Portrait generation method, device and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a portrait generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a portrait generation requestof a user side, and the portrait generation request comprises a target portrait condition and a random number seed; extracting the random number seed in the portrait generation request, and inputtingthe random number seed into a random number generator, so that the random number generator generates corresponding random noise according to the random number seed; according to the target portrait condition, matching a corresponding portrait generation model, inputting the random noise into the corresponding portrait generation model to generate a target portrait, wherein the portrait generationmodel is a pre-trained portrait generation model; and sending the target portrait to the user side. According to the invention, a large amount of portrait data can be obtained without collecting portraits on a large scale, so that the portrait data obtaining efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, and in particular to a portrait generation method, device, system, electronic equipment and storage medium. Background technique [0002] With the gradual deepening of research on face recognition technology and the landing and deployment of face recognition products in various fields, in the process of researching face recognition technology, when developing, testing, and displaying products based on face recognition, the accuracy of face images Demand is growing. The existing face data is obtained by collecting face images through cameras deployed in various scenes and entering them into the database. However, due to the limited range of camera deployment and the limited field of view captured, the collected data is not Comprehensive, the difficulty of data collection, and the accompanying legal and privacy risks make it difficult to obtain large-scale face image data, which in...

AI Technical Summary

Problems solved by technology

The existing face data is obtained by collecting face images through cameras deployed in various scenes and entering them into the database. However, due to the limited range of camera deployment and the limited field of view captured, the collected data is not Comprehensive, the difficulty of data collection, and the accompanying legal and privacy risks make it difficult to obtain large-scale face image data, which in turn affects the research and development based on large-scale face image data , testing, and demonstration activities are carried out smoothly

Therefore, the acquisition efficiency of existing face image data is not high

Images