A method of rock particle segmentation based on mathematical morphology

A mathematical morphology and rock technology, applied in the field of images, can solve the problems of submersion, inability to segment rock particles, and time-consuming, and achieve the effect of improving the accuracy rate.

Active Publication Date: 2018-12-25
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the segmentation effect of sequence images is the best, and the segmentation accuracy rate can reach 90%. However, this method needs to shoot polarized sequence images of rocks at a specific angle, and needs to segment each image, which takes a long time.
Both the watershed algorithm and the region growing algorithm cannot segment complete rock particles due to the influence of holes in the rock particle image
Using binary mathematical morphology to fill the holes in the rock particle image will cause incomplete filling of the holes or submerge the correct particle boundaries due to the irregular shape and size of the holes. Combined with the segmentation algorithm, it will also increase the accuracy of the segmentation Difficult to reach 70%, resulting in wrong petrophysical parameters, not of use value
[0003] In order to solve the problem that the particle size analysis of rock thin sections has always been restricted by the low accuracy of rock particle segmentation, a method of rock particle segmentation based on gray-scale mathematical morphology is proposed.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method of rock particle segmentation based on mathematical morphology
  • A method of rock particle segmentation based on mathematical morphology
  • A method of rock particle segmentation based on mathematical morphology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described with reference to the accompanying drawings.

[0040] combined with Figure 1-4 The specific implementation manner of the present invention will be described in further detail.

[0041] Such as figure 1 Shown, a flow chart of a rock particle segmentation method based on mathematical morphology, including the following steps:

[0042] Step (1) Read in a colored image of rock particles from the database and convert it into a grayscale image I, I=0.299·R+0.587·G+0.114·B. After several experiments, when the radius of the structural element b(s, t) is set to be a circle of 15 pixels, the parameter value is 1, and the threshold value T=15 is set as the condition for region growth, the experimental effect is the best;

[0043] Step (2) Use the structural element b(s, t) to scan t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a rock particle segmentation method based on mathematical morphology, by using gray-scale mathematical morphology to preprocess the rock grain image, the image is filled with tiny holes and the correct boundary of rock grains is preserved so that the rock grains form an effective agglomerate region. Then the pixels with similar properties in each agglomerate region are combined into a single region by the region growth algorithm to complete the segmentation of rock grains. By the invention, the corrosion operation and the dilation operation do not have fuzzy grain boundaries, and the complete shape of the reserved grains is relatively complete, so that the corrosion operation and the dilation operation do not have fuzzy grain boundaries.

Description

technical field [0001] The invention relates to the image field, in particular to a method for segmenting rock particles based on mathematical morphology. Background technique [0002] Image-based rock particle size analysis is to obtain the particle size and spatial distribution of rock particles through digital image processing technology, so as to obtain the physical properties of rocks. Among them, the segmentation of rock particles is the premise of completing the analysis of rock particle size. The main segmentation algorithms include watershed algorithm, region growing algorithm, gradient filter, sequence image processing, etc. Among them, the segmentation effect of sequence images is the best, and the segmentation accuracy rate can reach 90%. However, this method needs to shoot polarized sequence images of rocks at a specific angle, and needs to segment each image, which takes a long time. Both the watershed algorithm and the region growing algorithm cannot segment...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/11
CPCG06T7/11G06T2207/30132
Inventor 李作进何昌隆谭先锋陈刘奎贺吉胜
Owner CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products