Face fuzzy processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a face blurring processing method and device, electronic equipment and a storage medium. The method comprises the steps: carrying out the face detection of a target image through a preset first convolutional neural network, and extracting an image of an area where a face is located in the target image when the face is detected, and obtaining a first face image; inputting the first face image into a preset second convolutional neural network to segment the target face image to obtain a second face image, the second face image comprising at least one feature region; and performing fuzzy processing on the feature region to obtain a fuzzy face image. The human face is detected through the first convolutional neural network, the human face does not need to be marked manually, the feature regions of the human face are segmented through the second convolutional neural network, accurate segmentation boundaries are obtained, the segmentation boundaries of the feature regions serve as fuzzy boundaries, and the fuzzy accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a face blurring processing method, device, electronic equipment and storage medium. Background technique [0002] Artificial intelligence is widely used in the field of security, by deploying cameras in various demand scenes for video surveillance of the demand scene. In some video surveillance scenarios, human face images will be captured. For privacy protection or other purposes, it is necessary to blur the captured human face so that some observers without authorization cannot identify who is captured. , so as to protect the privacy of the person being photographed. The traditional blurring process needs to manually mark the face or perform the blurring process in a larger range after the face is detected, which is not accurate enough, which makes it easy to blur other features in the image, and the observer cannot Identify other features that should ...

AI Technical Summary

Problems solved by technology

The traditional blurring process needs to manually mark the face or perform the blurring process in a larger range after the face is detected, which is not accurate enough, which makes it easy to blur other features in the image, and the observer cannot Identify other features that should be blurred out

Therefore, the existing face blurring processing has the problem of low accuracy

Images