Multiple foreground object image interactive segmentation method

Abstract

The invention relates to the technical field of computer vision, image processing, pattern recognition and the like and particularly relates to a multiple foreground object image interactive segmentation method. The image interactive segmentation method includes the steps of (1) constructing an image pixel similarity matrix, (2) acquiring image pixel label information; (3) constructing a spectral clustering segmentation model by combining the image pixel similarity matrix and the image pixel label information and solving to obtain a preliminary segmentation result, (4) constructing spatial smoothing constraint, and (5) constructing a markov random field model by combining the preliminary segmentation result and the spatial smoothing constraint and solving to obtain a final segmentation result. According to the multiple foreground object image interactive segmentation method, advantages of grabcut methods and linear constraint spectral clustering methods are integrated, simultaneously defects of the grabcut methods and the linear constraint spectral clustering methods are overcome, and images with randomly distributed colors and multiple foreground objects can be segmented merely by labeling an extremely small quantity of pixel points.

Description

Technical field [0001] The invention relates to the technical fields of computer vision, image processing and pattern recognition, and in particular to a method for interactive segmentation of multi-foreground target images. Background technique [0002] Image segmentation is to divide the image into some non-overlapping areas according to its characteristics, so as to separate the part of the image that the user is interested in. Image segmentation is a key technology in the field of image processing and computer vision, and it is the basis for multiple applications such as target detection, target tracking, and target analysis. [0003] There are many types of image segmentation techniques, most of which are carried out in a bottom-up manner. They achieve the purpose of segmentation by detecting boundaries or clustering pixels based on features such as color and texture. The spectral clustering method is currently the most widely used pixel clustering algorithm because it can cl...

AI Technical Summary

Problems solved by technology

The main disadvantage of the GrabCut method is that it can only segment images with a single foreground object, and requires the color distribution of the foreground and background pixels to meet the mixed Gaussian model, and requires a large difference in the color distribution of the two, which is not strong for the front and background contrast. The boundary area segmentation effect of the

This method does not rely on the mixed Gaussian modeling of the front and background color distribution, so it can be applied to images of almost all scenes, but its disadvantages are: the calculation is time-consuming and cannot be applied in real time; the spatial smooth information of pixels cannot be encoded into the corresponding Constraints; for the low utilization efficiency of labeling information, a large number of labeling pixels are needed to obtain more accurate segmentation results

Images