Method and device for realizing interactive image segmentation, and terminal

Abstract

The invention discloses a method and device for realizing interactive image segmentation, and a terminal. The method comprises steps that smearing locus on an original image is taken as a framework to grow to form a mark area; an input mask artwork of an image segmentation algorithm is generated, pixels of the mark area are taken as foreground points of the mask artwork, and pixels outside the mark area are taken as background points of the mask artwork; a depth image containing the target object depth information is acquired, a segmentation parameter of each pixel of the mask artwork is determined according to the depth image and the mask artwork, an undirected graph is constructed, a segmentation parameter of each pixel of the mask artwork is mapped to the undirected graph, the the undirected graph is processed according to a minimal cut-maximal flow algorithm to acquire the mask artwork after fine segmentation, and an image corresponding to the foreground points of the mask artwork after fine segmentation is acquired through segmenting the original image. The method is advantaged in that the algorithm operation time is shortened, and the image segmentation effect is improved through utilizing the image depth information.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device and terminal for realizing interactive image segmentation. Background technique [0002] Image segmentation refers to dividing a plane image into several unconnected regions according to its color, texture, shape and other characteristics. This is a practical basic technology in the field of image processing. Existing image segmentation techniques include threshold-based segmentation methods, edge-based segmentation methods, region-based segmentation methods, energy functional-based segmentation methods, graph theory-based segmentation methods, and so on. Among them, the GraphCut algorithm and its improved version GrabCut algorithm are well-known in the graph theory method. [0003] The GraphCut algorithm and its improved version, the GrabCut algorithm, are interactive image segmentation methods based on region annotation. The GraphCut algorith...

AI Technical Summary

Problems solved by technology

[0004] When using the GrabCut algorithm for image segmentation on a mobile phone, in order to reduce the complexity of the interaction, there are usually no strict requirements on how the user marks. Therefore, when the foreground points marked by the user are few, the number of iterations may be large, and the running time of the algorithm Long, affecting the user experience

On the other hand, the GrabCut algorithm in the related art is based on color images for image segmentation. When the color features of the target object to be extracted are not obvious, the segmentation effect of using color images for segmentation is not ideal.

Images