An image matting method and device

Abstract

The invention discloses an image matting method and device, and belongs to the field of digit image matting. The method includes: inputting an input picture to a preset full-convolution network to obtain a prediction value Fs belonging to a foreground area, a prediction value Bs belonging to a background area and a prediction value Us belonging to an unknown area of each pixel in the input image,calculating a foreground probability matrix F and a background probability matrix B corresponding to the input image according to the Fs, Bs and Us of each pixel in the input image, inputting a presetimage matting realization function into the foreground probability matrix F and background probability matrix B to perform the image matting to obtain a transparency value matrix of the input image.The image matting realization function is obtained after utilizing a first sample image which employs a preset backward propagation algorithm to perform a training, the more accuracy image matting result is obtained without performing a three-value diagram calibration to the input image for multiple times, and the automatic digital image matting is realized.

Description

technical field [0001] Embodiments of the present invention relate to the field of digital image matting, in particular to a method and device for matting images. Background technique [0002] Digital matting technology is a technology that decomposes a digital image I into a foreground image F and a background image B. The decomposition process of digital matting technology can be expressed as: [0003] I=αF+(1-α)B; [0004] Among them, α is a number between 0 and 1, which is called the transparency value or α mask (alphamatte) of the digital image. The α matrix of the digital image I is used to represent the matting result of the digital image I. When the α value is When 1 means that the pixel belongs to the foreground, when the value of α is 0, it means that the pixel belongs to the background, when the value of α is between 0 and 1, it means that the pixel belongs to the foreground and background mixed area. Since α, F, and B must be estimated simultaneously for each ...

AI Technical Summary

Problems solved by technology

[0006] Since it is difficult for the user to accurately specify the ternary image required by the closed matting algorithm, if an accurate matting result is to be obtained, the user needs to constantly recalibrate the ternary image required for the next matting according to the current matting result , the process is time-consuming and heavily relies on the user's expertise

Images