Fuzzy rough set coal dust image segmentation method based on multiple attribute reduction

Abstract

The present invention discloses a fuzzy rough set coal dust image segmentation method based on multiple attribute reduction. The method comprises the steps: 1. determining the fuzzy type membership degree; 2. determining the fuzzy attribute reduction, and obtaining the coal dust image removing redundancy attributes; 3. calling a segmentation threshold determination module through an image processor and determining the threshold value for performing coal dust image segmentation according to the maximum entropy threshold value determination method; and 4. comparing the gray value of each pixel in the coal dust image segmentation removing the redundancy attributes with the threshold value for performing coal dust image segmentation through the image processor, and dividing the pixels which have the gray values are larger than the threshold value for performing coal dust image segmentation into target areas, and dividing the pixel which have the gray values are smaller than or equal to the threshold value for performing coal dust image segmentation into background areas. The method steps are simple, the efficiency and the precision of the coal dust image segmentation are improved, the effectiveness and the robustness are good, the usage is flexible and convenient, the expandability is good, and the popularization application value is high.

Description

technical field [0001] The invention belongs to the technical field of coal dust image processing, and in particular relates to a fuzzy rough set coal dust image segmentation method based on multi-attribute reduction. Background technique [0002] In coal preparation plants with severe coal dust pollution, during the screening, crushing and transportation of raw coal, due to the volatilization and drying of coal moisture, a large amount of dust will be generated in the process of being vibrated, impacted and caused to fall, and the concentration of coal dust will reach a certain level. When combined with oxygen in the presence of an open flame, a vicious safety accident of coal dust explosion will occur at any time, causing great harm. And too much coal dust will cause serious wear and tear on expensive and sophisticated equipment and instruments, causing the aging of the machine, reducing the service life of precision instruments, and also causing the problem of pneumoconio...

AI Technical Summary

Problems solved by technology

In practical applications, the threshold method has become the most basic and widely used segmentation technology in image segmentation, and has been applied to many fields, but the key and difficulty of this method lies in how to obtain an appropriate threshold; if the threshold is selected too high, then Too many target points will be misclassified as the background, and if the threshold is selected too low, the background will be misjudged as the target

Due to the small difference between the gray value of the coal dust particle target and the background, the features of the coal dust image are very blurred (there is no clear characteristic mode), therefore, there is still a lack of methods that can be reliably applied to coal dust image processing in the prior art. Image segmentation method, after the image segmentation method in the prior art is applied to coal dust image segmentation, there are defects and deficiencies such as complex segmentation method, low precision, and low efficiency, which limit the development of coal dust monitoring technology

Images