An Improved Geometric Active Contour Image Segmentation Method

Abstract

The invention discloses an improved image segmentation method of geometric active contour, including Step 1: inputting an image to be processed and a vector field; Step 2: sampling the vector field through a rectangular grid, obtaining an observation set after sampling, and embedding iteratively Rod estimator to eliminate the error and noise of the observations in the observation set; then insert the observation points, use the smoothed ridge regression and constrain the elastic net to construct the advection vector field; Step3: Embed the advection vector field and diffusion flow into the geometric active contour In this way, a unified geometric active contour model based on advection vector field and diffusion flow is constructed to guide the update of the initial level set, and the updated level set will evolve the active contour curve to the accurate target contour, thus completing the image analysis. segmentation. Compared with the traditional scheme, the method proposed by the present invention has obvious advantages and achieves a better segmentation effect.

Description

technical field [0001] The invention relates to an improved image segmentation method of geometric active contour, belonging to the field of image processing. Background technique [0002] Contours captured from image sequences have rich spatial structure and have been widely used in video surveillance, medical analysis, and action recognition, etc. Features of interest in an image, whether rigid or non-rigid, often involve complex motion and deformation. To accomplish this challenging task, the Active Contours (AC, Active Contours) method initiates an evolution curve near the object boundary, then matches the evolution curve to the real contour, and finally resides on that contour. Geometric active contour (GAC) captures the position of parametric contours by minimizing a smooth and gradient-driven energy combination. [0003] The curve evolution of the GAC model is essentially a diffusion that is regarded as a spatial scalar model, such as a level set function, and the n...

AI Technical Summary

Problems solved by technology

However, given the sampling interval, even if diffusion via Gaussian smoothing is pre-implemented to the original image, the global motion between adjacent images can be so significant that the DCF is temporally discontinuous

Images