An object segmentation method based on prior shape and cv model

Abstract

The invention relates to an object segmentation method based on a priori shape and a CV (Computer Vision) model. The method comprises the following steps of: constructing a signed distance function by selecting the priori shape; carrying out affine transformation on the signed distance function of the priori shape according to vectors of affine transformation parameters, wherein the affine transformation parameters are changed and finally tend to stabilize in the process of iterating a level set function; and finally, obtaining various affine transformation parameters of the next time according to a level set iteration formula evolution movable outline curved line and various affine parameter iteration formulae. According to the method disclosed by the invention, on the basis of keeping rotary, zoom and translation invariance of a priori shape model, stretching in X and Y directions and shear unchanged constraint energy item can be increased; and a space object with larger posture transformation under a complex background can be well segmented by expanding the self-adaptive transformation of the priori shape.

Description

technical field [0001] The invention relates to an image processing technology, in particular to a target segmentation method based on a priori shape and a CV model. Background technique [0002] At present, among the existing target segmentation methods, the curve evolution method has quite good results for target segmentation, including the Snake method, the active contour method, the deformation model and the level set method. The parameterized Snake method allows It interacts directly with the model, and the expression of the model is compact, which is conducive to the rapid realization of the model, but it is difficult to deal with the change of the model topology. The active contour model based on the variational level set method can naturally deal with the change of the evolution curve or surface topology, and can naturally integrate the boundary information and the region information together. [0003] Mumford proposed the M-S level set model to solve the edge detec...

AI Technical Summary

Problems solved by technology

However, the model divides the target area based on the gray similarity, so the model has three defects: ① cannot segment the target whose gray level is similar to the background, ② cannot effectively segment the texture image, ③ cannot segment the occluded, Targets with missing data

However, the prior shape item in this model only has the invariant characteristics of rotation, scaling, and translation. For objects that are sheared or have different stretch coefficients in the X and Y directions, the segmentation effect of the above model is poor.

Images