A method and device for image segmentation

Abstract

The present invention is applicable to the technical field of image processing, and provides an image segmentation method and device, including: detecting a sliding operation, generating a closed curve around the target image on the original image according to the sliding operation; generating two A valued image template, the size of the binarized image template is equal to that of the original image; the contour of the target image is detected and obtained according to the generated binary image template; according to the target image The mask is generated from the contour of the mask; the transparency value of the unknown area in the mask is calculated; the foreground component and the background component of the original image are determined by using the transparency value and the original image; according to the determined original The foreground component and the background component of the image are segmented from the original image to obtain the foreground image. The invention fully combines the operation characteristics and processing performance of the mobile terminal, and can effectively realize image segmentation on the mobile terminal.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image segmentation method and device. Background technique [0002] Image segmentation, that is, for an image, its foreground component, background component and the transparency value of the foreground are calculated separately, so as to separate the foreground from the image. The existing image segmentation methods need to manually mark the pixels in the image to manually mark the foreground and background in the image, and then use each pixel as a node to construct a graph structure, and solve the problem by solving the minimum segmentation of the graph structure. Realize image segmentation. [0003] With the improvement of the software and hardware level of mobile terminals, users hope to be able to perform image processing anytime and anywhere through mobile terminals. Obviously, due to the limitation of the screen size and operation mode of mobile t...

AI Technical Summary

Problems solved by technology

[0003] With the improvement of the software and hardware level of mobile terminals, users hope to be able to perform image processing anytime and anywhere through mobile terminals. Obviously, due to the limitation of the screen size and operation mode of mobile terminals, it is impossible to process each pixel of the image to be segmented one by one. mark, and is limited by the processor performance of the mobile terminal, and cannot afford the huge amount of calculation when the existing image segmentation method solves the graph structure

Images