Method and device for optimizing image segmentation result

Abstract

The invention provides a method for optimizing an image segmentation result, and the method comprises the steps: determining an under-segmentation region and an over-segmentation region in two segmentation regions if there is an unconspicuous boundary between the two adjacent segmentation regions in the image segmentation result; performing pixel value distribution statistics on the under-segmentation region and the over-segmentation region, and determining a conversion interval according to a statistical result; and converting the pixels meeting the conversion interval in the over-segmentation region into the under-segmentation region. According to the scheme, a pixel segmented into the over-segmentation region by mistake can be converted into an under-segmentation region; the technical problem that an unobvious boundary exists between two adjacent segmentation regions is solved, a good optimization effect can be achieved, and the optimized output image can accurately present variousinformation in original input, so that subsequent analysis processing based on an image segmentation result is facilitated, and the accuracy of an analysis processing result is improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a technical solution for optimizing image segmentation results. Background technique [0002] With the development of computer science and technology, image segmentation technology is widely used in various fields, such as industrial automation, production process control, online product inspection, remote sensing and medical image analysis. However, in a grayscale image, if a region is divided into two or more kinds of segmentation regions, there may be an indistinct boundary between two adjacent segmentation regions, and two adjacent segmentation regions with indistinct boundaries There may be a large difference from the original input, which may have a negative impact on the subsequent analysis and processing process based on the image segmentation results, especially in medical image analysis, which may lead to inaccurate analysis of individual diseases, and m...

AI Technical Summary

Problems solved by technology

However, in a grayscale image, if a region is divided into two or more kinds of segmentation regions, there may be an indistinct boundary between two adjacent segmentation regions, and two adjacent segmentation regions with indistinct boundaries There may be a large difference from the original input, which may have a negative impact on the subsequent analysis and processing process based on the image segmentation results, especially in medical image analysis, which may lead to inaccurate analysis of individual diseases, and may even Misdiagnosis leading to disease

Images