFi-based handwriting letter recognition. Background technique [0002] In recent years, action recognition technology has become more and more mature, and small-scale action recognition has attracted extensive attention from researchers because of its small and difficult to recognize action range. Among them, computer vision-based methods mainly capture images or videos through cameras, and apply image processing methods to identify types of actions. This type of technology is limited by sight distance and light intensity, cannot operate in dark scenes, and there is a risk of privacy leakage. The sensor-based...

AI Technical Summary

Problems solved by technology

Among them, the method based on computer vision mainly captures images or videos through the camera, and uses image processing methods to identify the types of actions. This type of technology is limited by the viewing distance and light intensity, cannot operate in dark scenes, and there is a risk of privacy leakage.

The sensor-based method uses the user to carry sensors such as accelerometers, gyroscopes, etc. to collect action information and extract information features for action recognition. This method requires users to wear sensor equipment, which is inconvenient to use and is not conducive to widespread promotion.

The action recognition method based on radio frequency technology uses special hardware equipment to obtain fine-grained radio frequency signals to perceive human actions. This method has high recognition accuracy, but the technical overhead is large, which is not conducive to widespread deployment.

Images