Graphcut-based switch mode image matting technology

Abstract

The invention discloses a graphcut-based switch mode image matting method. The graphcut-based switch mode image matting method includes the steps: (1) inputting an initial image to compute a covariance matrix, diagonalizing the computed covariance matrix to obtain a diagonalization matrix, judging whether the percentage of nonzero elements on diagonalization matrix diagonals accounting for the total elements exceeds a predetermined threshold or not, executing the step (2) if yes, and executing the step (3) by skipping the step (2) if no; (2), performing dimensionality reduction for the image by the aid of principal component analysis; (3) computing the probability density gradient of the image subjected to dimensionality reduction or the initial image not subjected to dimensionality reduction due to the fact the judgment result is yes by the aid of a camshift method, and clustering; (4) regarding the image processed in the step (3) as a graph, and marking energy for all classes in the graph; (5) performing graph cut according to the energy minimization principle; and (6) repeating the steps (3), (4) and (5) until the predetermined condition of convergence is satisfied to obtain matting results. The method has the advantages of high operating efficiency and accurate matting.

Description

technical field [0001] The invention belongs to the field of computer image processing, in particular to a Graphcut-based switch-type cut-out technology. Background technique [0002] Digital matting is a technology that separates the foreground part of the image from the background. It specifies a small number of foreground and background areas in the image by the user, and automatically and accurately separates all the foreground according to certain judgment rules according to these prompts. object. Cutout and image synthesis technology is an essential key technology in film and television production, and is widely used in media production. According to different original images, digital matting can be divided into blue screen matting, natural image matting, shadow matting and environment matting, etc. This patent mainly studies natural image matting with arbitrary background. [0003] The development of natural image matting has produced many different algorithms today...

AI Technical Summary

Problems solved by technology

The Knockout method is simple and fast, but it is only suitable for smooth image matting; the Ruzon-tomasi method uses statistical methods to estimate the value, but the calculation of the color estimation and α estimation of this method is very large, and its processing speed is very slow ; Chuang proposed a matting method based on the Bayesian framework - Bayesian matting method, although this method is faster, the effect is not ideal

Images