Target Scale Selection Method for Image Multi-level Segmentation Based on Depth Seed

Abstract

The invention discloses a target scale selection method for image multi-level segmentation based on depth seeds, comprising the steps of: using a multi-level image segmentation algorithm to divide an input image into several levels; constructing a multi-level segmentation tree; using color histograms, texture histograms and The geometric size of the region represents the image feature, and the quality of the segmented region is evaluated to obtain the segmentation quality score; the optimal segmentation tree is found; the depth seed positioning is performed on the foreground class and the background class of the input image; the image segmented region is used in the optimal segmented tree, Create a graph, and obtain the segmentation result by finding the minimum segmentation of the graph. The present invention locates the foreground seeds by improving the VGG-19 network and the saliency detection algorithm locates the background seeds, generates depth seeds to process multi-level segmentation of images; designs a graph model, uses depth Semantic information provided by the learning model enables optimal scale selection of image objects.

Description

technical field [0001] The invention relates to the technical field of image segmentation, in particular to a method for selecting a target scale for multi-level image segmentation based on depth seeds. Background technique [0002] Image segmentation is an important technology in computer vision. Its purpose is to divide the image into several segments according to the characteristics of the image such as color consistency or texture similarity. Although comprehensive segmentation algorithms have also been proposed in the literature, it remains an open challenge to efficiently segment out meaningful parts of objects to visualize human perception. Everyone has a different definition of "meaningful", and different people will have different ideas about how to correctly segment an image. Many people like to split the image into several segments, while others tend to only recognize a few segments of the image content. In this case, a single segmentation result can only be gen...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiency of the target scale selection of the existing hierarchical image segmentation, the present invention provides a method for selecting the target scale of the image multi-level segmentation based on the depth seed, which overcomes the difficulty of finding the correct target scale for the existing multi-level image segmentation algorithm at a single layer level. The disadvantage of the target segmentation scale, by generating the depth seeds of the foreground class and the background class, the optimal segmentation result is obtained

Images