Image processing method, device and system, and storage medium

Abstract

Embodiments of the present invention provide an image processing method, device, system, and storage medium. The method includes: acquiring an image sequence in real time; performing face detection on each image in the image sequence in real time, acquiring a face image corresponding to each face when a face is detected, and analyzing the face of each face image Quality: among the face images belonging to the same target object, the earliest face image whose face quality meets the preset requirements is sent to the face recognition module for face recognition; the face images belonging to the target object are cached in the optimal frame queue Among them, the optimal face image with the best face quality and the face quality exceeding the earliest face image; at a predetermined time, check the image cache of the optimal frame queue, if the optimal frame queue has the optimal frame queue that belongs to a specific object. If the face image and the face of the specific object have not been recognized, the optimal face image belonging to the specific object is sent to the face recognition module for face recognition. Can effectively reduce useless calculations.

Description

Technical field [0001] The present invention relates to the field of face recognition, and more particularly relates to an image processing method, apparatus and system and a storage medium. Background technique [0002] In face recognition, image capture device may be utilized (e.g. a camera) acquired face image of a person, a face image may then be captured using face recognition. In the course of a person to appear on the screen in the camera away from the camera screen, the camera can capture many photos of this person face image, if each face image recognition module are sent to face recognition, it will be a human face recognition system enormous computational load, likely to cause the device to heat hot, computing power drop, power consumption, short life and other issues, most importantly, will increase computing useless, because once a person successfully identified do not need more repeated recognition. Inventive content [0003] The present invention is proposed in co...

AI Technical Summary

Problems solved by technology

In the process of a person appearing in the camera screen and leaving the camera screen, the camera can collect many face images of this person. If each face image is sent to the face recognition module for face recognition, it will be The recognition system brings a huge computing load, which is likely to cause problems such as overheating, reduced computing power, high power consumption, and short battery life. The most important thing is that it will increase useless computing, because once a person is successfully recognized, there is no need repeat recognition

Images