Image segmentation method based on network dynamical evolution strategy

Abstract

The invention discloses an image segmentation method based on a network dynamical evolution strategy. The method comprises the following steps: step one, carrying out pixel feature extraction; step two, carrying out pre segmentation; step three, acquiring features of regional block; step four, calculating a similarity degree between random two regional blocks; step five, establishing a network model; step six, classifying nodes of the network based on a network dynamical evolution strategy; and step seven, outputting an image segmentation result. According to the image segmentation method disclosed by the invention, regional consistency and detail integrity of the segmented images are kept well and thus the effect of image segmentation is improved. Moreover, the time complexity of the algorithm is reduced and thus the algorithm is converged as soon as possible; and thus defects that the convergence is done slowly, the algorithm is easy to fall into a local optimization problem, and the time complexity is high of the traditional machine learning algorithm are overcome.

Description

technical field [0001] The invention relates to an image segmentation method based on a network dynamic evolution strategy, belonging to the technical field of image processing. Background technique [0002] Image segmentation is a key technology in image processing technology. It refers to dividing the image into several non-overlapping regions according to the characteristics of the image such as grayscale, color, texture and shape. The same region has similar characteristics. The characteristics of different regions show obvious differences. Image segmentation is the first step in image analysis. The next tasks of image segmentation, such as feature extraction and target recognition, all depend on the quality of image segmentation. [0003] At present, image segmentation is widely used in fields such as medicine, remote sensing, image processing, intelligent transportation and computer vision. In recent years, the image segmentation technology based on graph theory has ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that although the image is preprocessed and divided into a certain number of regional blocks before the establishment of the graph theory model, in the specific segmentation process, it is necessary to construct a training set and use the obtained training model to Unclassified images are segmented, and the construction of the training model virtually increases the time complexity of the algorithm. At the same time, in this method, the construction of the training set affects the effect of image segmentation to a certain extent. For different types of images, the construction The training set must also be different, which also increases the complexity of the algorithm

Images