Image threshold determination method and device based on three-dimensional connectivity

Abstract

The invention provides an image threshold value method and device based on three-dimensional connectivity. The method comprises the steps: completely importing two-dimensional images collected at a time; setting a segmentation threshold interval o, and judging a parameter threshold epsilon; selecting a threshold search initial value [mu]0, wherein the threshold search initial value [mu]0 is less than or equal to the segmentation threshold; respectively calculating the total number N of the voxels of the foreground region segmented under the threshold value [mu]0-2 * o, the threshold value [mu]0-o and the threshold value [mu]0, and / or the total number M of the segmented voxels, and / or the total number L of the voxels of the non-foreground region segmented; setting a discrimination parameterbeta; if the discrimination parameter beta is greater than the discrimination parameter threshold epsilon, taking a threshold [mu]0 corresponding to the current beta, and outputting [mu]0-o as an optimal threshold, otherwise, [mu]0 <- [mu]0 + o, and continuing threshold detection. According to the method and the device provided by the invention, the optimal segmentation pixel value is searched byusing the significant change of the voxel spatial characteristics, so the foreground segmentation is more accurate.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to an image threshold measurement method and device, in particular to a three-dimensional connectivity-based image threshold measurement method and device. Background technique [0002] Threshold method is one of the commonly used methods for image segmentation. It uses the difference in gray value between the target and the background in the image, and classifies the pixels by setting the threshold, so as to achieve the separation of the target and the background. Common threshold methods include: [0003] (1) Artificial experience selection method [0004] According to prior knowledge, or by analyzing and summarizing the rules of the target and background in the image, the pixel value range of the target and background is obtained, and a better threshold is found on this basis. This method cannot achieve automatic threshold selection and is therefore less efficient and susceptible ...

AI Technical Summary

Problems solved by technology

[0029] Both the maximum inter-class variance method and the iterative method require consideration of the pixel value distribution characteristics of the foreground and background regions at the same time, so the process of determining the threshold will be interfered by the background feature information

In addition, these two methods require the distribution of pixel values ​​​​in each part of the foreground to be continuous. If there are areas with contrasting pixel values ​​in the foreground or local information is missing, etc., large segmentation errors will also occur.

Images