CN113034573A - Ball granule diameter detection method and system - Google Patents
Ball granule diameter detection method and system Download PDFInfo
- Publication number
- CN113034573A CN113034573A CN202110356547.5A CN202110356547A CN113034573A CN 113034573 A CN113034573 A CN 113034573A CN 202110356547 A CN202110356547 A CN 202110356547A CN 113034573 A CN113034573 A CN 113034573A
- Authority
- CN
- China
- Prior art keywords
- pellet
- image
- characteristic
- generate
- pixel
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 239000008187 granular material Substances 0.000 title claims description 16
- 239000008188 pellet Substances 0.000 claims abstract description 298
- 238000009826 distribution Methods 0.000 claims abstract description 74
- 239000002245 particle Substances 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims abstract description 15
- 230000009466 transformation Effects 0.000 claims description 27
- 238000010586 diagram Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 description 11
- 238000005453 pelletization Methods 0.000 description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 239000012141 concentrate Substances 0.000 description 4
- 229910052742 iron Inorganic materials 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 239000000446 fuel Substances 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 239000007791 liquid phase Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005245 sintering Methods 0.000 description 3
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052595 hematite Inorganic materials 0.000 description 1
- 239000011019 hematite Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- LIKBJVNGSGBSGK-UHFFFAOYSA-N iron(3+);oxygen(2-) Chemical compound [O-2].[O-2].[O-2].[Fe+3].[Fe+3] LIKBJVNGSGBSGK-UHFFFAOYSA-N 0.000 description 1
- SZVJSHCCFOBDDC-UHFFFAOYSA-N iron(II,III) oxide Inorganic materials O=[Fe]O[Fe]O[Fe]=O SZVJSHCCFOBDDC-UHFFFAOYSA-N 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000001953 recrystallisation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- QAOWNCQODCNURD-UHFFFAOYSA-N sulfuric acid group Chemical group S(O)(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
- G01N15/0227—Investigating particle size or size distribution by optical means using imaging; using holography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Dispersion Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for detecting the diameter of a pellet, belonging to the technical field of target detection.A pellet image is firstly obtained, an interested area is extracted to obtain a pellet characteristic image, then the pellet characteristic image is sequentially subjected to gray level conversion, filtering, self-adaptive binarization, distance conversion, denoising and watershed conversion to obtain a pellet profile distribution map, the center of each pellet is determined, and the particle diameter of each pellet is obtained according to the center of each pellet; according to the invention, the pellet characteristic image is subjected to filtering, self-adaptive binarization, distance conversion, denoising, watershed conversion and other processing, so that the detection and identification capability of the pellet image is improved, the particle size of each pellet is obtained according to the center of each pellet, the particle size of the pellet can be calculated in real time, and the time and labor are saved.
Description
Technical Field
The invention belongs to the technical field of target detection, and particularly relates to a method and a system for detecting the diameter of a ball granule.
Background
The pellet has better cold strength, reducibility and granularity composition. Pellets and sinter are also important blast furnace burden in the iron and steel industry, and can together form a better burden structure. Also applied to non-ferrous metal smelting.
Along with the continuous exploitation of earth resources and the shortage of rich ores, the utilization of lean ore resources must be continuously expanded, and the improvement of the beneficiation technology can economically sort out high-grade fine ground iron concentrate, wherein the granularity of the fine ground iron concentrate is further reduced from minus 200 meshes (less than 0.074mm) to minus 325 meshes (less than 0.044 mm). The superfine concentrate is not beneficial to sintering, has poor air permeability, and influences the improvement of the yield and the quality of sintered ore, but is very suitable for being treated by a pelletizing method because the superfine concentrate is easy to be pelletized, the finer the granularity is, the better the pelletizing property is, and the higher the strength of the pellet is.
The finished ore varies in shape: the sintered ore is irregular porous lump ore, and the pellet is regular 10-25 mm more uniform in granularity, more in micropores, good in reducibility, high in strength, easy to store and beneficial to strengthening blast furnace production.
The raw materials suitable for the treatment by the pelletizing method are expanded from magnetite to hematite, limonite, various iron-containing dusts, chemical sulfuric acid residues and the like; from the product, not only the conventional oxidized pellet can be manufactured, but also the reduced pellet, the metallized pellet and the like can be produced; meanwhile, the pelletizing method is suitable for the recovery of nonferrous metals and is beneficial to the development of comprehensive utilization.
The mechanism of consolidation into a mass is different: the sintered ore is consolidated by liquid phase, and a certain amount of liquid phase is required to be generated in order to ensure the strength of the sintered ore, so that fuel must be contained in the mixture to provide a heat source for the sintering process. The pellet ore is mainly solidified by high-temperature recrystallization of the ore powder particles, a liquid phase does not need to be generated, heat is provided by fuel combustion in a roasting furnace, and fuel is not added into the mixture.
The production process is different: the mixing and pelletizing of the sintering material are carried out simultaneously in a mixer, the pelletizing is incomplete, and the mixture still contains a considerable amount of small particles which are not pelletized. In the pellet production process, special pelletizing procedures and equipment (pelletizing discs and the like) are required, all mixed materials are formed into 10-25 mm pellets, and small pellets smaller than 10mm are screened out for re-pelletizing. Particle size screening is a crucial step.
The particle size detection is a key link in the pellet production process, and the accuracy of the particle size detection and statistics provides a powerful reference for the pellet production process.
In the existing pellet particle size detection, pellets with different particle sizes are screened from large to small by using sieves with different diameters, and the number of the screened particulate matters under each diameter is counted so as to obtain the distribution condition of the pellet particle sizes. Although the method is simple and feasible, the particle size of the pellets cannot be counted in real time, and the method is time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to provide a pellet diameter detection method and a pellet diameter detection system, and aims to solve the problems that the existing pellet diameter detection method cannot count pellet diameters in real time and wastes time and labor.
In order to achieve the purpose, the invention adopts the technical scheme that: a ball granule diameter detection method comprises the following steps:
step 1: acquiring a pellet image acquired by an industrial camera;
step 2: extracting an interested area on the pellet image to generate a pellet characteristic image;
and step 3: carrying out gray level transformation on the pellet characteristic image to generate a pellet characteristic gray level image;
and 4, step 4: filtering the pellet characteristic gray image to generate a filtered pellet characteristic gray image;
and 5: carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
step 6: carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
and 7: denoising the pellet distribution binary image to generate a noise-removed pellet distribution binary image;
and 8: extracting the outline of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet outline distribution map;
and step 9: obtaining the center of each pellet according to the pellet profile distribution map;
step 10: and fitting the pellets on the pellet profile distribution diagram according to the centers of the pellets to obtain the particle sizes of the pellets.
Preferably, the step 4: filtering the pellet characteristic gray image to generate a filtered pellet characteristic gray image, wherein the filtering comprises the following steps:
taking each pixel in the pellet characteristic gray image as a center to obtain a neighborhood, calculating the gray average value of all pixels in the neighborhood to be used as the output of the center pixel, and generating a filtered pellet characteristic gray image; wherein, the output formula of the central pixel is as follows:
g (j, k) represents a central pixel, N multiplied by N represents a neighborhood, A represents a point set formed by neighborhood pixels, and d (m, N) represents a pixel point on the neighborhood.
Preferably, the step 5: carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image, which comprises the following steps:
step 5.1: taking an s × s matrix by taking pixel points to be binarized in the filtered pellet characteristic gray level image as a center, and calculating the sum of all pixel values in the s × s matrix;
step 5.2: processing the filtered pellet characteristic gray level image by using a self-adaptive binarization formula to generate a pellet characteristic binarization image; wherein, the self-adaptive binarization formula is as follows:
wherein T (n) represents the binarization result of the pellet characteristic binarization image at n points, PnIs the pixel value of the pixel point to be binarized, fs×s(n) denotes the sum of all pixel values in the s × s matrix, and t denotes a correction coefficient.
Preferably, the step 7: denoising the pellet distribution binary image to generate a noise-removed pellet distribution binary image, comprising:
performing image opening operation on the pellet distribution binary image to generate a noise-removed pellet distribution binary image; wherein, the image opening operation processing formula is as follows:
wherein f isopen(x, y) represents that the opening operation is carried out on the spherical distribution binary image f (x, y), theta represents the corrosion operation,
indicating a dilation operation, b (i, j) indicates a structural element.
Preferably, the step 9: obtaining the center of each pellet according to the pellet profile distribution diagram, wherein the center comprises the following components:
step 9.1: acquiring all pixel coordinates on each pellet profile in the pellet profile distribution map;
step 9.2: acquiring pixel coordinates in each pellet profile, calculating the sum of the pixel coordinates in the pellet profile and the distance values of all the pixel coordinates on the corresponding pellet profile, and generating a pixel coordinate total distance value set;
step 9.3: and taking the pixel coordinate corresponding to the minimum value on the pixel coordinate total distance value set as the center of each pellet.
Preferably, the step 10: and fitting the pellets on the pellet profile distribution diagram according to the centers of the pellets to obtain the particle size of each pellet, wherein the particle size comprises the following steps:
step 10.1: taking the center of each pellet as the circle center to make a circle with the diameter being continuously enlarged, and solving the circumscribed rectangle of the circle;
step 10.2: and when the ratio of the number of the pixels in the circle to the area value of the circumscribed rectangle is larger than or equal to a fixed threshold value, the diameter of the circle is the particle size of the corresponding pellet.
Preferably, the fixed threshold value is 0.7-0.9.
The invention also provides a ball granule diameter detection system, comprising:
the pellet image acquisition module is used for acquiring a pellet image acquired by the industrial camera;
the interesting region extraction module is used for extracting an interesting region on the pellet image to generate a pellet characteristic image;
the gray level conversion module is used for carrying out gray level conversion on the pellet characteristic image to generate a pellet characteristic gray level image;
the filtering module is used for filtering the pellet characteristic gray level image to generate a filtered pellet characteristic gray level image;
the self-adaptive binarization processing module is used for carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
the distance transformation module is used for carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
the de-noising module is used for de-noising the pellet distribution binary image to generate a pellet distribution binary image after noise removal;
the pellet contour processing module is used for extracting the contour of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet contour distribution map;
the pellet center determining module is used for obtaining the center of each pellet according to the pellet profile distribution map;
and the pellet particle size determining module is used for fitting the pellets on the pellet profile distribution map according to the centers of the pellets to obtain the particle sizes of the pellets.
The method and the system for detecting the diameter of the ball granules have the beneficial effects that: compared with the prior art, the pellet diameter detection method comprises the steps of firstly obtaining a pellet image, extracting an interested area to obtain a pellet characteristic image, then sequentially carrying out gray level transformation, filtering, self-adaptive binarization, distance transformation, denoising and watershed transformation on the pellet characteristic image to obtain a pellet profile distribution map, determining the center of each pellet, and obtaining the particle diameter of each pellet according to the center of each pellet; according to the invention, the pellet characteristic image is subjected to filtering, self-adaptive binarization, distance conversion, denoising, watershed conversion and other processing, so that the detection and identification capability of the pellet image is improved, the particle size of each pellet is obtained according to the center of each pellet, the particle size of the pellet can be calculated in real time, and the time and labor are saved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flow chart of a ball granule diameter detection method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a method for detecting a ball particle size according to an embodiment of the present invention;
fig. 3 is a gray scale image of a feature of a pellet provided in an embodiment of the present invention;
FIG. 4 is a binarized image of pellet features provided by an embodiment of the present invention;
FIG. 5 is a binarized image of pellet distribution provided by an embodiment of the present invention;
fig. 6 is a schematic diagram of a contour of a pellet fitted by using the center of the pellet according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention aims to provide a pellet diameter detection method and a pellet diameter detection system, and aims to solve the problems that the existing pellet diameter detection method cannot count pellet diameters in real time and wastes time and labor.
Referring to fig. 1-5, to achieve the above object, the technical solution adopted by the present invention is: a ball granule diameter detection method comprises the following steps:
step 1: acquiring a pellet image acquired by an industrial camera;
in practical application, when the pellets come out of the pelletizer and reach the conveyor belt, the pellets can be captured by an industrial camera arranged above the conveyor belt.
Step 2: extracting an interested area on the pellet image to generate a pellet characteristic image;
and step 3: carrying out gray level transformation on the pellet characteristic image to generate a pellet characteristic gray level image;
and 4, step 4: filtering the characteristic gray image of the pellet to generate a filtered characteristic gray image of the pellet;
the step 4 specifically comprises the following steps:
taking each pixel in the pellet characteristic gray image as a center to obtain a neighborhood, calculating the gray average value of all pixels in the neighborhood to be used as the output of the center pixel, and generating a filtered pellet characteristic gray image; wherein, the output formula of the central pixel is as follows:
g (j, k) represents a central pixel, N multiplied by N represents a neighborhood, A represents a point set formed by neighborhood pixels, and d (m, N) represents a pixel point on the neighborhood.
In the invention, the gray average value of the neighborhood center is used for replacing the pixel, so that the noise mixed in the image can be eliminated, and the accuracy of subsequent target identification is improved.
And 5: carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
the step 5 specifically comprises the following steps:
step 5.1: taking an s multiplied by s matrix by taking pixel points to be binarized in the filtered pellet characteristic gray level image as a center, and calculating the sum of all pixel values in the s multiplied by s matrix;
step 5.2: processing the filtered pellet characteristic gray level image by using a self-adaptive binarization formula to generate a pellet characteristic binarization image; the self-adaptive binarization formula is as follows:
wherein T (n) represents the binarization result of the pellet characteristic binarization image at n points, PnIs the pixel value of the pixel point to be binarized, fs×s(n) denotes the sum of all pixel values in the s × s matrix, and t denotes a correction coefficient.
The self-adaptive binarization method provided by the invention can solve the problem of poor binarization effect of the pellet image acquired by the industrial camera under the condition of uneven illumination by adjusting the correction coefficient. Generally, the correction factor takes a value between 0.01 and 3.
Step 6: carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
according to the invention, each pellet which is close to each other in the pellet characteristic binary image can be separated by using distance transformation, so that the particle size of the pellet can be fitted better in the following process.
After the step 6, the method further comprises the following steps: and (3) carrying out normalization processing and binarization processing on the spherical characteristic binarization image, wherein the normalization is to limit the processed data (through a normalization algorithm) in a required range.
Firstly, normalization is for the convenience of data processing later, and secondly, convergence is accelerated when the program runs. The specific role of normalization is to generalize the statistical distribution of uniform samples. The normalization is a statistical probability distribution between 0 and 1 and the normalization is a statistical coordinate distribution over a certain interval. Normalization has the meaning of identity, unity, and unity.
The purpose of normalization is to make data without comparability comparable while maintaining a relative relationship, such as a magnitude relationship, between the two compared data; or for drawing, the method is difficult to make on a graph, and after normalization, the relative position on the graph can be conveniently given.
The Opencv normalization function is used in the present invention: normalize (image,0,1.0, cv2.norm _ MINMAX) to normalize the image of the two-valued ball distribution.
And 7: denoising the pellet distribution binary image to generate a pellet distribution binary image after noise removal;
the step 7 specifically comprises the following steps:
carrying out image opening operation on the pellet distribution binary image to generate a noise-removed pellet distribution binary image; the image opening operation processing formula is as follows:
wherein f isopen(x, y) represents that the opening operation is carried out on the spherical distribution binary image f (x, y), theta represents the corrosion operation,
indicating a dilation operation, b (i, j) indicates a structural element.
The invention can remove isolated dots and burrs in the image by processing the binary image of the ball distribution by utilizing the opening operation of the image.
And 8: extracting the outline of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet outline distribution map;
in practical application, the invention adopts a watershed () function to realize the watershed algorithm. The watershed algorithm implemented by the watershed function is one of the label-based segmentation algorithms. Before passing the image to the function, we need to roughly delineate the regions in the image that are desired to be segmented, labeled as positive indices. Therefore, each region will be labeled with pixel values 1, 2, 3, etc., representing one or more connected components. The values of these flags may be retrieved from the binary mask using a findContours () function and a drawContours () function. It will be understood that these labels are the "seeds" of the segmented regions to be rendered, and the regions without clear labels are set to 0. In the function output, the pixels in each marker are set to the value of the "seed" and the values between the regions are set to-1.
C++:void watershed(InputArray image，InputOutputArray markers)，
The first parameter, src of the InputArray type, is the input image, i.e. the source image, and the object of the Mat class is filled.
The second parameter, markers of the InputOutputArray type, where the operation result after the function call exists, inputs/outputs the marking result of the 32-bit single-channel image. That is, the parameter is used to store the output result after the function call, and has the same size and type as the source picture.
And step 9: obtaining the center of each pellet according to the pellet profile distribution map; the step 9 specifically comprises:
step 9.1: acquiring all pixel coordinates on each pellet profile in the pellet profile distribution map;
step 9.2: acquiring pixel coordinates in each pellet profile, calculating the sum of the pixel coordinates in the pellet profile and the distance values of all the pixel coordinates on the corresponding pellet profile, and generating a pixel coordinate total distance value set;
step 9.3: and taking the pixel coordinate corresponding to the minimum value on the pixel coordinate total distance value set as the center of each pellet.
Step 10: and fitting the pellets on the pellet profile distribution diagram according to the centers of the pellets to obtain the particle sizes of the pellets.
Referring to fig. 6, step 10 specifically includes:
step 10.1: taking the center of each pellet as the center of a circle with the diameter being continuously enlarged, and solving the circumscribed rectangle of the circle; the minimum distance between the circle centers is the minimum particle diameter of the pellet to be measured.
Step 10.2: and when the ratio of the number of the pixels in the circle to the area value of the circumscribed rectangle is larger than or equal to a fixed threshold value, the diameter of the circle is the particle size of the corresponding pellet. In the invention, the threshold value of the detection circle size is the average value of the maximum particle size and the minimum particle size of the detected pellet material, and the fixed threshold value is 0.7-0.9. In the invention, the number of the pixel points in the circle can be replaced by the area of the circle, and when the ratio of the area of the circle to the area of the rectangle circumscribed to the circle is greater than or equal to a fixed threshold value, the diameter of the circle is the particle diameter of the corresponding pellet.
After the particle sizes of the pellets are obtained, the pellets are sequentially screened according to the filtering conditions, so that the information of the qualified rate of the pellets, the total number of the pellets, the average diameter of the pellets, the maximum and minimum particle sizes of the pellets and the like is obtained, a table is generated, and the table is uploaded to an upper computer.
The invention is further explained by combining specific implementation, the particle size distribution situation is counted every three seconds in the invention, and 10 groups of actual pellet particle size distribution situation data in the production process are listed, so that the observation is convenient.
Cumulative data statistics over 8 hours
The invention also provides a control group, namely, 7 mm and 14mm filter screens are adopted, and the particle size is counted manually, so that the following conclusion is obtained.
Therefore, the pellet feature image is subjected to filtering, self-adaptive binarization, distance transformation, denoising, watershed transformation and the like, the detection and identification capacity of the pellet image is improved, the particle size of each pellet is obtained according to the center of each pellet, the particle size of each pellet can be calculated in real time and a statistical result can be generated, the time and labor are saved, and the particle size detection process is safer.
The invention also provides a ball granule diameter detection system, comprising:
the pellet image acquisition module is used for acquiring a pellet image acquired by the industrial camera;
the interesting region extraction module is used for extracting an interesting region on the pellet image to generate a pellet characteristic image;
the gray level conversion module is used for carrying out gray level conversion on the pellet characteristic image to generate a pellet characteristic gray level image;
the filtering module is used for filtering the pellet characteristic gray level image to generate a filtered pellet characteristic gray level image;
the adaptive binarization processing module is used for carrying out adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
the distance transformation module is used for carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
the de-noising module is used for de-noising the pellet distribution binary image to generate a de-noised pellet distribution binary image;
the pellet contour processing module is used for extracting the contour of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet contour distribution map;
the pellet center determining module is used for obtaining the center of each pellet according to the pellet profile distribution map;
and the pellet particle size determining module is used for fitting the pellets on the pellet profile distribution map according to the centers of the pellets to obtain the particle sizes of the pellets.
The invention provides a pellet diameter detection method and a system, belonging to the technical field of target detection, wherein the pellet diameter detection method comprises the steps of firstly obtaining a pellet image, extracting an interested area to obtain a pellet characteristic image, then sequentially carrying out gray level transformation, filtering, self-adaptive binarization, distance transformation, denoising and watershed transformation on the pellet characteristic image to obtain a pellet profile distribution map, determining the center of each pellet, and obtaining the particle diameter of each pellet according to the center of each pellet; according to the invention, the pellet characteristic image is subjected to filtering, self-adaptive binarization, distance conversion, denoising, watershed conversion and other processing, so that the detection and identification capability of the pellet image is improved, the particle size of each pellet is obtained according to the center of each pellet, the particle size of the pellet can be calculated in real time, and the time and labor are saved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. The ball granule diameter detection method is characterized by comprising the following steps:
step 1: acquiring a pellet image acquired by an industrial camera;
step 2: extracting an interested area on the pellet image to generate a pellet characteristic image;
and step 3: carrying out gray level transformation on the pellet characteristic image to generate a pellet characteristic gray level image;
and 4, step 4: filtering the pellet characteristic gray image to generate a filtered pellet characteristic gray image;
and 5: carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
step 6: carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
and 7: denoising the pellet distribution binary image to generate a noise-removed pellet distribution binary image;
and 8: extracting the outline of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet outline distribution map;
and step 9: obtaining the center of each pellet according to the pellet profile distribution map;
step 10: and fitting the pellets on the pellet profile distribution diagram according to the centers of the pellets to obtain the particle sizes of the pellets.
2. The method for detecting the diameter of a ball granule according to claim 1, wherein the step 4: filtering the pellet characteristic gray image to generate a filtered pellet characteristic gray image, wherein the filtering comprises the following steps:
taking each pixel in the pellet characteristic gray image as a center to obtain a neighborhood, calculating the gray average value of all pixels in the neighborhood to be used as the output of the center pixel, and generating a filtered pellet characteristic gray image; wherein, the output formula of the central pixel is as follows:
g (j, k) represents a central pixel, N multiplied by N represents a neighborhood, A represents a point set formed by neighborhood pixels, and d (m, N) represents a pixel point on the neighborhood.
3. The method for detecting the diameter of a ball granule according to claim 1, wherein the step 5: carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image, which comprises the following steps:
step 5.1: taking an s × s matrix by taking pixel points to be binarized in the filtered pellet characteristic gray level image as a center, and calculating the sum of all pixel values in the s × s matrix;
step 5.2: processing the filtered pellet characteristic gray level image by using a self-adaptive binarization formula to generate a pellet characteristic binarization image; wherein, the self-adaptive binarization formula is as follows:
wherein T (n) represents the binarization result of the pellet characteristic binarization image at n points, PnIs the pixel value of the pixel point to be binarized, fs×s(n) denotes the sum of all pixel values in the s × s matrix, and t denotes a correction coefficient.
4. The method for detecting the diameter of a ball granule according to claim 1, wherein the step 7: denoising the pellet distribution binary image to generate a noise-removed pellet distribution binary image, comprising:
performing image opening operation on the pellet distribution binary image to generate a noise-removed pellet distribution binary image; wherein, the image opening operation processing formula is as follows:
wherein f isopen(x, y) represents that the opening operation is carried out on the spherical distribution binary image f (x, y), theta represents the corrosion operation,
indicating a dilation operation, b (i, j) indicates a structural element.
5. The method for detecting the diameter of a ball granule according to claim 1, wherein the step 9: obtaining the center of each pellet according to the pellet profile distribution diagram, wherein the center comprises the following components:
step 9.1: acquiring all pixel coordinates on each pellet profile in the pellet profile distribution map;
step 9.2: acquiring pixel coordinates in each pellet profile, calculating the sum of the pixel coordinates in the pellet profile and the distance values of all the pixel coordinates on the corresponding pellet profile, and generating a pixel coordinate total distance value set;
step 9.3: and taking the pixel coordinate corresponding to the minimum value on the pixel coordinate total distance value set as the center of each pellet.
6. The method for detecting the diameter of a ball granule according to claim 5, wherein the step 10: and fitting the pellets on the pellet profile distribution diagram according to the centers of the pellets to obtain the particle size of each pellet, wherein the particle size comprises the following steps:
step 10.1: taking the center of each pellet as the circle center to make a circle with the diameter being continuously enlarged, and solving the circumscribed rectangle of the circle;
step 10.2: and when the ratio of the number of the pixels in the circle to the area value of the circumscribed rectangle is larger than or equal to a fixed threshold value, the diameter of the circle is the particle size of the corresponding pellet.
7. The method of claim 6, wherein the fixed threshold is 0.7-0.9.
8. A ball granule diameter detection system, comprising:
the pellet image acquisition module is used for acquiring a pellet image acquired by the industrial camera;
the interesting region extraction module is used for extracting an interesting region on the pellet image to generate a pellet characteristic image;
the gray level conversion module is used for carrying out gray level conversion on the pellet characteristic image to generate a pellet characteristic gray level image;
the filtering module is used for filtering the pellet characteristic gray level image to generate a filtered pellet characteristic gray level image;
the self-adaptive binarization processing module is used for carrying out self-adaptive binarization processing on the filtered pellet characteristic gray level image to generate a pellet characteristic binarization image;
the distance transformation module is used for carrying out distance transformation on the pellet characteristic binary image to generate a pellet distribution binary image;
the de-noising module is used for de-noising the pellet distribution binary image to generate a pellet distribution binary image after noise removal;
the pellet contour processing module is used for extracting the contour of the noise-removed pellet distribution binary image and carrying out watershed transformation to generate a pellet contour distribution map;
the pellet center determining module is used for obtaining the center of each pellet according to the pellet profile distribution map;
and the pellet particle size determining module is used for fitting the pellets on the pellet profile distribution map according to the centers of the pellets to obtain the particle sizes of the pellets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356547.5A CN113034573A (en) | 2021-04-01 | 2021-04-01 | Ball granule diameter detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356547.5A CN113034573A (en) | 2021-04-01 | 2021-04-01 | Ball granule diameter detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113034573A true CN113034573A (en) | 2021-06-25 |
Family
ID=76454102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110356547.5A Pending CN113034573A (en) | 2021-04-01 | 2021-04-01 | Ball granule diameter detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034573A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570557A (en) * | 2021-07-12 | 2021-10-29 | 北京科技大学 | Pellet consolidation degree evaluation method based on image recognition |
| CN113870268A (en) * | 2021-12-06 | 2021-12-31 | 华北理工大学 | Method for counting pellet ore number based on connected component detection |
| CN114897789A (en) * | 2022-04-14 | 2022-08-12 | 安徽工业大学 | Sinter particle size detection method and system based on image segmentation |
| CN115436238A (en) * | 2022-09-22 | 2022-12-06 | 中冶南方工程技术有限公司 | Blast furnace raw fuel granularity online detection method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010211498A (en) * | 2009-03-10 | 2010-09-24 | Kyodo Printing Co Ltd | Image processing program and image processing system |
| CN107063946A (en) * | 2016-12-23 | 2017-08-18 | 天津市三特电子有限公司 | Video green-ball particle instrument and its green-ball particle diameter condition detection method |
| CN110057308A (en) * | 2019-04-30 | 2019-07-26 | 北京理工大学 | A kind of deformation monitoring method and system |
| US20190347497A1 (en) * | 2017-01-25 | 2019-11-14 | Wuhan Jimu Intelligent Technology Co., Ltd. | Road sign recognition method and system |
| 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 |
| CN111179236A (en) * | 2019-12-23 | 2020-05-19 | 湖南长天自控工程有限公司 | Raw ball granularity analysis method and device for pelletizer |
-
2021
- 2021-04-01 CN CN202110356547.5A patent/CN113034573A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010211498A (en) * | 2009-03-10 | 2010-09-24 | Kyodo Printing Co Ltd | Image processing program and image processing system |
| CN107063946A (en) * | 2016-12-23 | 2017-08-18 | 天津市三特电子有限公司 | Video green-ball particle instrument and its green-ball particle diameter condition detection method |
| US20190347497A1 (en) * | 2017-01-25 | 2019-11-14 | Wuhan Jimu Intelligent Technology Co., Ltd. | Road sign recognition method and system |
| CN110057308A (en) * | 2019-04-30 | 2019-07-26 | 北京理工大学 | A kind of deformation monitoring method and system |
| 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 |
| CN111179236A (en) * | 2019-12-23 | 2020-05-19 | 湖南长天自控工程有限公司 | Raw ball granularity analysis method and device for pelletizer |
Non-Patent Citations (2)
| Title |
|---|
| 刘小燕;吴鑫;孙炜;毛传刚;: "基于形态学重建和GMM的球团颗粒图像分割", 仪器仪表学报, no. 03, 15 March 2019 (2019-03-15) * |
| 秦长泽;刘琼;: "基于改进分水岭算法的球团矿图像分割", 武汉科技大学学报, no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570557A (en) * | 2021-07-12 | 2021-10-29 | 北京科技大学 | Pellet consolidation degree evaluation method based on image recognition |
| CN113870268A (en) * | 2021-12-06 | 2021-12-31 | 华北理工大学 | Method for counting pellet ore number based on connected component detection |
| CN114897789A (en) * | 2022-04-14 | 2022-08-12 | 安徽工业大学 | Sinter particle size detection method and system based on image segmentation |
| CN115436238A (en) * | 2022-09-22 | 2022-12-06 | 中冶南方工程技术有限公司 | Blast furnace raw fuel granularity online detection method and system |
| CN115436238B (en) * | 2022-09-22 | 2023-11-21 | 中冶南方工程技术有限公司 | Blast furnace raw fuel granularity online detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034573A (en) | Ball granule diameter detection method and system | |
| Pei et al. | Robustness of machine learning to color, size change, normalization, and image enhancement on micrograph datasets with large sample differences | |
| CA3118067C (en) | Apparatus for analyzing composition of electronic and electrical device part scraps, device for processing electronic and electrical device part scraps, and method for processing electronic and electrical device part scraps | |
| CN107314957B (en) | Method for measuring rock block size distribution | |
| CN109701737B (en) | Beneficiation method for comprehensively recovering magnetite from cyanidation tailings | |
| CN112419397B (en) | Ore granularity grading method and system based on image and deep neural network | |
| CN103509901A (en) | Blast furnace raw fuel particle size detection method | |
| Liu et al. | Image-based method for measuring pellet size distribution in the stable area of disc pelletizer | |
| CN113887308A (en) | Blast furnace charge identification method, device and system based on image multivariate features | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN102220479A (en) | Beneficiation method for comprehensive recovery of valuable metals from sulfuric acid residues through chlorination and segregation | |
| CN112597904A (en) | Method for identifying and classifying blast furnace charge level images | |
| CN108629776A (en) | Ore-rock granularity Detection system | |
| CN107024416A (en) | With reference to similitude and the quasi-circular particle mean size detection method of discontinuity | |
| CN106957955A (en) | Handle the method and system of lateritic nickel ore | |
| CN115436238B (en) | Blast furnace raw fuel granularity online detection method and system | |
| CN108950195B (en) | Method for extracting valuable metals from zinc concentrate oxidizing slag by using chlorine-containing wastewater | |
| Jiang et al. | A coke detection method based on reweighting a composite feature for mixed material recognition and quantification | |
| CN114863277A (en) | Machine vision-based method for rapidly detecting irregular particle group overrun particles | |
| Malage et al. | Automatic quantitative analysis of microstructure of ductile cast iron using digital image processing | |
| CN116228681A (en) | Intelligent sintered ore particle counting method based on image multistage feature matching | |
| CN115170992B (en) | Image identification method and system for scattered blanking of scrap steel yard | |
| CN112396590B (en) | Method, equipment and medium for detecting granularity of semi-autogenous grinding ore | |
| CN116703927B (en) | Cell counting method, device and storage medium based on bright field optical image processing | |
| CN113680522B (en) | Method for preparing micro-nano magnetic material from carbonate-containing iron ore flotation tailings |
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 |