-
公开(公告)号:US20210397873A1
公开(公告)日:2021-12-23
申请号:US17241191
申请日:2021-04-27
Inventor: Yuexiang HU , Renyi ZHOU , Junyu HAN
Abstract: An image processing method, an electronic device and a readable storage medium, which relate to the technical field of computer vision, are disclosed. In an embodiment, a face recognition module and a service processing module maintains respectively an image buffer queue; the face recognition module maintains a face image buffer queue of face images, and the service processing module maintains a background image buffer queue of background images, i.e., first images; since the face recognition module only maintains the face image buffer queue, only a determined optimal face image, i.e., a face image to be matched, is transmitted to the service processing module, and then, the service processing module determines a background image matched with the optimal face image transmitted by the face recognition module from the maintained background image buffer queue, thus performing image recognition and image matching on a face appearing in a video source.