Online live broadcast method and device based on image cartoonization and electronic equipment

Abstract

The invention belongs to the field of education, and provides an online live broadcast method and device based on image cartoonization, and electronic equipment, the method is used for identifying anoriginal image in a live broadcast video stream in real time and cartoonizing a face image in the original image, and the method further comprises the steps of collecting a real face data set and a cartoon face data set, establishing a training data set; based on the generative adversarial network, establishing an initial figure cartoon head portrait generation model, and performing alternate training by using the training data set; determining a loss function according to a constraint rule, and controlling the alternate training by using the loss function to obtain a final figure cartoon headportrait generation model; and obtaining a to-be-converted original image in the current live video stream, and converting a face image in the original image into a cartoon face image by using the final cartoon head portrait generation model. According to the invention, the consistency of images before and after the figure cartoon image is generated in multiple dimensions such as color, position,edge, texture, head portrait attribute and the like can be ensured.

Description

technical field [0001] The invention belongs to the field of education, and is particularly suitable for the field of online education, and more specifically relates to an image cartoon-based online live broadcast method, device and electronic equipment. Background technique [0002] With the development of the Internet, more and more online courses have emerged, and it has become an important learning method for teachers to impart knowledge through online lectures or online classrooms. [0003] However, in some existing online education systems, there is usually an interaction process between teachers and students during the learning process of specific courses. However, in related technologies, the face and the facial features are located, and then the various organs of the face are transformed separately, and then spliced ​​together. The above method has high requirements on the stability of the detection model. For the interactive scene, the position detection also need...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the problems that the existing cartoon image generation method cannot meet the real-time generation in the live broadcast scene, and the image color consistency is poor.

Images