Object segmentation method and system based on mixed marks

Abstract

The invention discloses an object segmentation method and an object segmentation system based on mixed marks. The method comprises the following steps of: receiving marking strokes of pixels in an image which comprises a target object, wherein the marking strokes comprise foreground strokes for the target object, background strokes for a background and undetermined strokes which are undetermined for a foreground or the background; on the basis of the foreground strokes and the background strokes, establishing a foreground model and a background model to classify the pixels in the image, which are not marked by the undetermined strokes, into foreground pixels or background pixels; and according to the foreground pixels and the background pixels, which are classified, calculating probability values with which one or more pixels corresponding to the undetermined strokes belong to the foreground strokes, determining the pixels of which the probability values are smaller than lower limit as the background pixels, and determining the pixels of which the probability values are greater than upper limit as the foreground pixels. An object in the image is interactively segmented on the basis of various marks, so complicated boundary situation can be handled, and a high-accuracy segmentation result is obtained.

Description

technical field [0001] The invention relates to image processing technology, in particular to an object segmentation method and system based on mixed markers. Background technique [0002] The purpose of image segmentation is to mark the region of interest in the image. According to the marked results, people can perform image processing on specific regions of interest. This requirement for image processing for a specific region is a common requirement in image processing applications. However, methods that can efficiently mark regions of interest are not yet mature. If the region itself is regular, it is easy to do the job with an interactive tool such as a mouse. However, if the region of interest is irregular, it is more difficult to divide the region of interest. To obtain the region of interest, it is necessary to mark the boundary pixels of all regions of interest one by one. Such work is very trivial and labor-intensive. Therefore, people hope to extract the reg...

AI Technical Summary

Problems solved by technology

For complex situations, the segmentation results are often not accurate enough

For example, for an object like hair, the boundary is extremely complex, and it is difficult for the user to mark the boundary of the target object

Therefore, when these boundary pixels have segmentation errors or insufficient label information, the user's annotation often obtains poor results due to insufficient labeling.

Therefore, it is difficult for current segmentation algorithms to handle such complex boundaries

[0005] Patent Document 1 (US20080136820A1) proposes a marker-based object segmentation method, but its core technology is still to use two markers, foreground and background, to obtain segmentation results

For complex boundaries such as hair, the method proposed in this patent document 1 still has difficulties, and the segmentation accuracy is not high

Images