Identity recognition system, client, server and method

Abstract

The embodiment of the invention discloses an identity recognition system, a client, a server and a method. The client comprises an image collection module used for obtaining a to-be-used image; a feature extraction module used for performing image feature extraction on the to-be-utilized image by utilizing a feature extraction model locally stored in the client to determine features of the to-be-utilized image; a determining module used for determining a speculated identity label corresponding to the image feature to be utilized by utilizing the image feature to be utilized and the establishedlabel corresponding relationship; an obtaining module used for obtaining a calibration identity label corresponding to the to-be-utilized image feature; a first sending module used for sending the to-be-utilized image features, the speculated identity label and the calibrated identity label to the server as training data; and an updating module used for replacing and updating the feature extraction model locally stored in the client according to the feature extraction model sent by the server so as to protect the privacy of the personnel to a certain extent and reduce the risk of leaking theprivacy of the personnel.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to an identity recognition system, a client, a server and a method. Background technique [0002] With the advancement of technology, image-based face recognition has been widely used in fields such as human identification, finance and security systems. [0003] By investigating the theory and product status of identity recognition technology, we can find that the image-based identity recognition model in the prior art often needs to send the user's original image data to the device on the service side for identity training and inference. Processing, for example, using image sensors to collect various sample image data including human faces and / or human bodies, and then uploading the sample image data to terminal devices, servers or cloud platforms that provide services to users for neural network models for identity authentication training, and then solidify the ...

AI Technical Summary

Problems solved by technology

[0004] The above method has the following problems: the terminal device, server or cloud platform on the side that provides services to users receives a large amount of sample image data containing faces and / or human bodies, which may easily cause user privacy leakage and bring psychological burden to users; and users Only a certain model trained at the factory can be used, which cannot fully meet the changes of usage scenarios and target objects. If you try to adapt to all possible scenarios and objects, you will need a large number of samples, and the neural network training time for the entire product before leaving the factory will be greatly reduced. increase, and the cost is higher

Images