Method for optimizing multilayer image segmentation of multiclass color texture images based on variation model

Abstract

The invention discloses a method for optimizing double-layer image segmentation of multiclass color texture images based on a variation model. The method comprises the steps of establishing a multiclass variation active contour model, obtaining an energy function of the multiclass variation active contour model, carrying out disperse expression on the energy function of the multiclass variation active contour model, establishing a multilayer image segmentation model, solving the energy function of the multiclass variation active contour model after disperse expression to obtain a globally near optimal solution, and carrying out multi-layer image segmentation minimality optimization on multiclass disperse variation active contour energy in an iteration mode to achieve stable segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a multi-class color texture image segmentation method based on a variational active contour model. Background technique [0002] At present, the image segmentation method based on the variational model has received extensive attention. It is widely used in visual tracking and target detection because it can provide smooth and closed curves and can combine prior information to obtain the desired non-homogeneous target boundaries. , scene understanding, industrial inspection, content-based image retrieval, and medical image analysis. Since the image contains multiple non-homogeneous target areas, although many scholars have proposed multi-class segmentation methods, they all use constant density descriptions and use interactive methods to mark target areas or sub-target areas, resulting in segmentation The results of the method depend largely on prior informat...

AI Technical Summary

Problems solved by technology

However, when region-based methods segment complex and varied natural images, the final segmentation results are prone to false target regions, and the captured target edges are not smooth enough. If the edge-based method is combined with the region-based method, it can Get better segmentation results

However, the area corresponding to each calibration color uses K-Means for statistical calculation of multiple constant cluster centers, which may lead to unstable feature distribution descriptions of multiple target areas.

More importantly, for complex and variable color texture images, it is difficult to describe the nonlinear and continuous feature changes in the image using this multi-segment constant cluster center assumption.

Images