An image matting method and system

Abstract

The invention provides an image matting method and system. The image matting method comprises the steps of 1, training an image matting model by using an image training set; wherein samples in the image training set comprise an original image, and a tripartite graph, a gold standard mask and a gold standard combined mask which correspond to the original image; wherein the image matting model comprises a depth feature extraction module which is used for learning semantic features and detail information features of an original image; The similarity learning module is used for fusing the semanticfeatures and the detail information features to obtain a similarity relation of the pixel points; The mask propagation module is used for obtaining a mask value of each pixel point through a propagation algorithm according to the similarity relation between the trisection image and the pixel points, and outputting an alpha mask image corresponding to the original image; and 2, inputting the original image to be subjected to image matting and the corresponding tripartite image into the trained image matting model, and outputting an alpha mask image corresponding to the original image to be subjected to image matting.

Description

technical field [0001] The disclosure belongs to the field of digital image processing, and in particular relates to an image matting method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Cutout technology refers to a technology that extracts foreground objects of any shape from the original image. It is an indispensable technical means in modern film and television production and is widely used in magazine design, graphic art, advertising, film and television post-production and other fields. Image matting technology is to separate a certain part of an image or video from the original image or video, and has become a key technology in the production of visual effects. Generally speaking, the extraction and synthesis of the foreground and background of natural images has become more urgent with the development of application...

AI Technical Summary

Problems solved by technology

Such as sampling-based methods, propagation-based methods, and matting methods that combine sampling and propagation. These methods rely on artificially designed simple features, such as color and other information. The accuracy of this type of method is limited by assumptions. , when applying such methods to actual natural image matting, there are often certain limitations, and the practicability is not high; as deep learning technology has become popular in various fields in recent years, some image matting technologies based on deep learning network models have emerged. Such methods usually directly solve the mask pixel by pixel. As the image size increases, the computational complexity and parameter complexity increase exponentially.

On the other hand, when the foreground and background of the matting image have similar tones, it is difficult for the existing matting technology to accurately distinguish whether the pixels of similar tones belong to the foreground or the background

Images