Video figure dressing method and device, computing device and computer memory medium

Abstract

The invention discloses a video figure dressing method and device, a computing device and a computer memory medium. The method comprises the steps of obtaining a current frame image comprising a specific object in a video in real time; carrying out scene segmentation processing on the current frame image, thereby obtaining a foreground image for the specific object and a to-be-dressed face area image of the specific object; drawing a beauty makeup effect chartlet corresponding to the to-be-dressed face area image; fusing the beauty makeup effect chartlet and the foreground image to obtain a frame processing image; covering the current frame image by the frame processing image to obtain processed video data; and displaying the processed video data. According to the method, the device, the computing device and the computer memory medium, through adoption of a deep learning method, the scene segmentation processing is finished high efficiently and high accurately; a beauty makeup effect can be added to a face area of the figure in the video precisely and rapidly; the video data processing efficiency is improved; a video data processing mode is optimized; and a video data display effect is beautified.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a video character dressing method, device, computing equipment and computer storage medium. Background technique [0002] With the development of science and technology, the technology of image acquisition equipment is also improving day by day. The collected images are clearer, the resolution, and the display effect are also greatly improved. However, the existing recorded video is only a monotonous recording material itself, which may not meet the needs of the user. The user wishes to personalize the video. For example, the user wants to add a beautification effect to the facial area of ​​the person in the video. In the prior art, most of the frame images of the video are processed by adaptive blurring, so that the characters in it have a beautifying effect, but the display effect of the video obtained after this processing is not good, and the video is not enough. S...

AI Technical Summary

Problems solved by technology

However, the existing recorded videos are only monotonous recording materials themselves, which may not meet the needs of users. Users want to personalize the videos. For example, users want to add beautification effects to the facial areas of people in the videos.

In the prior art, most of the frame images of the video are processed by adaptive blurring, so that the characters in it have a beautifying effect, but the display effect of the video obtained after this processing is not good, and the video is not enough. Sharp, bokeh, lack of realism

Images