Automatic identification method for coal petrography image

Abstract

The invention discloses an automatic identification method for a coal petrography image. The method comprises the following steps: extracting textural feature information of an image by using Daubechies wavelet, wherein the textural feature information comprises coefficient mean value, coefficient variance, mean value texture guiding degree, variance texture guiding degree and distance value representing similar features between a sample image and a to-be-measured image; and identifying the coal petrography image by analyzing the distance value. According to the invention, the Daubechies wavelet is adopted to extract the feature information of the image, so as to realize the characteristics of rapid identification, wide adaptability and high reliability.

Description

technical field

[0001] The invention relates to a method for recognizing a target image in the field of image processing, in particular to a method for realizing automatic recognition of coal and rock images by using Daubechies wavelet transform. Background technique

[0002] In the process of underground coal mine mining, it is necessary to accurately identify the coal seam and rock formation, so as to control the lifting of the rocker arm of the shearer, so as to avoid cutting the roof and floor rocks. At present, my country mainly adopts conservative mining methods, and the actual recovery rate is low, resulting in serious waste of resources. And the current technical level is also difficult to carry out secondary mining of the remaining large coal resources, so the development of coal rock identification technology is of great significance.

[0003] Since the 1950s, the United States and other major coal-producing countries in the world have paid more and more attention...

Examples

Embodiment

[0112] 1. Establish a database of coal and rock sample characteristics

[0113] Table 1 Sandstone eigenvalue parameter list

[0114]

[0115] Table 2 Shale eigenvalue parameter table

[0116]

[0117] Table 3 Anthracite characteristic value parameter table

[0118]

[0119] Table 4 Bituminous coal eigenvalue parameter table

[0120]

[0121] 2. Feature extraction of the sample to be tested (such as Figure 5 , Figure 6 , Figure 7 shown)

[0122] Table 5 Parameter table of eigenvalues ​​of samples to be tested

[0123]

[0124] 3. Calculate the spatial distance between the sample to be tested and the coal and rock samples in the database

[0125] By computer according to the Minkowski distance formula D ( f q , f t ) = Σ i = 1 ...

technical field

[0001] The invention relates to a method for recognizing a target image in the field of image processing, in particular to a method for realizing automatic recognition of coal and rock images by using Daubechies wavelet transform. Background technique

[0002] In the process of underground coal mine mining, it is necessary to accurately identify the coal seam and rock formation, so as to control the lifting of the rocker arm of the shearer, so as to avoid cutting the roof and floor rocks. At present, my country mainly adopts conservative mining methods, and the actual recovery rate is low, resulting in serious waste of resources. And the current technical level is also difficult to carry out secondary mining of the remaining large coal resources, so the development of coal rock identification technology is of great significance.

[0003] Since the 1950s, the United States and other major coal-producing countries in the world have paid more and more attention...

Examples

Embodiment

[0112] 1. Establish a database of coal and rock sample characteristics

[0113] Table 1 Sandstone eigenvalue parameter list

[0114]

[0115] Table 2 Shale eigenvalue parameter table

[0116]

[0117] Table 3 Anthracite characteristic value parameter table

[0118]

[0119] Table 4 Bituminous coal eigenvalue parameter table

[0120]

[0121] 2. Feature extraction of the sample to be tested (such as Figure 5 , Figure 6 , Figure 7 shown)

[0122] Table 5 Parameter table of eigenvalues ​​of samples to be tested

[0123]

[0124] 3. Calculate the spatial distance between the sample to be tested and the coal and rock samples in the database

[0125] By computer according to the Minkowski distance formula D ( f q , f t ) = Σ i = 1 ...

Images