Interactive graph cutting method

Abstract

The invention discloses an interactive graph cutting method. The interactive graph cutting method is used for solving the problems that an existing interactive graph cutting method is low in operating efficiency, and the workload of a user is high. The interactive graph cutting method comprises the following steps that (1) the user inputs a graph, and a rectangular region containing a foreground target graph is selected through a rectangular frame in a frame mode; (2) the outer boundary of the rectangular region is extracted through the Canny edge detection algorithm; (3) a ternary graph is initialized through the outer boundary of the region with the foreground target graph, and a background region in the rectangular region is removed through the GrabCut algorithm, so that the foreground target graph is cut; (4) the foreground target graph is output. According to the interactive graph cutting method, the advantage that user interactivity of the GrabCut algorithm is low is reserved, and the defects of the GrabCut algorithm are overcome by making full use of boundary information of a foreground target with the help of the Canny algorithm under the condition that foreground / background colors are similar or shadows exist in the foreground target. In addition, due to the fact that the iterations of the GrabCut algorithm is reduced through the interactive graph cutting method, operating efficiency is greatly improved; meanwhile, due to the fact that the user does not need to draw the general outline of the foreground target graph, the workload of the user is reduced.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to an interactive image segmentation method. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. The existing image segmentation methods are mainly divided into the following categories: threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories. [0003] Currently, image segmentation is a key issue in the fields of image processing, pattern recognition, and computer vision. Since the traditional machine automatic segmentation and manual segmentation are difficult to achieve the expected purpose, interactive image segmentation has become the mainstream of current research. Since the development of image segmentation, many interactive...

AI Technical Summary

Problems solved by technology

Among them, the GrabCut method uses the Gaussian mixture model (GMM) to characterize the color probability distribution, and performs image segmentation simply based on the region information. For images with similar color information or shadows in the foreground target, the extracted foreground target is inaccurate and requires a lot of manual correction in the later stage

However, the images of foreground objects that have been artificially corrected in the later stage are often inaccurate, which brings errors to the further analysis and processing of foreground objects.

In response to this problem, Wang Jianqing et al. proposed a target extraction method combining boundaries and regions. This method combines GCBAC and GrabCut algorithms to improve the traditional GrabCut algorithm. Algorithm increases the amount of calculation, and another obvious disadvantage is that this method requires the user to draw the outline of the foreground target, which also increases the workload of the user

Images