Image screening method and device

Abstract

The embodiments of the invention provide an image screening method and device. The method comprises the following steps of acquiring a plurality of alternative images acquired through shooting, wherein each alternative image includes a plurality of target objects; extracting the key characteristic of each target object from the alternative images, according to the extracted key characteristic, carrying out shooting quality analysis on each alternative image, and acquiring the shooting quality analysis results of the alternative images; and according to the shooting quality analysis result of each alternative image, selecting a target image from the plurality of alternative images. Through carrying out shooting quality analysis on the plurality of alternative images, the target image whoseshooting quality accords with a preset requirement is determined from the plurality of alternative images so as to increase image screening efficiency, and the time for a user to browse the alternative images one by one and select the target image is shortened. Simultaneously, a condition that the alternative image whose shooting quality does not accord with the preset requirement is taken as thetarget image due to the selection error of the user is avoided, the precision of target image selection is increased and user experience is improved.

Description

technical field [0001] The present application relates to the technical field of image recognition, in particular to an image screening method and device. Background technique [0002] At present, in the social process of users, for example, a class reunion, etc., a group photo is usually taken as a souvenir. However, the more people taking pictures, the more uncertain factors will increase. For example, in the photos taken, there may be unqualified shooting items such as sudden blinking of a participant, exaggerated expression, and sudden head tilt. In order to avoid sharing unqualified images on social platforms and affecting the user’s image, multiple images of the target object are often taken, and then the user browses the captured images one by one, and selects the Output the target image whose shooting quality meets the preset requirements. [0003] It can be seen that in the process of selecting the target image from multiple images, the user needs to browse throug...

AI Technical Summary

Problems solved by technology

[0003] It can be seen that in the process of selecting the target image from multiple images, the user needs to browse through the captured images one by one and select the target image, which not only requires the user to spend a certain amount of time for selection, but also increases the difficulty of selection. , it may also be caused by the wrong selection by the user that the image whose shooting quality does not meet the preset requirements may be shared as the target image on the social platform, resulting in a bad user experience

Images