A Petri Network Image Segmentation Method Based on Rough Set and Rough Entropy

Abstract

The invention belongs to the field of image information processing research, and specifically relates to a Petri network image segmentation method based on rough sets and rough entropy, comprising the following steps: finding the maximum and minimum gray values ​​of the image, and storing them in variables max and min ;Divide the image into point sets according to the width and height of the image; use the Monte Carlo method to randomly select 1000 points from the point set; calculate the maximum and minimum gray values ​​of the point set as Pimax and Pimin respectively; calculate the drop and rise of the object Rough sets are stored separately in O T and compute background ascent and descent rough sets saved to and B T Medium; Sort the subsets and draw outlines according to the threshold T, if the gray value of the subset is greater than the threshold T, then the subset belongs to the object buffer, if the gray value of the subset is lower than the threshold T, then the subset The set belongs to the background buffer to get a rough outline of the graph; the first stage of coarse segmentation is adjusted to get a precise outline. The invention solves the problems of uncertainty, non-uniformity and inefficiency.

Description

technical field [0001] The invention belongs to the field of image information processing research, in particular to a Petri network image segmentation method based on rough sets and rough entropy. Background technique [0002] Image segmentation is a key step in image processing and analysis. For example, medical image segmentation is of great significance in the research of medical image processing. As an intermediate process, it is the basis for subsequent image processing, including registration and measurement. Accurately locating the lesion and determining the extent of the lesion in medical imaging have a crucial impact on subsequent diagnosis and treatment. In the early days of medical image segmentation, the boundaries were manually drawn by medical workers, with low repeatability and heavy workload. With the development of computer and image processing technology, computer-aided medical image segmentation has become an increasingly important research direction. ...

AI Technical Summary

Problems solved by technology

For example, when the image has a weak boundary with a low gradient value, the segmentation effect is not good, and when the intensity of the image is uneven in each region, the segmentation effect is not good, and it is difficult to ensure that it is applicable to various images, and the amount of calculation is large, resulting in equipment processing load. Increase

[0005] For example, due to the inherent characteristics of ultrasound imaging, the image may have large noise, many spots, low contrast, uneven gray scale inside the mass, and unclear boundaries.

Regardless of which of the above-mentioned methods in the prior art is used, it is difficult to achieve ideal segmentation results for ultrasound images with different characteristics

[0006] In summary, there are problems such as heavy workload, complicated operation, poor effect and unclear graphics in the prior art

Images