Color image segmentation method of a self-adaptive hierarchical histogram

Abstract

The invention relates to the technical field of image processing, and discloses a color image segmentation method of a self-adaptive hierarchical histogram, which comprises the following steps of: S1,respectively generating three groups of hierarchical histograms on an R color plane, a G color plane and a B color plane for an RGB color image; wherein each group of hierarchical histograms comprises a plurality of layers of histograms which respectively correspond to the multi-level abstract granularity of the image; wherein the bottommost histogram in the group of hierarchical histograms is anoriginal histogram and represents the image with the finest granularity of the image; wherein the upper layer of histogram is generated according to the lower layer of histogram, so that the image extraction granularity of the upper layer of histogram is larger than that of the lower layer of histogram; s2, performing thresholding on the top layer histogram in each group of hierarchical histograms to complete initial segmentation of the image; and S3, merging clusters formed by initial segmentation to complete final image segmentation, and the color image segmentation method of the adaptive hierarchical histogram has better segmentation efficiency and can obtain better segmentation quality.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a color image segmentation method of an adaptive hierarchical histogram. Background technique [0002] Image segmentation plays an important role in image analysis, pattern recognition, and computer vision-related applications. In segmentation, an image is segmented into distinct non-overlapping regions whose interiors are homogeneous in certain attributes, such as color information, edges, and texture. Although many image segmentation techniques have been proposed, image segmentation is still a very challenging research topic due to the diversity and complexity of images. In addition, color images provide richer information than grayscale images, especially natural color image segmentation has attracted more and more attention from scholars. [0003] The method of using the shape information of the image histogram to determine the image segmentation threshold is a rel...

AI Technical Summary

Problems solved by technology

However, such methods need to calculate the distance between each pixel and its neighbors, and the algorithm takes a long time.

In addition, such techniques usually include some smoothing of the histogram (histon or roughness-index) data, searching for significant peaks, and then determining the minimum value between adjacent significant peaks as a threshold, the steps are cumbersome

And, if the trough is flat, it is difficult for these techniques to find the exact threshold

Images