The Graph Cut Energy Image Matting Model Based on Dynamic Weight Parameter

Abstract

The traditional graph cut algorithm for complex image matting accuracy is not high, the weight parameters in the dynamic graph cut energy model is based on image matting. The degree of similarity the algorithm uses Gauss model to calculate the foreground color and background color, in graph cut energy model of dynamic weight parameters are added, by it and then many corrections to the image matting. The experimental results show that the algorithm is easy to operate, that can improve the accuracy of image matting.