Face area image archiving method, device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a face area image archiving method, a face area image archiving device, electronic equipment and a storage medium. The method comprises the steps of acquiringa to-be-archived image containing at least one face; performing face detection on the to-be-archived image to obtain at least one face region image; performing face recognition on each face region image to obtain face features corresponding to each face region image; based on the face features corresponding to each face area image, respectively calculating the similarity between the face area image and each file in a pre-stored file set, wherein the archive set comprises at least one archive, and each archive comprises at least one face area image based on the same person; and putting each face region image into a file which is most similar to the face region image. Since the similarity of the human face features can represent the similarity of the human face, the human face archiving is carried out by calculating the similarity of the human face features. The calculation complexity of calculating the similarity can be reduced, and the time overhead in the archiving process is reduced.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device, electronic equipment and storage medium for archiving images of human face regions. Background technique [0002] In recent years, monitoring equipment has been widely used in shopping malls, parking lots, transportation, logistics and other occasions. These monitoring equipment are generating image data such as vehicle images and face area images all the time. In order to effectively utilize these image data, it is necessary to classify and archive these image data, and it will be a huge task to rely on manpower to process these huge information. [0003] In order to effectively archive and process images of human face regions, a face recognition algorithm has been proposed in the prior art. Similarity, when the similarity is greater than a preset threshold, it is considered that the collected face area image is similar to the face area image ...

AI Technical Summary

Problems solved by technology

The face area is only a part of the image that contains the face. If the similarity between the image that contains the face and the image that contains the face in the preset face database is calculated, the complexity of calculation will inevitably be increased. thus increasing the time overhead in the archiving process

Images