Image segmentation method based on color sample and electric field model

Abstract

The invention relates to an image segmentation method based on a color sample and an electric field model. In the invention, an electric field theory in physics is introduced to color sample learning, model training and pixel classification. The method comprises the steps of: selecting positive sample pixel data and negative sample pixel data of a target area from sample pictures, taking color space as a 3D electric field model and calculating field intensity of each coordinate point, deducing each color value probability belonging to an object area in the space based on a Bayesian criterion, searching an optimal segmentation threshold of an object in the space through an ROC curve describing classification effect, determining related parameters of the field model and a suitable electric field spatial resolution, and building indexes through a mapping table method to further achieve rapid pixel classification and image segmentation. Compared with the histogram model in the prior art, according to the invention, the non-sample point probability can be estimated under the circumstance of a small sample; compared with the kernel density estimation method in the prior art, according to the invention, image segmentation with high precision and high time-efficiency can be realized by using more kernels to describe color distribution of the target area.

Description

technical field [0001] The invention relates to the technical field of image segmentation based on color features in digital image processing, in particular to an image segmentation method based on color samples and electric field models. Background technique [0002] Image segmentation is a basic and key problem in the field of digital image processing and computer vision. The purpose is to extract the target of interest from the image background and provide the basis for subsequent processing such as classification, tracking, and recognition. Specifically, image segmentation refers to the process of subdividing an image into multiple image sub-regions or sets of pixels by using certain characteristics of a digital image, such as color, shape, texture, etc. [0003] The existing image segmentation methods can be roughly divided into threshold segmentation, edge detection segmentation, region characteristic segmentation, feature space clustering segmentation and so on. The ...

AI Technical Summary

Problems solved by technology

This model attempts to describe the continuity of color distribution through the combination of several Gaussian kernels that affect the surrounding space, but this approximate expression is still relatively rough, the definition of the color range and its boundary is not precise enough, and the corresponding segmentation effect is not ideal.

In addition, the training time of GMM is too long, especially in the case of automatic calculation of the number of Gaussian kernels

Images