CN116823827B - Ore crushing effect evaluation method based on image processing - Google Patents
Ore crushing effect evaluation method based on image processing Download PDFInfo
- Publication number
- CN116823827B CN116823827B CN202311092828.XA CN202311092828A CN116823827B CN 116823827 B CN116823827 B CN 116823827B CN 202311092828 A CN202311092828 A CN 202311092828A CN 116823827 B CN116823827 B CN 116823827B
- Authority
- CN
- China
- Prior art keywords
- ore
- ore particle
- particle
- central
- pixel point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 54
- 230000000694 effects Effects 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 title claims abstract description 30
- 239000002245 particle Substances 0.000 claims abstract description 379
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000012916 structural analysis Methods 0.000 abstract description 12
- 238000010191 image analysis Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 8
- 238000012937 correction Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- FKENQMMABCRJMK-RITPCOANSA-N sulbactam Chemical compound O=S1(=O)C(C)(C)[C@H](C(O)=O)N2C(=O)C[C@H]21 FKENQMMABCRJMK-RITPCOANSA-N 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/49—Analysis of texture based on structural texture description, e.g. using primitives or placement rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to the technical field of image analysis, in particular to an ore crushing effect evaluation method based on image processing. According to the method, ore gray level images are obtained, ore particle detection operators with different scales are built, ore appearance images are generated based on the ore particle detection operators, offset distances between ore particle pixel points to be detected and center ore particle pixel points are determined, iteration processing is conducted on the center ore particle pixel points, segmentation processing is conducted on the ore appearance images according to iteration results, ore particle images are generated, ore areas in the ore particle images are extracted, ore particle crushing effects are evaluated, and evaluation results are generated. The evaluation time of ore crushing effect can be effectively reduced, the image is convolved by the ore particle detection operator with multiple scales, the accuracy of texture structural analysis in the ore image can be improved, the reliability of the evaluation result is further improved, and the evaluation effect is enhanced.
Description
Technical Field
The disclosure relates to the technical field of image analysis, in particular to an ore crushing effect evaluation method based on image processing.
Background
The method comprises the steps of carrying out structural analysis on ore texture distribution in an ore image, evaluating the ore crushing effect, and calculating and detecting the particle size and the particle number of ore fragments by using a three-dimensional cloud image or enhancing the image by using an image denoising mode based on image processing in the related technology to obtain a clear ore particle image so as to carry out crushing effect detection according to image intelligent identification of the ore particle image.
In the mode, a large number of data sets are required to be marked on the three-dimensional cloud image, the calculation time is long easily, the image denoising mode is easy to lose texture details generated by fine ores, the structural analysis efficiency of textures on the ore image is poor, the accuracy is poor, and the evaluation effect is further insufficient.
Disclosure of Invention
In order to solve the technical problems of poor structural analysis efficiency and insufficient accuracy of texture of an ore image and insufficient evaluation effect in the related art, the purpose of the present disclosure is to provide an ore crushing effect evaluation method based on image processing, and the adopted technical scheme is as follows:
the disclosure provides an ore crushing effect evaluation method based on image processing, which comprises the following steps:
acquiring ore gray level images of crushed ores, constructing ore particle detection operators with different scales, and carrying out convolution processing on the ore gray level images based on the ore particle detection operators to generate ore appearance images;
according to the ore appearance image, determining a central ore particle pixel point, building an ore circle domain by taking the central ore particle pixel point as a midpoint, determining an ore particle pixel point to be detected in the ore circle domain, and determining an ore particle influence factor according to gray distribution characteristics around the ore particle pixel point to be detected and gray distribution characteristics around the central ore particle pixel point;
determining the offset distance between the ore particle pixel points to be detected and the central ore particle pixel points according to the ore particle influence factors, carrying out iterative processing on the central ore particle pixel points according to the offset distance, determining target ore particle pixel points after iterative convergence, and carrying out segmentation processing on the ore appearance image according to the target ore particle pixel points to generate an ore particle image;
and carrying out correction processing on the ore particle image according to the gray information of the ore particle image, extracting an ore region in the ore particle image, determining ore granularity information from the ore region, evaluating the ore particle crushing effect based on the ore granularity information, and generating an evaluation result.
Further, the ore gray level image is convolved based on the ore particle detection operator to generate an ore appearance image, comprising:
determining an ore profile image from an ore profile image acquisition formula, wherein the ore profile image acquisition formula comprises:
in the method, in the process of the invention,representing an image of the appearance of ore particles, < > x->Representing the total number of scale types for the ore particle detection operator,the gray level image of the ore is expressed in +.>Gray value at>Representing a scale size of +.>Is provided.
Further, determining an ore particle impact factor according to the gray scale distribution characteristics around the ore particle pixel points to be detected and the gray scale distribution characteristics around the central ore particle pixel points, including:
determining a central appearance characteristic value at a central ore particle pixel point and an appearance characteristic value to be detected at an ore particle pixel point to be detected; and determining the ore particle influence factor according to the central appearance characteristic value, the appearance characteristic value to be detected and the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected.
Further, configuring a first window to be tested with the center ore particle pixel point as a midpoint, configuring a second window to be tested with the center ore particle pixel point to be tested as a midpoint, and determining the center appearance characteristic value at the center ore particle pixel point and the appearance characteristic value to be tested at the ore particle pixel point to be tested includes:
determining a first gray value mean value of pixel points in a first window to be tested, determining a central local binary value of the central ore particle pixel point, and determining a central appearance characteristic value at the central ore particle pixel point according to the first gray value mean value and the central local binary value;
determining a second gray value average value of pixel points in a second window to be detected, determining a to-be-detected local binary value of the pixel points of the ore particles to be detected, and determining the feature value of the to-be-detected appearance at the pixel points of the ore particles to be detected according to the second gray value average value and the to-be-detected local binary value.
Further, determining an ore particle impact factor according to the center profile feature value, the to-be-measured profile feature value, and the euclidean distance between the center ore particle pixel point and the to-be-measured ore particle pixel point, including:
determining an ore particle impact factor using an ore particle impact factor formula, wherein the ore particle impact factor formula comprises:
in the method, in the process of the invention,representing a central ore particle pixel, +.>Representing pixel points of ore particles to be detected, +.>Representation ofOre particle influencing factor, < >>Base representing the logarithm of the natural number, +.>Represents the coordinate pairs at the pixel points of the central ore particles,/->Representing the coordinate pairs at the pixel points of the ore particles to be measured, < ->Indicating Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected, < ->Representing variances of all Euclidean distances calculated by pixel points of ore particles to be detected at all different positions in ore circle>Representing the central profile feature value, < >>Representing the feature value of the outline to be measured, < >>Representing the variance of the feature values of the appearance to be measured obtained by calculating pixel points of ore particles to be measured at all different positions in the ore circle, < + >>Representing the radius of the ore circle.
Further, determining an offset distance between the pixel point of the ore particle to be measured and the pixel point of the central ore particle according to the ore particle influence factor includes:
and traversing other ore particle pixel points to be detected except the center ore particle pixel point in the ore circle, and determining the offset distance according to the product of the ore particle influence factor and the Euclidean distance between the center ore particle pixel point and the ore particle pixel point to be detected.
Further, according to the gray information of the ore particle image, performing correction processing on the ore particle image to extract an ore region in the ore particle image, including:
determining second gray value average values of adjacent and different ore particle images, setting a gray value threshold value of the second gray value average values, determining a comparison result of the second gray value average values and the gray value threshold values, and merging the ore particle images with the second gray value average values smaller than or equal to the gray value threshold values to generate an ore region.
Further, the ore particle size information includes: ore particle size and ore particle size uniformity, determining ore particle size information, comprising:
the number of pixel points in the ore area is used as the size of the ore granularity, the uniformity of the ore granularity is calculated by using an ore granularity uniformity formula according to the size of the ore granularity, and the uniformity of the ore granularity is generated, wherein the ore granularity uniformity formula comprises:
in the method, in the process of the invention,represents the uniformity of the particle size of ore, +.>Representing the number of ore areas in the ore gray image, a +.>Represents the size of ore particle size,/->The average value of the size of ore particle in the ore gray scale image is represented.
The method has the following beneficial effects:
according to the method, ore gray level images of broken ores are obtained, ore particle detection operators with different scales are built, and convolution processing is carried out on the ore gray level images based on the ore particle detection operators to generate ore appearance images; according to the ore appearance image, determining a central ore particle pixel point, building an ore circle domain by taking the central ore particle pixel point as a midpoint, determining an ore particle pixel point to be detected in the ore circle domain, and determining an ore particle influence factor according to gray distribution characteristics around the ore particle pixel point to be detected and gray distribution characteristics around the central ore particle pixel point; determining the offset distance between the ore particle pixel points to be detected and the central ore particle pixel points according to the ore particle influence factors, carrying out iterative processing on the central ore particle pixel points according to the offset distance, determining target ore particle pixel points after iterative convergence, and carrying out segmentation processing on the ore appearance image according to the target ore particle pixel points to generate an ore particle image; and carrying out correction processing on the ore particle image according to the gray information of the ore particle image, extracting an ore region in the ore particle image, determining ore granularity information from the ore region, evaluating the ore particle crushing effect based on the ore granularity information, and generating an evaluation result. The method has the advantages that the convolution processing of the images is realized by using the ore particle detection operators with various different scales, the periphery of the center ore particle pixel point is analyzed according to the ore circle area, the structural analysis of textures in the ore image is realized according to the segmented ore particle image, the analysis time in the structural analysis process is effectively reduced, meanwhile, the convolution processing is carried out on the images by setting the ore particle detection operators with multiple scales, so that the influence of fine ores on the structural analysis effect evaluation can be effectively reserved, the accuracy of the texture structural analysis in the ore image is improved, the reliability of the evaluation result is further improved, and the evaluation effect is enhanced.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings required for the embodiments or the prior art description, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
FIG. 1 is a flow chart of an image processing-based ore crushing effect evaluation method according to one embodiment of the present disclosure;
FIG. 2 is a schematic diagram of the structure of an ore particle detection operator provided in one embodiment of the present disclosure;
fig. 3 is a schematic structural view of an ore round area provided in one embodiment of the present disclosure.
Detailed Description
In order to further describe the technical means and effects adopted by the present disclosure to achieve the preset purposes, the following detailed description refers to specific embodiments, structures, features and effects of a quality maintaining method for a novel sulbactam acid extraction process according to the present disclosure, which are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
The following specifically describes a specific scheme of an ore crushing effect evaluation method based on image processing provided in the present disclosure with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an ore crushing effect evaluation method based on image processing according to an embodiment of the present disclosure is shown, where the method includes:
s101: and acquiring ore gray level images of crushed ores, constructing ore particle detection operators with different scales, and carrying out convolution processing on the ore gray level images based on the ore particle detection operators to generate ore appearance images.
In embodiments of the present disclosure, an industrial camera may be used to capture raw images of crushed ore, such as by placing the industrial camera over an ore conveyor belt, by configuring a light source.
In the embodiment of the disclosure, image processing may be performed on an original image after the original image is acquired to generate an ore gray image, where the image processing may specifically include image denoising and image graying processing, in the embodiment of the disclosure, image denoising processing may be implemented by using a double-sideband filtering manner, and graying processing may be performed on the denoised image by using a weighted average manner to generate an ore gray image, and of course, the image processing in the embodiment of the disclosure may also include multiple image preprocessing manners to generate an ore gray image with better imaging effect, which is not limited thereto.
The ore particle detection operator is used for carrying out convolution processing on an ore gray image, and is different from the traditional edge detection operator, and the ore particle detection operator in the embodiment of the disclosure can be preset with various scales. As shown in fig. 2, fig. 2 is a schematic structural diagram of an ore particle detection operator according to an embodiment of the present disclosure, by presetting、、/>And (3) the ore particle detection operators with various dimensions are used for respectively processing the ore gray level images, so that the reliability of the ore appearance images can be improved through multiple operations and multi-scale processing.
Further, in an embodiment of the present disclosure, performing convolution processing on an ore gray image based on an ore particle detection operator to generate an ore profile image includes:
determining an ore profile image from an ore profile image acquisition formula, wherein the ore profile image acquisition formula comprises:
in the method, in the process of the invention,representing an image of the appearance of ore particles, < > x->Representing the total number of scale types for the ore particle detection operator,the gray level image of the ore is expressed in +.>Gray value at>Representing a scale size of +.>Is provided.
In the embodiment of the disclosure, the outline information in the ore gray level image is extracted through convolution of coordinates of a point to be measured in the ore gray level image and an ore particle detection operator corresponding to the point to be measured, so that an ore appearance image is obtained.
In the embodiment of the disclosure, the ore gray level images can be respectively convolved by using the ore particle detection operators with different sizes, the moving step length of the ore particle detection operators is set to be 1, the convolution processing is performed by sliding the ore particle detection operators in the ore gray level images, the outline information of ore particles in the ore gray level images is obtained, and the ore appearance images are generated.
According to the embodiment of the disclosure, the ore appearance image is obtained in a convolution mode, the gray level of ore particles is reserved in the ore appearance image, the space integral information and the outline information among different ore particles are obtained, and the detection precision of the ore appearance image is improved.
S102: according to the ore appearance image, determining a central ore particle pixel point, constructing an ore circle domain by taking the central ore particle pixel point as a midpoint, determining the ore particle pixel point to be detected in the ore circle domain, and determining an ore particle influence factor according to gray distribution characteristics around the ore particle pixel point to be detected and gray distribution characteristics around the central ore particle pixel point.
In the embodiment of the disclosure, any point in the ore appearance image can be randomly selected as a central ore particle pixel point, a circular area with a specific radius is set as an ore circular area by taking the central ore particle pixel point as a midpoint, and the clustering analysis of the ore particle pixel points in the ore appearance image is realized through the ore circular area.
The influence factors of the ore particles are the influence factors of the pixel points at different positions in the ore circle on the pixel points of the central ore particles. In the embodiment of the disclosure, any pixel point except the central ore particle pixel point can be determined from the ore circle domain as the ore particle pixel point to be detected, and the gray distribution characteristics around the ore particle pixel point to be detected and the gray distribution characteristics around the central ore particle pixel point are respectively determined, so that the ore particle influence factors are determined.
Further, in the embodiment of the disclosure, a central appearance characteristic value at a central ore particle pixel point and an appearance characteristic value to be measured at an ore particle pixel point to be measured are determined; according to the central appearance characteristic value, the appearance characteristic value to be measured and the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be measured, the ore particle influence factor is determined, and as the ore particle influence factor is determined according to the central appearance characteristic value, the appearance characteristic value to be measured and the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be measured, the appearance characteristic information such as the surface roughness and the gray level of the ore particles can be effectively considered, so that the accuracy and the objectivity of the ore particle influence factor are ensured, and the reliability of cluster analysis is improved.
In the embodiment of the disclosure, the coordinates of the central ore particle pixel point in the ore appearance image and the coordinates of the ore particle pixel point to be detected in the ore appearance image can be determined, and then the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected is determined according to the two coordinates.
Further, configuring a first window to be tested with the center ore particle pixel point as a midpoint, configuring a second window to be tested with the center ore particle pixel point to be tested as a midpoint, and determining the center appearance characteristic value at the center ore particle pixel point and the appearance characteristic value to be tested at the ore particle pixel point to be tested includes: determining a first gray value mean value of pixel points in a first window to be tested, determining a central local binary value of the central ore particle pixel point, and determining a central appearance characteristic value at the central ore particle pixel point according to the first gray value mean value and the central local binary value; determining a second gray value average value of pixel points in a second window to be detected, determining a to-be-detected local binary value of the pixel points of the ore particles to be detected, and determining the feature value of the to-be-detected appearance at the pixel points of the ore particles to be detected according to the second gray value average value and the to-be-detected local binary value.
Wherein the first window to be measured is a window for determining the range of the pixel point of the central ore particle, and the first window to be measured can be preset with a specific size, such asThe size is not limited, and the gray value average value of all pixel points in the first window to be tested is used as the first gray value average value.
The central local binary value is a local binary pattern (Local Binary Patterns, LBP) value corresponding to the central ore particle pixel point, and the pixel point in the first window to be tested can be binary processed to obtain the central local binary value, and the calculation of the local binary value is a known technology and will not be repeated herein.
In the embodiment of the disclosure, the pixel points of the central ore particles can be calculated as given that the same ore particle surfaces should have the same surface roughnessLBP value of the first window to be measured, and obtaining the central ore particle pixel point as +.>LBP value decimal size ++of the first window to be tested>And then, obtaining a central appearance characteristic value through a central appearance characteristic value formula, wherein the central appearance characteristic value formula comprises the following components:
in the method, in the process of the invention,representing the central profile feature value, < >>Represents a first gray value mean +.>And the LBP value decimal value of the first window to be tested, namely the central local binary value, takes the product of the first gray value mean value and the central local binary value as the central appearance characteristic value.
Similarly, a second window to be measured can be determined by taking the pixel point of the ore particle to be measured as the center, the second window to be measured can have the same size as the first window to be measured, and the second gray value mean value and the local binary value to be measured are determined through the second window to be measured, so that the appearance characteristic value to be measured at the pixel point of the ore particle to be measured is determined.
Further, in an embodiment of the disclosure, determining an ore particle impact factor according to a central profile feature value, a profile feature value to be measured, and an euclidean distance between a central ore particle pixel point and an ore particle pixel point to be measured, includes:
determining an ore particle impact factor using an ore particle impact factor formula, wherein the ore particle impact factor formula comprises:
in the method, in the process of the invention,representing a central ore particle pixel, +.>Representing pixel points of ore particles to be detected, +.>Representing the ore particle influencing factor,/->Base representing the logarithm of the natural number, +.>Represents the coordinate pairs at the pixel points of the central ore particles,/->Representing the coordinate pairs at the pixel points of the ore particles to be measured, < ->Indicating Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected, < ->Representing variances of all Euclidean distances calculated by pixel points of ore particles to be detected at all different positions in ore circle>Representing the central profile feature value, < >>Representing the feature value of the outline to be measured, < >>Representing the variance of the feature values of the appearance to be measured obtained by calculating pixel points of ore particles to be measured at all different positions in the ore circle, < + >>Representing the radius of the ore circle.
In one embodiment of the present disclosure, fig. 3 is a schematic structural diagram of an ore round domain provided in one embodiment of the present disclosure, in fig. 3,representing a central ore particle pixel, +.>Representing pixel points of ore particles to be detected, +.>Representing the ore particle influencing factor,/->The radius of the ore circle field is indicated, the solid line circle indicates the ore circle field, and the dotted line circle indicates the radius +.>As shown in FIG. 3, in the pixel point of the ore particles to be measured +.>Pixel point of central ore particle>The distance between them exceeds the radius of the ore circle>The ore particle influence factor of the pixel point of the ore particle to be detected on the pixel point of the central ore particle can be determined>In the pixel point of the ore particle to be measured +.>Pixel point of central ore particle>The distance between the two is not more than +.>And the two ore particle pixel points can be distributed at a space position at a relatively short distance, so that the two ore particle pixel points are likely to be located in the same ore block, namely the influence of the ore particle pixel point to be measured on the central ore particle pixel point is relatively large, the calculation amount can be effectively reduced by setting a strict distance penalty, meanwhile, the calculation accuracy is ensured, the interference of the remote pixel point on the ore particle influence factor is reduced, and the accuracy of determining the ore particle influence factor is improved.
S103: determining the offset distance between the ore particle pixel points to be detected and the central ore particle pixel points according to the ore particle influence factors, carrying out iterative processing on the central ore particle pixel points according to the offset distance, determining target ore particle pixel points after iterative convergence, and carrying out segmentation processing on the ore appearance image according to the target ore particle pixel points to generate an ore particle image.
In the embodiment of the disclosure, the offset distance between the pixel point of the ore particle to be measured and the pixel point of the central ore particle can be determined according to the influence factor of the ore particle, and it can be understood that in the ore circle domain, the pixel points of the same ore particle, the pixel points of different ore particles and the meaningless pixel points of the background area may occur. Therefore, the influence degree of the ore particle pixel points at different positions on the offset distance of the center ore particle pixel point at the center position of the ore particle is different, and the influence of the offset distance of the ore particle pixel points to be measured at different positions on the center ore particle pixel point is measured through calculation of the ore particle influence factors.
Further, in the embodiment of the disclosure, other ore particle pixels to be measured in the ore circle except for the center ore particle pixel are traversed, and the offset distance is determined according to the product of the ore particle influence factor and the euclidean distance between the center ore particle pixel and the ore particle pixel to be measured.
In the embodiment of the disclosure, the offset distance may be determined using an offset distance calculation formula, where the offset distance calculation formula is:
in the method, in the process of the invention,represents the offset distance +.>Pixel point for indicating ore particles except center in ore circle>Besides, the pixel points of the ore particles to be detected at all other positions are +.>Total number of possible positions, < >>Represents the coordinate pairs at the pixel points of the central ore particles,/->Representing the coordinate pairs at the pixel points of the ore particles to be measured, < ->And expressing Euclidean distance between the center ore particle pixel point and the ore particle pixel point to be measured.
According to the embodiment of the disclosure, through the offset distance calculation formula, the ore particle influence factors between the ore particle pixel points to be measured and the central ore particle pixel points and the Euclidean distance between the central ore particle pixel points and the ore particle pixel points to be measured can be comprehensively considered, so that the error analysis of the distance factors on the central pixel points is realized, and the accuracy of the determination of the central pixel points is ensured.
In the embodiment of the disclosure, the central ore particle pixel point can be subjected to iterative correction through the offset distance to obtain a plurality of target ore particle pixel points, the target ore particle pixel points represent the pixel points at the positions of the ore particles, and the ore appearance image can be subjected to segmentation processing according to the plurality of target ore particle pixel points to generate the ore particle image.
In the embodiment of the disclosure, the positions of the central ore particle pixel points are updated, the algorithm is considered to be converged at the moment through multiple iterations until the spatial positions of the central ore particle pixel points are not transformed, clustering is completed, and the obtained positions of all the central ore particle pixel points are recorded as the pixel points of the same ore particle, namely target ore particle pixel points. The plurality of target ore particle pixel points of different types can be segmented by traversing the whole ore particle appearance image, and the plurality of ore particle images are obtained by segmenting according to the types of the target ore particle pixel points.
S104: and carrying out correction processing on the ore particle image according to the gray information of the ore particle image, extracting an ore region in the ore particle image, determining ore granularity information from the ore region, evaluating the ore particle crushing effect based on the ore granularity information, and generating an evaluation result.
In the embodiment of the disclosure, after the ore appearance image obtained by the acquisition processing is segmented by the segmentation algorithm, the geometric appearance of the surface of the ore particles obtained by the crushing is irregular and not smooth, so that an obvious boundary line on the same piece of ore particles may appear in the imaging process, and the ore particles are mistakenly segmented, so that the mistakenly segmented ore particle image needs to be corrected for obtaining a better segmentation effect.
Further, in the embodiment of the disclosure, a second gray value average value of adjacent and different ore particle images is determined, a gray value threshold value of the second gray value average value is set, a comparison result of the second gray value average value and the gray value threshold value is determined, and the ore particle images with the second gray value average value smaller than or equal to the gray value threshold value are combined to generate an ore region.
The combination of the ore particle images is realized through the comparison of the second gray value mean value and the gray value threshold value, so that two ore particle images representing the same ore particle can be accurately combined, the accuracy of image segmentation is enhanced, and the reliability of subsequent crushing effect evaluation is ensured.
The second gray value average value is a gray value average value generated by jointly calculating at least two adjacent and different ore particle images, and in the embodiment of the present disclosure, the gray value average value between the two adjacent and different ore particle images may be set as the second gray value average value.
In the embodiment of the disclosure, the setting of the gray value threshold may be adjusted according to the actual image situation, or a fixed empirical value may be taken, for example, the empirical value is taken to be 190, and two ore particle images with the second gray value average value less than or equal to 190 are combined to generate an ore region, which represents the same ore particle in the ore region.
Optionally, in an embodiment of the disclosure, the ore granularity information includes: ore particle size and ore particle size uniformity, determining ore particle size information, comprising:
the number of pixel points in the ore area is used as the size of the ore granularity, the uniformity of the ore granularity is calculated by using an ore granularity uniformity formula according to the size of the ore granularity, and the uniformity of the ore granularity is generated, wherein the ore granularity uniformity formula comprises:
in the method, in the process of the invention,represents the uniformity of the particle size of ore, +.>Representing the number of ore areas in the ore gray image, a +.>Represents the size of ore particle size,/->The average value of the size of ore particle in the ore gray scale image is represented.
In the embodiment of the disclosure, the uniformity of the particle size of the ore is determined according to the information such as the number of the ore areas and the particle size of the ore, and the uniformity of the particle size of the ore and the particle size of the ore are used as evaluation indexes for evaluating the crushing effect of the ore particles to generate an evaluation result. For example, if the size of the ore particle satisfies the production requirement and the uniformity of the ore particle size is high, it means that the effect of crushing the ore particles is better, otherwise, it means that the effect of crushing the ore particles is insufficient.
In the embodiment, ore gray level images of broken ores are obtained, ore particle detection operators with different scales are built, and convolution processing is carried out on the ore gray level images based on the ore particle detection operators to generate ore appearance images; according to the ore appearance image, determining a central ore particle pixel point, building an ore circle domain by taking the central ore particle pixel point as a midpoint, determining an ore particle pixel point to be detected in the ore circle domain, and determining an ore particle influence factor according to gray distribution characteristics around the ore particle pixel point to be detected and gray distribution characteristics around the central ore particle pixel point; determining the offset distance between the ore particle pixel points to be detected and the central ore particle pixel points according to the ore particle influence factors, carrying out iterative processing on the central ore particle pixel points according to the offset distance, determining target ore particle pixel points after iterative convergence, and carrying out segmentation processing on the ore appearance image according to the target ore particle pixel points to generate an ore particle image; and carrying out correction processing on the ore particle image according to the gray information of the ore particle image, extracting an ore region in the ore particle image, determining ore granularity information from the ore region, evaluating the ore particle crushing effect based on the ore granularity information, and generating an evaluation result. The method has the advantages that the convolution processing of the images is realized by using the ore particle detection operators with various different scales, the periphery of the center ore particle pixel point is analyzed according to the ore circle area, the structural analysis of textures in the ore image is realized according to the segmented ore particle image, the analysis time in the structural analysis process is effectively reduced, meanwhile, the convolution processing is carried out on the images by setting the ore particle detection operators with multiple scales, so that the influence of fine ores on the structural analysis effect evaluation can be effectively reserved, the accuracy of the texture structural analysis in the ore image is improved, the reliability of the evaluation result is further improved, and the evaluation effect is enhanced.
It should be noted that: the foregoing sequence of the embodiments of the present disclosure is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present disclosure is not intended to limit the disclosure, but rather to enable any modification, equivalent replacement, improvement or the like, which fall within the spirit and principles of the present disclosure.
Claims (4)
1. An ore crushing effect evaluation method based on image processing, characterized by comprising the following steps:
acquiring ore gray level images of crushed ores, constructing ore particle detection operators with different scales, and carrying out convolution processing on the ore gray level images based on the ore particle detection operators to generate ore appearance images;
according to the ore appearance image, determining a central ore particle pixel point, building an ore circle domain by taking the central ore particle pixel point as a midpoint, determining an ore particle pixel point to be detected in the ore circle domain, and determining an ore particle influence factor according to gray distribution characteristics around the ore particle pixel point to be detected and gray distribution characteristics around the central ore particle pixel point;
determining the offset distance between the ore particle pixel point to be detected and the central ore particle pixel point according to the ore particle influence factor, performing iterative processing on the central ore particle pixel point according to the offset distance, determining a target ore particle pixel point after iterative convergence, and performing segmentation processing on the ore appearance image according to the target ore particle pixel point to generate an ore particle image;
correcting the ore particle image according to the gray information of the ore particle image, extracting an ore region in the ore particle image, determining ore granularity information from the ore region, evaluating the ore particle crushing effect based on the ore granularity information, and generating an evaluation result;
the ore particle detection operator is based on the ore gray level image is convolved to generate an ore appearance image, and the method comprises the following steps:
determining the ore profile image from an ore profile image acquisition formula, wherein the ore profile image acquisition formula comprises:
in the method, in the process of the invention,representing an image of the appearance of ore particles, < > x->Representing the total number of scale types of the ore particle detection operator, < +.>The gray level image of the ore is expressed in +.>Gray value at>Representing a scale size of +.>Ore particle detection operators of (a);
the determining of the ore particle influencing factor according to the gray scale distribution characteristics around the ore particle pixel points to be detected and the gray scale distribution characteristics around the central ore particle pixel points comprises the following steps:
determining a central appearance characteristic value at the central ore particle pixel point and an appearance characteristic value to be detected at the ore particle pixel point to be detected; determining the ore particle influence factor according to the central appearance characteristic value, the appearance characteristic value to be detected and the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected;
the method for determining the central appearance characteristic value of the central ore particle pixel point and the appearance characteristic value to be measured of the ore particle pixel point to be measured comprises the steps of:
determining a first gray value mean value of pixel points in the first window to be tested, determining a central local binary value of the central ore particle pixel point, and determining a central appearance characteristic value at the central ore particle pixel point according to the first gray value mean value and the central local binary value;
determining a second gray value average value of pixel points in the second window to be detected, determining a to-be-detected local binary value of the pixel points of the ore particles to be detected, and determining an appearance characteristic value to be detected at the pixel points of the ore particles to be detected according to the second gray value average value and the to-be-detected local binary value;
determining the ore particle influencing factor according to the center appearance characteristic value, the appearance characteristic value to be detected and the Euclidean distance between the center ore particle pixel point and the ore particle pixel point to be detected, including:
determining the ore particle impact factor using an ore particle impact factor formula, wherein the ore particle impact factor formula comprises:
in the method, in the process of the invention,representing a central ore particle pixel, +.>Representing pixel points of ore particles to be detected, +.>Representing the ore particle influencing factor,/->Base representing the logarithm of the natural number, +.>Represents the coordinate pairs at the pixel points of the central ore particles,/->Representing the coordinate pairs at the pixel points of the ore particles to be measured, < ->Indicating Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected, < ->Representing variances of all Euclidean distances calculated by pixel points of ore particles to be detected at all different positions in ore circle>Representing the central profile feature value, < >>Representing the feature value of the outline to be measured, < >>Representing the variance of the feature values of the appearance to be measured obtained by calculating pixel points of ore particles to be measured at all different positions in the ore circle, < + >>Representing the radius of the ore circle;
determining the offset distance between the pixel point of the ore particle to be detected and the pixel point of the central ore particle according to the ore particle influence factor comprises the following steps:
traversing other ore particle pixel points to be detected except the central ore particle pixel point in the ore circle, and determining an offset distance according to the product of the ore particle influence factor and the Euclidean distance between the central ore particle pixel point and the ore particle pixel point to be detected;
and correcting the ore particle image according to the gray information of the ore particle image, and extracting an ore region in the ore particle image, wherein the method comprises the following steps:
determining second gray value average values of adjacent and different ore particle images, setting a gray value threshold value of the second gray value average values, determining a comparison result of the second gray value average values and the gray value threshold value, and merging the ore particle images with the second gray value average values smaller than or equal to the gray value threshold value to generate the ore region.
2. The method for evaluating an ore crushing effect based on image processing according to claim 1, wherein the ore granularity information includes: ore particle size and ore particle size uniformity, the determining ore particle size information comprising:
the number of pixel points in the ore area is used as the size of the ore granularity, the uniformity of the ore granularity is calculated by using an ore granularity uniformity formula according to the size of the ore granularity, and the uniformity of the ore granularity is generated, wherein the ore granularity uniformity formula comprises:
in the method, in the process of the invention,represents the uniformity of the particle size of ore, +.>Representing the number of ore areas in the ore gray image, a +.>Represents the size of ore particle size,/->The average value of the size of ore particle in the ore gray scale image is represented.
3. The method for evaluating an ore crushing effect based on image processing according to claim 1, wherein said determining a center profile characteristic value at a pixel point of said center ore particles based on said first gray value average and said center local binary value comprises:
and calculating the product of the first gray value mean value and the central local binary value as a central appearance characteristic value.
4. The method for evaluating an ore crushing effect based on image processing according to claim 1, wherein the determining the feature value of the appearance to be measured at the pixel point of the ore particle to be measured according to the second gray value average value and the local binary value to be measured comprises:
and calculating the product of the second gray value mean value and the local binary value to be measured as the appearance characteristic value to be measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092828.XA CN116823827B (en) | 2023-08-29 | 2023-08-29 | Ore crushing effect evaluation method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092828.XA CN116823827B (en) | 2023-08-29 | 2023-08-29 | Ore crushing effect evaluation method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116823827A CN116823827A (en) | 2023-09-29 |
| CN116823827B true CN116823827B (en) | 2023-11-10 |
Family
ID=88120658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311092828.XA Active CN116823827B (en) | 2023-08-29 | 2023-08-29 | Ore crushing effect evaluation method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823827B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2074706A1 (en) * | 1991-08-30 | 1993-03-01 | Richard D. Grove | Method and apparatus for image analysis of composite ores |
| RU2013118786A (en) * | 2013-04-23 | 2014-10-27 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Южно-Российский государственный университет экономики и сервиса" (ФГБОУ ВПО "ЮРГУЭС") | METHOD FOR DETERMINING THE PARAMETERS OF WEIGHTED PARTICLES OF AN ARBITRARY FORM |
| CN104657988A (en) * | 2015-02-04 | 2015-05-27 | 中国矿业大学 | Image segmentation method for micro-fine cohesive core particles based on angular point and curvature detection |
| FI20155909A (en) * | 2015-12-01 | 2017-06-02 | Outotec Finland Oy | Method and arrangement for controlling the comminution process |
| WO2017093610A1 (en) * | 2015-12-01 | 2017-06-08 | Outotec (Finland) Oy | A method and an arrangement for controlling of a comminution process having a grinding circuit |
| CN109785378A (en) * | 2018-03-21 | 2019-05-21 | 威海晶合数字矿山技术有限公司 | A kind of ore grain size online detection instrument based on atlas image algorithm analytical technology |
| CN111047555A (en) * | 2019-11-13 | 2020-04-21 | 鞍钢集团矿业有限公司 | Ore image granularity detection algorithm based on image processing technology |
| CN113240663A (en) * | 2021-05-31 | 2021-08-10 | 西安建筑科技大学 | Conveyor belt ore granularity detection method based on edge response fusion algorithm |
| CN115272319A (en) * | 2022-09-27 | 2022-11-01 | 江苏亚振钻石有限公司 | Ore granularity detection method |
| CN115841490A (en) * | 2023-02-23 | 2023-03-24 | 山东泗水山岭石材厂 | Mining process ore particle segmentation method and system based on image processing |
| WO2023092965A1 (en) * | 2021-11-23 | 2023-06-01 | 赣州好朋友科技有限公司 | Ore image segmentation method and device and computer-readable storage medium |
-
2023
- 2023-08-29 CN CN202311092828.XA patent/CN116823827B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2074706A1 (en) * | 1991-08-30 | 1993-03-01 | Richard D. Grove | Method and apparatus for image analysis of composite ores |
| RU2013118786A (en) * | 2013-04-23 | 2014-10-27 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Южно-Российский государственный университет экономики и сервиса" (ФГБОУ ВПО "ЮРГУЭС") | METHOD FOR DETERMINING THE PARAMETERS OF WEIGHTED PARTICLES OF AN ARBITRARY FORM |
| CN104657988A (en) * | 2015-02-04 | 2015-05-27 | 中国矿业大学 | Image segmentation method for micro-fine cohesive core particles based on angular point and curvature detection |
| FI20155909A (en) * | 2015-12-01 | 2017-06-02 | Outotec Finland Oy | Method and arrangement for controlling the comminution process |
| WO2017093610A1 (en) * | 2015-12-01 | 2017-06-08 | Outotec (Finland) Oy | A method and an arrangement for controlling of a comminution process having a grinding circuit |
| CN109785378A (en) * | 2018-03-21 | 2019-05-21 | 威海晶合数字矿山技术有限公司 | A kind of ore grain size online detection instrument based on atlas image algorithm analytical technology |
| CN111047555A (en) * | 2019-11-13 | 2020-04-21 | 鞍钢集团矿业有限公司 | Ore image granularity detection algorithm based on image processing technology |
| CN113240663A (en) * | 2021-05-31 | 2021-08-10 | 西安建筑科技大学 | Conveyor belt ore granularity detection method based on edge response fusion algorithm |
| WO2023092965A1 (en) * | 2021-11-23 | 2023-06-01 | 赣州好朋友科技有限公司 | Ore image segmentation method and device and computer-readable storage medium |
| CN115272319A (en) * | 2022-09-27 | 2022-11-01 | 江苏亚振钻石有限公司 | Ore granularity detection method |
| CN115841490A (en) * | 2023-02-23 | 2023-03-24 | 山东泗水山岭石材厂 | Mining process ore particle segmentation method and system based on image processing |
Non-Patent Citations (4)
| Title |
|---|
| Analysis of the Process of Washing Diamond-Bearing Ore After Crushing as an Object of Automation;Yu.A. Podkamenniy等;2020 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon);全文 * |
| 基于形态学优化处理的标记符分水岭矿石图像分割;蔡改贫;刘占;汪龙;张丹荣;;科学技术与工程(第23期);全文 * |
| 基于机器视觉的矿石粒度检测方法比较研究;马连铭;姬建钢;杜波;刘俊;郭庶;;矿山机械(第10期);全文 * |
| 基于颗粒流数值方法的岩石压剪破坏细观特征研究;张钦礼;韩森;;安全与环境学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116823827A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115861135B (en) | Image enhancement and recognition method applied to panoramic detection of box body | |
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| CN110286124B (en) | Machine vision-based refractory brick measuring system | |
| CN107798326B (en) | Contour vision detection method | |
| CN109580630B (en) | Visual inspection method for defects of mechanical parts | |
| CN113450307A (en) | Product edge defect detection method | |
| CN115829883A (en) | Surface image denoising method for dissimilar metal structural member | |
| CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
| JP6099479B2 (en) | Crack detection method | |
| CN108376403B (en) | Grid colony image segmentation method based on Hough circle transformation | |
| CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
| CN110288571B (en) | High-speed rail contact net insulator abnormity detection method based on image processing | |
| CN111415376B (en) | Automobile glass subpixel contour extraction method and automobile glass detection method | |
| CN109559324A (en) | A kind of objective contour detection method in linear array images | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| CN110222661B (en) | Feature extraction method for moving target identification and tracking | |
| CN116309577B (en) | Intelligent detection method and system for high-strength conveyor belt materials | |
| CN114067147B (en) | Ship target confirmation method based on local shape matching | |
| CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
| CN116168025B (en) | Oil curtain type fried peanut production system | |
| CN115797813B (en) | Water environment pollution detection method based on aerial image | |
| CN108596151B (en) | Method for rapidly extracting ship target slice in large-scene SAR image | |
| CN116703251A (en) | Rubber ring production quality detection method based on artificial intelligence | |
| CN107516315B (en) | Tunneling machine slag tapping monitoring method based on machine vision | |
| CN115880699A (en) | Food packaging bag detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |