CN115035303A - Method for detecting abrasive concentration of electroplated colored cBN grinding wheel - Google Patents
Method for detecting abrasive concentration of electroplated colored cBN grinding wheel Download PDFInfo
- Publication number
- CN115035303A CN115035303A CN202210692100.XA CN202210692100A CN115035303A CN 115035303 A CN115035303 A CN 115035303A CN 202210692100 A CN202210692100 A CN 202210692100A CN 115035303 A CN115035303 A CN 115035303A
- Authority
- CN
- China
- Prior art keywords
- colored
- abrasive
- cbn
- channel
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000000463 material Substances 0.000 claims abstract description 62
- 238000012545 processing Methods 0.000 claims abstract description 23
- 239000003082 abrasive agent Substances 0.000 claims description 40
- 239000011159 matrix material Substances 0.000 claims description 34
- 238000009826 distribution Methods 0.000 claims description 17
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 239000002184 metal Substances 0.000 claims description 7
- 229910052751 metal Inorganic materials 0.000 claims description 7
- 229910052759 nickel Inorganic materials 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000009713 electroplating Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 239000007767 bonding agent Substances 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 27
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000002356 single layer Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 229910052582 BN Inorganic materials 0.000 description 1
- PZNSFCLAULLKQX-UHFFFAOYSA-N Boron nitride Chemical compound N#B PZNSFCLAULLKQX-UHFFFAOYSA-N 0.000 description 1
- VEQPNABPJHWNSG-UHFFFAOYSA-N Nickel(2+) Chemical compound [Ni+2] VEQPNABPJHWNSG-UHFFFAOYSA-N 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 229910001651 emery Inorganic materials 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000010410 layer Substances 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
- 229910001453 nickel ion Inorganic materials 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24D—TOOLS FOR GRINDING, BUFFING OR SHARPENING
- B24D18/00—Manufacture of grinding tools or other grinding devices, e.g. wheels, not otherwise provided for
-
- 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
- G06V10/457—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 by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
-
- 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
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for detecting the abrasive concentration of an electroplated colored cBN grinding wheel, which comprises the following steps: obtaining an Overall color image I of an unplated colored cBN grit and white Chassis 1 Performing digital image processing to obtain a binary image M 1 Calculating the color interval of the colored cBN abrasive of the current batch and the interval of the number of the pixel points occupied by a single abrasive; obtaining the local color image I of the electroplated colored cBN grinding wheel in the same batch with the colored cBN grinding material 2 (ii) a For partial color image I 2 Digital image processing is carried out to obtain a binary image M based on the characteristics of the colored cBN in the batch 2 Calculating the number of connected domains and the number of pixel points which are occupied by the single grinding material of the batch of the colored cBN grinding materialsAnd (4) calculating the abrasive concentration of the electroplated colored cBN grinding wheel according to the total pixel point number in the connected domain. The invention improves the objectivity and consistency of the detection of the abrasive concentration, improves the accuracy and the detection efficiency, and solves the problem of low detection efficiency in the abrasive concentration detection technology.
Description
Technical Field
The invention relates to the technical field of single-layer abrasive grinding wheel abrasive concentration detection, in particular to an abrasive concentration detection method of an electroplated colored cBN grinding wheel.
Background
The superhard materials such as diamond, cubic boron nitride (cBN) and the like have series of excellent performances such as high hardness, high wear resistance, high temperature resistance and the like, and the single-layer electroplated superhard material grinding wheel has good material removal rate and linear application speed, and is widely applied to the field of high-speed and ultrahigh-speed grinding. Wherein, the single-layer electroplating superhard material grinding wheel mainly uses colored cBN grinding material, and the colors are divided into black, yellow, amber and the like.
The electroplated colored cBN grinding wheel has a single-layer grinding material structure, high-strength colored cBN grinding materials and metal nickel ions are deposited on the surface of a substrate together, and compared with the ceramic bond and resin bond cBN grinding wheels, the electroplated colored cBN grinding wheel has the advantages of being sharp in cutting, high in grinding efficiency, free of trimming in the grinding process, easy in chip removal and the like. However, the chip containing space is reduced due to the excessively high abrasive concentration of the single-layer abrasive grinding wheel, and the grinding quality problems such as burrs, burns and the like are easily caused; the effective grinding material is reduced due to too low concentration, the grinding allowance of a single grinding material is increased, and the service life is shortened, so that the detection of the concentration of the grinding material is particularly important.
In the traditional grinding wheel manufacturing process, the grinding material concentration detection of the single-layer electroplated colored cBN grinding wheel generally has two schemes: firstly, use microscope observation emery wheel surface, count abrasive material quantity through artifical visualization, but abrasive material quantity is many under a field of view area, leads to this method efficiency extremely low, and easy mistake counts, omits, seriously influences abrasive material concentration's detection efficiency. And secondly, shooting a grinding material microscopic image of one area of the grinding wheel, comparing the difference of the grinding material concentrations of different grinding wheels according to experience, but the difference of the crystal forms of the colored cBN grinding materials causes different quantity of reflecting surfaces and different grinding material colors due to different batches of the colored cBN grinding materials. In addition, the distribution state of the abrasive is random, and the detector usually has own subjective judgment, which seriously affects the detection precision.
Disclosure of Invention
Aiming at the technical problems of low detection precision, low efficiency and strong subjectivity of the conventional abrasive concentration detection method, the invention provides the abrasive concentration detection method for the electroplated colored cBN grinding wheel, which improves the objectivity and consistency of detection and improves the accuracy and the efficiency of detection.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: a method for detecting the abrasive concentration of an electroplated colored cBN grinding wheel comprises the following steps:
step S1: placing the non-electroplated colored cBN grinding material on a white base plate with the color close to that of the metal nickel of the electroplating bonding agent to obtain the whole color image I of the non-electroplated colored cBN grinding material and the white base plate 1 ；
Step S2: integral color image I 1 Digital image processing is carried out to obtain a binary image M based on colored cBN abrasive material characteristic segmentation 1 Using a binary image M 1 Respectively calculating the color interval of the colored cBN grinding material of the current batch and the pixel point number interval occupied by a single grinding material;
step S3: using the same photographing conditions as in step S1, a local color image I of the electroplated colored cBN grinding wheel in the same batch as the above colored cBN grinding material was obtained 2 ；
Step S4: for partial color image I 2 Digital image processing is carried out to obtain a binary image M based on the characteristics of the colored cBN in the batch 2 ；
Step S5: for binary image M 2 And (4) performing image processing, calculating the number of connected domains and the number of total pixels according to the pixel number rule of the single abrasive of the batch of the colored cBN abrasive, judging whether the number of the total pixels is in the pixel number interval occupied by the single abrasive in the step S2, and calculating the abrasive concentration of the electroplated colored cBN grinding wheel according to the number of the total pixels in the connected domains.
The digital image processing of step S2, the digital image processing of step S4, and the image processing of step S5 are all implemented by MATLAB.
The step S2 uses the binarized image M 1 The implementation method for calculating the color interval of the colored cBN abrasive material of the current batch comprises the following steps: calling find function in MATLAB to find binary image M 1 All the pixel point coordinates with the value of 1 form a set S 1 Computing a set S 1 Corresponding position whole color image I 1 R channel pixel I 1 R (S 1 ) G channel pixel I 1 G (S 1 ) Obtaining the color interval of the colored cBN abrasive material of the current batch, wherein the R channel color interval is [ min { I ] 1 R (S 1 )},max{I 1 R (S 1 )}]And the color interval of the G channel is [ min { I ] 1 G (S 1 )},max{I 1 G (S 1 )}]And the color interval of the B channel is [0, V ]]And V is a threshold value for the floor characteristic.
In the step S2, the binarized image M is used 1 The realization method for calculating the pixel point number interval occupied by a single abrasive comprises the following steps: calling a bwleabel command in MATLAB to search a binary image M 1 Obtaining a distribution matrix L of the connected domains 1 And total number of connected domains P 1 (ii) a Calling find functions in MATLAB to respectively search connected domain distribution matrix L 1 Middle P 1 The number of pixel points contained in each connected domain forms a set Q 1 The interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material of the current batch is [ min (Q) ] 1 ),max(Q 1 )]。
The binary image M 1 The acquisition method comprises the following steps: extraction of a whole color image I using MATLAB 1 R channel pixel I 1 R (x, y), G channel pixel I 1 G (x, y) and B-channel pixels I 1 B (x, y) value of where I 1 R (x,y)、I 1 G (x,y)、I 1 B (x, y) are respectively a whole color image I 1 R channel pixels, G channel pixels and B channel pixels of the pixel points with the middle row number of x and the column number of y;
invoking ones function in MATLAB to establish one large and small whole color image I 1 Matrix M of equal size and all element values 1 1 (ii) a Extracting all pixel points representing white baseboard characteristics, namely extracting B channel pixel I 1 B All the pixel points with the (x, y) value larger than the threshold value V and the matrix M corresponding to the (x, y) position of each pixel point 1 The assigned value of the pixel point is 0, and a binary image M based on the colored cBN abrasive material characteristic segmentation is obtained 1 。
The binarized image M in said step S4 2 The acquisition method comprises the following steps:
local color image extraction by MATLAB 2 R channel pixel I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B A value of (x, y) wherein I 2 R (x,y)、I 2 G (x,y)、I 2 B (x, y) are respectively partial color images I 2 R channel pixels, G channel pixels and B channel pixels of the pixel points with the row number of x and the column number of y;
invoking zeros function in MATLAB to establish a size and local color image I 2 Matrix M of equal size and all element values 0 2 (ii) a Respectively judging R channel pixels I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B (x, y) whether the following conditions are satisfied:
wherein x ∈ [0, M ]],y∈[0,N]M and N are respectively partial color images I 2 Is defined as length and width, V is the threshold value of the floor characteristic, [ min { I } 1 R (S 1 )},max{I 1 R (S 1 )}]For binarizing the image M 1 The color interval of the R channel and the color interval of the G channel are [ min { I ] 1 G (S 1 )},max{I 1 G (S 1 )}]；
If so, the matrix M is divided into 2 Pixel point M of corresponding position 2 (x, y) is assigned a value of 1; if not, the pixel point M is still kept 2 (x, y) is 0, and a binary image M is obtained 2 。
The abrasive concentration of the electroplated colored cBN grinding wheel in the step S5 is as follows:
wherein M and N are respectively binary images M 2 Length and width of (P) 3 For binarizing the image M 2 The number of the medium potential abrasives is the total number of connected domains, Q 3i The number of pixels in the ith connected domain.
The method for calculating the number of the pixel points in the connected domain comprises the following steps: calling bwmorphh function in MATLAB to binarize image M 2 Performing opening operation until the binary image does not change any more, and obtaining the binary image M after noise reduction and abrasive separation 3 ；
Calling a bwleabel command in MATLAB to search for a binary image M 3 All the connected domains in the matrix are obtained, each connected domain represents a potential abrasive, and a connected domain distribution matrix L is obtained 3 And total number of connected domains P 3 ；
Calling find functions in MATLAB to respectively search connected domain distribution matrix L 3 Middle P 3 The number of pixel points contained in each connected domain forms a set Q 3 (ii) a Respectively judge the set Q 3 The number Q of pixel points contained in the ith connected domain 3i Whether the following conditions are satisfied:
min(Q 1 )≤Q 3i ≤max(Q 1 )
wherein i ∈ [1, P ] 3 ]；[min(Q 1 ),max(Q 1 )]The interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material in the current batch is obtained;
if the above conditions are satisfied, the number Q of the pixel points is reserved 3i (ii) a If the above conditions are not met, the pixel point number Q is assigned 3i Is 0.
The total amount of the non-electroplated colored cBN grinding material obtained in the step S1 should be greater than 0.1% of the theoretical basic allowable grinding material of the electroplated colored cBN grinding wheel to be detected, wherein the diameter of the electroplated grinding wheel is set to be D, the thickness of the electroplated grinding wheel is set to be T, and the selected basic grain size of the colored cBN grinding material is set to be D, so that the number of the grinding material capable of being accommodated in the circumferential direction is set to be D
And the whole is m downwards, and the quantity of the abrasive materials in the thickness direction can be accommodated
And rounding down to n, the theory of the wheel basically allows for m n abrasive.
The amount of the individual separated abrasives in the non-plated colored cBN abrasive collected in the step S1 is 50% or more of the total collected abrasive amount; the threshold V of the yellow and amber abrasives is 30-80, and the threshold V of the black abrasives is 10-50.
Compared with the prior art, the invention has the following beneficial effects:
1. the quantity requirement of the collected non-electroplated colored cBN abrasives is specified, the color information and the single abrasive information of the colored cBN abrasives in the current batch can be fully obtained, and the influence of colors and crystal forms in different batches on concentration detection is reduced.
2. The information of the non-electroplated colored cBN abrasive is used as a detection reference, the same batch image identification standard is established, the subjective image of manual visual inspection in the abrasive concentration detection technology is removed, and the objectivity and the consistency of detection are improved.
3. By adopting the image recognition method, the concentration of the abrasive of the electroplated colored cBN grinding wheel in the same batch and in a large scale can be quickly and efficiently detected only by carrying out one-time information acquisition on the non-electroplated colored cBN abrasive, and the problem of low detection efficiency in the abrasive concentration detection technology is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a grayscale image of a single acquisition of an image of an unplated colored cBN abrasive according to the invention.
Fig. 3 is a binarized image of the feature segmentation of fig. 2.
FIG. 4 is a gray scale of a color image of a portion of an electroplated colored cBN wheel of the same batch of the invention.
FIG. 5 is the noise-reduced, abrasive-separated binary image of FIG. 4.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
Example 1
As shown in FIG. 1, the method for detecting the abrasive concentration of the electroplated colored cBN grinding wheel comprises the following steps:
step S1: placing the non-electroplated colored cBN grinding material on a white base plate with the color close to that of the metal nickel of the electroplating bonding agent to obtain the whole color image I of the non-electroplated colored cBN grinding material and the white base plate 1 。
Whole color image I 1 The size of the image pixel points is M rows and N columns, and the number of the image pixel points is M x N. The white bottom plate with the color of the metal nickel layer is used for detecting the benchmark, which is beneficial to improving the accuracy of detection. The total quantity of the obtained non-electroplated colored cBN abrasives is 0.1 percent of the theoretical basic allowable abrasives of the electroplated colored cBN grinding wheel to be detected, wherein the diameter of the electroplated grinding wheel is set to be D, the thickness of the electroplated grinding wheel is set to be T, the basic grain diameter of the selected colored cBN abrasives is set to be D, and the quantity of the abrasives capable of being accommodated in the circumferential direction is set to be
And the whole is m downwards, and the quantity of the grinding materials in the thickness direction can be
And rounding down to n, the theory of the wheel basically allows for m n abrasive. Stipulate the minimum sampling abrasive amount as' theoretical basic allowable abrasive0.1% of the total amount of the abrasive, and a calculation formula of a theoretical basic allowable abrasive is given, so that the sufficiency of a detection standard is ensured.
The individual separated abrasives in the collected non-electroplated colored cBN abrasive accounted for more than 50% of the total collected abrasive quantity. When 0.1% of the theoretical basic allowable abrasive cannot be acquired once, the steps S1-S2 can be successively completed through multiple acquisition, and finally, all data are integrated into a color interval and a pixel point number interval occupied by a single abrasive.
Step S2: integral color image I 1 Digital image processing is carried out to obtain a binary image M based on colored cBN abrasive material characteristic segmentation 1 Using a binary image M 1 And respectively calculating the color interval of the colored cBN grinding material of the current batch and the interval of the number of the pixel points occupied by the single grinding material.
Digital image processing is accomplished by MATLAB.
Binary image M 1 The acquisition method comprises the following steps: extraction of a whole color image I using MATLAB 1 R channel pixel I 1 R (x, y), G channel pixel I 1 G (x, y) and B-channel pixels I 1 B A value of (x, y), wherein I 1 R (x,y)、I 1 G (x,y)、I 1 B (x, y) are respectively a whole color image I 1 R channel pixels, G channel pixels and B channel pixels of the pixel points with the middle row number of x and the column number of y.
Invoking ones function in MATLAB to establish one large and small whole color image I 1 Matrix M of equal size and all element values 1 1 (ii) a Extracting all pixel points representing white bottom plate characteristics, namely extracting B channel pixel I 1 B All the pixel points with the (x, y) value larger than the threshold value V and the matrix M corresponding to the (x, y) position of each pixel point 1 The assigned value of the pixel point is 0, and a binary image M based on the colored cBN abrasive material characteristic segmentation is obtained 1 。
Using a binarized image M 1 The implementation method for calculating the color interval of the colored cBN abrasive of the current batch comprises the following steps: calling find function in MATLAB to find binary image M 1 All the pixel points with the numerical value of 1Set S of coordinates 1 Computing a set S 1 Corresponding position whole color image I 1 R channel pixel I 1 R (S 1 ) G-channel pixel I 1 G (S 1 ) Obtaining the color interval of the colored cBN abrasive material of the current batch, wherein the R channel color interval is [ min { I ] 1 R (S 1 )},max{I 1 R (S 1 )}]And the color interval of the G channel is [ min { I ] 1 G (S 1 )},max{I 1 G (S 1 )}]And the color interval of the B channel is [0, V ]]And V is a threshold value for the floor characteristic. The threshold V is related to shooting conditions and the actual color of the colored cBN abrasive, the threshold V of a common yellow abrasive and an amber abrasive is 30-80, and the threshold V of a black abrasive is 10-50. Since no blue color is contained in yellow, amber, and black, the B channel should be zero; the color of the bottom plate is white, and the B channel is generally larger than 100, so that the abrasive and the bottom plate can be distinguished by distinguishing the value of the B channel, the threshold value is preset to reduce the calculation time, and the automatic extraction of the abrasive is realized.
Using a binarized image M 1 The implementation method for calculating the pixel point number interval occupied by the single abrasive comprises the following steps: calling a bwleabel command in MATLAB to search a binary image M 1 Obtaining a distribution matrix L of the connected domains by using all the connected domains 1 And total number of connected domains P 1 (ii) a Calling find function in MATLAB to respectively search connected domain distribution matrix L 1 Middle P 1 The number of pixel points contained in each connected domain forms a set Q 1 And obtaining the interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material of the current batch as [ min (Q) ] 1 ),max(Q 1 )]。
Step S3: using the same imaging conditions as in step S1, a partial color image I of the electroplated colored cBN grinding wheel of the above-described colored cBN abrasive batch was obtained 2 . The abrasive is measured to obtain a reference, and then the grinding wheels using the same batch of abrasive are inspected to determine whether the grinding wheels are abrasive or not using the previously determined reference.
Step S4: for partial color image I 2 Performing digital image processing to obtain two color cBN characteristics based on the batchValued image M 2 。
Digital image processing is accomplished by MATLAB.
Binary image M 2 The acquisition method comprises the following steps:
local color image I extraction using MATLAB 2 R channel pixel I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B A value of (x, y) wherein I 2 R (x,y)、I 2 G (x,y)、I 2 B (x, y) are respectively partial color images I 2 R channel pixels, G channel pixels and B channel pixels of the pixel points with the row number of x and the column number of y;
invoking zeros function in MATLAB to establish one size and local color image I 2 Matrix M of equal size and all element values 0 2 (ii) a Respectively judging R channel pixels I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B (x, y) whether the following conditions are satisfied:
wherein x is ∈ [0, M ∈],y∈[0,N]M and N are respectively partial color images I 2 Is defined as length and width, V is the threshold value of the floor characteristic, [ min { I } 1 R (S 1 )},max{I 1 R (S 1 )}]For binarizing the image M 1 The color interval of the R channel and the color interval of the G channel are [ min { I ] 1 G (S 1 )},max{I 1 G (S 1 )}]. The screening method aims at judging whether a pixel point with the coordinate (x, y) is an abrasive or not, if the pixel point to be judged can meet the screening, the pixel point is considered to be the abrasive, and if the pixel point cannot meet the screening requirement, the pixel point is considered not to be the abrasive. When the connected domain is calculated subsequently, only the screened pixel points need to be counted.
If so, the matrix M is divided into 2 Pixel point M of corresponding position 2 (x, y) is assigned a value of 1;if not, the pixel point M is still kept 2 (x, y) is 0, and a binary image M is obtained 2 。
Step S5: for binary image M 2 And (4) performing digital image processing, calculating the number of connected domains and the number of pixel points according to the pixel point number rule occupied by the single abrasive of the batch of the colored cBN abrasive, judging whether the total number of the pixel points is in the pixel point number interval occupied by the single abrasive in the step S2, and calculating the abrasive concentration of the electroplated colored cBN grinding wheel according to the total number of the pixel points in the connected domains.
Digital image processing is accomplished by MATLAB.
The method for calculating the number of the pixel points in the connected domain comprises the following steps: calling bwmorphh function in MATLAB to binarize image M 2 Performing opening operation until the binary image does not change any more, and obtaining the binary image M after noise reduction and abrasive separation 3 ；
Calling a bwleabel command in MATLAB to search for a binary image M 3 All the connected domains in the matrix are obtained, each connected domain represents a potential abrasive, and a connected domain distribution matrix L is obtained 3 And total number of connected domains P 3 ；
Calling find functions in MATLAB to respectively search connected domain distribution matrix L 3 Middle P 3 The number of pixel points contained in each connected domain forms a set Q 3 (ii) a Respectively judge the set Q 3 The number Q of pixel points contained in the ith connected domain 3i Whether the following conditions are satisfied:
min(Q 1 )≤Q 3i ≤max(Q 1 )
wherein i ∈ [1, P ] 3 ]；[min(Q 1 ),max(Q 1 )]The number of the pixel points occupied by the single grinding material of the colored cBN grinding material in the current batch is within the range. The abrasive material is a complete continuous substance, and the connected domains have a certain volume. Thus, it can be determined by screening whether the domains are abrasive or not, and if so, the domains are considered abrasive; otherwise it is not an abrasive. Only the connected component passing the screen needs to be considered when subsequently calculating the concentration.
If the above conditions are satisfied, the number Q of the pixel points is reserved 3i (ii) a If the above conditions are not satisfiedThen, the pixel number Q is assigned 3i Is 0.
According to the invention, the calculation result of the local image of the grinding wheel is removed by using the interval of the pixels occupied by the volume of the single abrasive material which is not processed in the same batch, so that the influence of noise and spots on metal nickel on detection is effectively reduced; by using an image processing mode, the detection has the same evaluation standard, the efficiency is high, and subjective factors are shielded.
The abrasive concentration of the electroplated colored cBN grinding wheel in the step S5 is as follows:
wherein M and N are respectively binary images M 2 Length and width of (P) 3 For binarizing the image M 2 The number of the medium potential abrasives is the total number of connected domains, Q 3i The number of pixels in the ith connected domain.
According to the invention, the unprocessed colored cBN grinding material is analyzed in an image processing mode, all information of the batch of colored cBN grinding material is obtained to form a detection standard, and then the local color picture of the grinding wheel is processed based on the standard to obtain the grinding material concentration, so that the detection accuracy is improved. The invention is suitable for various electroplated colored cBN grinding wheels with different grinding material colors, and comprises cBN grinding materials with black, yellow, amber and the like.
Example 2
The invention provides a method for detecting the abrasive concentration of an electroplated colored cBN grinding wheel, and a flow chart is shown in figure 1. The diameter of the grinding wheel detected in the example is 60mm, the thickness is 6mm, the selected grinding wheel is 120/140 amber cBN abrasive, the basic particle size is 106-:
s1: the non-electroplated colored cBN abrasive is placed on a white base plate with the color close to that of the electroplated bond metal nickel, and the theory of the electroplated colored cBN grinding wheel basically allows 0.1 percent of the abrasive to be 0.1 percent
The number of the abrasives is more than 100 when the abrasives are observed by the image acquisition equipment.
S2: obtaining an entire color image I of the non-electroplated colored cBN abrasive and the white base plate 1 The number of image pixels is 1600 × 1200, as shown in fig. 2.
S3: whole color image I with MATLAB 1 And (3) carrying out image processing to obtain a color interval of the colored cBN grinding material of the current batch and a pixel point number interval occupied by a single grinding material, specifically:
s31: extraction of a whole color image I using MATLAB 1 I of (A) 1 R (x,y)、I 1 G (x,y)、I 1 B (x, y) value, wherein I 1 R (x,y)、I 1 G (x,y)、I 1 B (x, y) are respectively a whole color image I 1 And R channel pixels, G channel pixels and B channel pixels of the pixels with the middle row number of x and the column number of y.
S32: calling the ones function in MATLAB to establish a matrix M with all element values being 1 1 Size and overall color image I 1 Equi-large, 1600 x 1200.
S33: extracting all pixel points representing white baseboard characteristics, namely B channel pixel I 1 B All the pixel points with the (x, y) value larger than the proper threshold value V equal to 80 and the pixel point M corresponding to each pixel point position 1 (x, y) is assigned to be 0, and a binarized image M based on colored cBN abrasive characteristic segmentation is obtained 1 As shown in fig. 3.
S34: calling find function in MATLAB to find binary image M 1 All the pixel point coordinates with the value of 1 form a set S 1 Computing a set S 1 Corresponding position R channel pixel I 1 R (S 1 ) G channel pixel I 1 G (S 1 ) Obtaining the color interval of the colored cBN abrasive material of the current batch, wherein the color interval of the R channel is [ min { I ] 1 R (S 1 )},max{I 1 R (S 1 )}]G channel color interval is [ min { I } 1 G (S 1 )},max{I 1 G (S 1 )}]And the color interval of the B channel is [0, 80 ]]. S35: calling a bwlan command in MATLAB, using 8 connected domains by default, and searching M 1 All the connected domains in the matrix are obtained, each connected domain represents one abrasive, and a connected domain distribution matrix L is obtained 1 And total number of connected domains P 1 。
S36: calling find functions in MATLAB and respectively searching a connected domain distribution matrix L 1 Middle P 1 The number of pixel points contained in each connected domain forms a set Q 1 And obtaining the interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material of the current batch as [ min (Q) ] 1 ),max(Q 1 )]。
S4: obtaining the local color image I of the electroplated colored cBN grinding wheel in the same batch with the colored cBN grinding wheel by using the same shooting condition 2 The same size is 1600 x 1200, as shown in fig. 4.
S5: local color image I using MATLAB 2 Carrying out image processing to obtain a binary image M based on the characteristics of the colored cBN in the batch 2 The method specifically comprises the following steps:
s51: local color image I extraction using MATLAB 2 R channel pixel I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B (x, y) value, wherein I 2 R (x,y)、I 2 G (x,y)、I 2 B (x, y) are respectively partial color images I 2 And the R channel pixel, the G channel pixel and the B channel pixel of the pixel point with the middle row number of x and the column number of y.
S52: invoking zeros function in MATLAB to establish a matrix M with all element values being 0 2 Size and I of 2 Equi-large, i.e., M x N.
S53: respectively determine I 2 R (x,y)、I 2 G (x,y)、I 2 B (x, y) whether the following conditions are satisfied:
wherein,
x∈[0,M],y∈[0,N]；
if yes, pixel point M is set 2 (x, y) is assigned a value of 1; if not, the binary image M is still kept at 0 to obtain a binary image M 2 。
S6: binarizing image M by using MATLAB 2 And (3) processing to obtain the number of connected domains and the total number of pixel points according with the pixel point number rule occupied by the single grinding material of the colored cBN grinding material in the batch, and calculating the grinding material concentration of the electroplated colored cBN grinding wheel by using the connected domain number and the total pixel point number, wherein the specific steps are as follows:
s61: calling bwmorphh function in MATLAB to binarize image M 2 Performing opening operation until the image does not change any more to obtain a noise-reduced and abrasive-separated binary image M 3 In the image state after the operation is completed as shown in fig. 5, the on operation means noise reduction from the image, and removes a single noise point, thereby reducing the subsequent workload.
S62: calling a bwleabel command in MATLAB, defaulting to use an 8-connected domain, and searching a binary image M 3 All the connected domains in the matrix are obtained, each connected domain represents a potential abrasive, and a connected domain distribution matrix L is obtained 3 And total number of connected domains P 3 。
S63: calling find functions in MATLAB and respectively searching a connected domain distribution matrix L 3 Middle P 3 The number of pixel points contained in each connected domain forms a set Q 3 . Set Q 3 The sum of which is a binary image M 3 The total number of all the pixels in the image.
S64: respectively judge the set Q 3 The number Q of pixel points contained in the ith connected domain 3i Whether the following conditions are satisfied:
min(Q 1 )≤Q 3i ≤max(Q 1 )
wherein i ∈ [1, P ] 3 ]。
If the conditions are met, keeping the number Q of the pixel points 3i (ii) a If the condition is not satisfied, Q is assigned 3i Is 0.
S65: processed set Q according to S64 3 And (3) calculating the abrasive concentration of the electroplated colored cBN grinding wheel, wherein the calculation formula is as follows:
the above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (10)
1. The method for detecting the abrasive concentration of the electroplated colored cBN grinding wheel is characterized by comprising the following steps of:
step S1: placing the non-electroplated colored cBN grinding material on a white base plate with the color close to that of the metal nickel of the electroplating bonding agent to obtain the whole color image I of the non-electroplated colored cBN grinding material and the white base plate 1 ；
Step S2: for the whole color image I 1 Digital image processing is carried out to obtain a binary image M based on colored cBN abrasive characteristic segmentation 1 Using a binary image M 1 Respectively calculating the color interval of the colored cBN grinding material of the current batch and the pixel point number interval occupied by a single grinding material;
step S3: using the same photographing conditions as in step S1, a local color image I of the electroplated colored cBN grinding wheel in the same batch as the above colored cBN grinding material was obtained 2 ；
Step S4: for local color image I 2 Digital image processing is carried out to obtain a binary image M based on the characteristics of the colored cBN in the batch 2 ；
Step S5: for binary image M 2 And (4) performing image processing, calculating the number of connected domains and the number of total pixels according to the pixel number rule of the single abrasive of the batch of the colored cBN abrasive, judging whether the number of the total pixels is in the pixel number interval occupied by the single abrasive in the step S2, and calculating the abrasive concentration of the electroplated colored cBN grinding wheel according to the number of the total pixels in the connected domains.
2. The method for detecting the abrasive concentration of a plated colored cBN grinding wheel according to claim 1, characterized in that the digital image processing of step S2, step S4 and step S5 are all realized by MATLAB.
3. The method for detecting abrasive concentration of electroplated colored cBN grinding wheel according to claim 2, characterized in that in step S2, binary image M is used 1 The implementation method for calculating the color interval of the colored cBN abrasive material of the current batch comprises the following steps: calling find function in MATLAB to find binary image M 1 All the pixel point coordinates with the value of 1 form a set S 1 Computing a set S 1 Corresponding position whole color image I 1 R channel pixel I 1 R (S 1 ) G-channel pixel I 1 G (S 1 ) Obtaining the color interval of the colored cBN abrasive material of the current batch, wherein the R channel color interval is [ min { I ] 1 R (S 1 )},max{I 1 R (S 1 )}]G channel color interval is [ min { I } 1 G (S 1 )},max{I 1 G (S 1 )}]And the color interval of the B channel is [0, V ]]And V is a threshold value for the floor characteristic.
4. The method for detecting the abrasive density of a plated colored cBN grinding wheel according to claim 3, characterized in that a binarized image M is used in step S2 1 The implementation method for calculating the pixel point number interval occupied by the single abrasive comprises the following steps: calling a bwleabel command in MATLAB to search a binary image M 1 Obtaining a distribution matrix L of the connected domains 1 And total number of connected domains P 1 (ii) a Calling find functions in MATLAB to respectively search connected domain distribution matrix L 1 Middle P 1 The number of pixel points contained in each connected domain forms a set Q 1 The interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material of the current batch is [ min (Q) ] 1 ),max(Q 1 )]。
5. The method for detecting abrasive concentration of electroplated colored cBN grinding wheel according to claim 2, 3 or 4, characterized in that the binarized image M 1 The acquisition method comprises the following steps: extraction of a whole color image I using MATLAB 1 R channel pixel I 1 R (x, y), G channel pixel I 1 G (x, y) and B-channel pixels I 1 B A value of (x, y), wherein I 1 R (x,y)、I 1 G (x,y)、I 1 B (x, y) are respectively a whole color image I 1 R channel pixels, G channel pixels and B channel pixels of the pixel points with the middle row number of x and the column number of y;
calling ones function in MATLAB to establish a large and small whole color image I 1 Matrix M of equal size and all element values 1 1 (ii) a Extracting all pixel points representing white bottom plate characteristics, namely extracting B channel pixel I 1 B All the pixel points with the (x, y) value larger than the threshold value V, and the matrix M corresponding to the position of each pixel point (x, y) 1 The assigned value of the pixel point is 0, and a binary image M based on the colored cBN abrasive material characteristic segmentation is obtained 1 。
6. The method for detecting abrasive concentration of electroplated colored cBN grinding wheel according to claim 3 or 4, characterized in that the binarized image M in step S4 2 The acquisition method comprises the following steps:
local color image extraction by MATLAB 2 R channel pixel I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B A value of (x, y) wherein I 2 R (x,y)、I 2 G (x,y)、I 2 B (x, y) are respectively partial color images I 2 R channel pixels, G channel pixels and B channel pixels of the pixel points with the row number of x and the column number of y;
invoking zeros function in MATLAB to establish a size and local color image I 2 Matrix M of equal size and all element values 0 2 (ii) a Respectively judging R channel pixels I 2 R (x, y), G channel pixel I 2 G (x, y), B channel pixel I 2 B (x, y) whether the following conditions are satisfied:
wherein x is ∈ [0, M ∈],y∈[0,N]M and N are respectively partial color images I 2 Is defined as length and width, V is the threshold value of the floor characteristic, [ min { I } 1 R (S 1 )},max{I 1 R (S 1 )}]For binarizing the image M 1 The color interval of the R channel and the color interval of the G channel are [ min { I ] 1 G (S 1 )},max{I 1 G (S 1 )}]；
If so, the matrix M is divided into 2 Pixel point M of corresponding position 2 (x, y) is assigned a value of 1; if not, the pixel point M is still kept 2 (x, y) is 0, and a binary image M is obtained 2 。
7. The method for detecting the abrasive concentration of a plated colored cBN grinding wheel according to claim 6, wherein the abrasive concentration of the plated colored cBN grinding wheel in the step S5 is:
wherein M and N are respectively binary images M 2 Length and width of (P) 3 For binarizing the image M 2 The number of the medium potential abrasives is the total number of connected domains, Q 3i The number of pixels in the ith connected domain.
8. The method for detecting the abrasive concentration of the electroplated colored cBN grinding wheel according to claim 7, wherein the method for calculating the number of pixel points in the connected domain comprises the following steps: calling bwmorphh function in MATLAB to binarize image M 2 Performing opening operation until the binary image does not change any more, and obtaining the binary image M after noise reduction and abrasive separation 3 ；
Calling a bwleabel command in MATLAB to search for a binary image M 3 All connected domains in (1), each connected domain representingOne potential abrasive material to obtain connected domain distribution matrix L 3 And total number of connected domains P 3 ；
Calling find functions in MATLAB to respectively search connected domain distribution matrix L 3 Middle P 3 The number of pixel points contained in each connected domain forms a set Q 3 (ii) a Respectively judge the set Q 3 The number Q of pixel points contained in the ith connected domain 3i Whether the following conditions are satisfied:
min(Q 1 )≤Q 3i ≤max(Q 1 )
wherein i ∈ [1, P ] 3 ]；[min(Q 1 ),max(Q 1 )]The interval of the number of the pixel points occupied by the single grinding material of the colored cBN grinding material in the current batch is obtained;
if the above conditions are satisfied, the number Q of the pixel points is reserved 3i (ii) a If the above conditions are not met, the pixel point number Q is assigned 3i Is 0.
9. The method for detecting the abrasive concentration of the electroplated colored cBN grinding wheel according to claim 8, wherein the total amount of the non-electroplated colored cBN abrasives obtained in the step S1 is more than 0.1% of the 'theoretical basic allowable abrasives' of the electroplated colored cBN grinding wheel to be detected, wherein the diameter of the electroplated grinding wheel is set to be D, the thickness of the electroplated grinding wheel is set to be T, the selected basic grain diameter of the colored cBN grinding wheel is set to be D, and the amount of the abrasives capable of being accommodated in the circumferential direction is set to be D
And the whole is m downwards, and the quantity of the abrasive materials in the thickness direction can be accommodated
And rounding down to n, the theory of the wheel basically allows for m n abrasive.
10. The method for detecting the abrasive concentration of a plated colored cBN grinding wheel according to claim 8 or 9, characterized in that the individual separated abrasives in the non-plated colored cBN grinding material collected in the step S1 account for more than 50% of the total collected abrasive amount; the threshold V of the yellow and amber abrasives is 30-80, and the threshold V of the black abrasives is 10-50.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210692100.XA CN115035303B (en) | 2022-06-17 | 2022-06-17 | Abrasive concentration detection method of electroplated colored cBN grinding wheel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210692100.XA CN115035303B (en) | 2022-06-17 | 2022-06-17 | Abrasive concentration detection method of electroplated colored cBN grinding wheel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115035303A true CN115035303A (en) | 2022-09-09 |
| CN115035303B CN115035303B (en) | 2024-04-26 |
Family
ID=83125068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210692100.XA Active CN115035303B (en) | 2022-06-17 | 2022-06-17 | Abrasive concentration detection method of electroplated colored cBN grinding wheel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115035303B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115239736A (en) * | 2022-09-23 | 2022-10-25 | 海安玻克超硬材料有限公司 | Method for monitoring quality of mixed material of abrasive layer for production of diamond-impregnated wheel |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09238256A (en) * | 1995-12-28 | 1997-09-09 | Ricoh Co Ltd | Image processing method and image processing unit |
| CN103593831A (en) * | 2013-10-25 | 2014-02-19 | 同济大学 | Method for automatically overcoming defects of cement paste backscattered electron image sample preparation |
| CN107742285A (en) * | 2017-09-26 | 2018-02-27 | 内江金鸿曲轴有限公司 | In machine grinding wheel grinding layer thickness detecting method |
| CN113409229A (en) * | 2021-08-20 | 2021-09-17 | 南京航空航天大学 | Method for evaluating contour of abrasive particles of large-abrasive-particle superhard abrasive grinding wheel |
| CN113850800A (en) * | 2021-10-15 | 2021-12-28 | 郑州磨料磨具磨削研究所有限公司 | Method for detecting edge breakage of cutting seam of hard and brittle material |
-
2022
- 2022-06-17 CN CN202210692100.XA patent/CN115035303B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09238256A (en) * | 1995-12-28 | 1997-09-09 | Ricoh Co Ltd | Image processing method and image processing unit |
| CN103593831A (en) * | 2013-10-25 | 2014-02-19 | 同济大学 | Method for automatically overcoming defects of cement paste backscattered electron image sample preparation |
| CN107742285A (en) * | 2017-09-26 | 2018-02-27 | 内江金鸿曲轴有限公司 | In machine grinding wheel grinding layer thickness detecting method |
| CN113409229A (en) * | 2021-08-20 | 2021-09-17 | 南京航空航天大学 | Method for evaluating contour of abrasive particles of large-abrasive-particle superhard abrasive grinding wheel |
| CN113850800A (en) * | 2021-10-15 | 2021-12-28 | 郑州磨料磨具磨削研究所有限公司 | Method for detecting edge breakage of cutting seam of hard and brittle material |
Non-Patent Citations (2)
| Title |
|---|
| 孟丹: "电镀金属结合剂砂轮磨粒特征的检测", 装备制造技术, no. 08, 15 August 2009 (2009-08-15), pages 9 - 10 * |
| 房佳斌等: "图像分析技术在磨具磨粒的形态分布研究中的应用", 硅酸盐通报, vol. 35, no. 07, 15 July 2016 (2016-07-15), pages 2309 - 2313 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115239736A (en) * | 2022-09-23 | 2022-10-25 | 海安玻克超硬材料有限公司 | Method for monitoring quality of mixed material of abrasive layer for production of diamond-impregnated wheel |
| CN115239736B (en) * | 2022-09-23 | 2022-12-13 | 海安玻克超硬材料有限公司 | Method for monitoring quality of mixed material of abrasive layer for production of diamond-impregnated wheel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115035303B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114723701B (en) | Gear defect detection method and system based on computer vision | |
| CN107909138B (en) | Android platform-based circle-like particle counting method | |
| CN109636824B (en) | Multi-target counting method based on image recognition technology | |
| CN115861320B (en) | Intelligent detection method for automobile part machining information | |
| CN116091499B (en) | Abnormal paint production identification system | |
| CN112215790A (en) | KI67 index analysis method based on deep learning | |
| CN113298776B (en) | Method for detecting appearance defects of metal closed water pump impeller | |
| CN115035303A (en) | Method for detecting abrasive concentration of electroplated colored cBN grinding wheel | |
| CN114926463A (en) | Production quality detection method suitable for chip circuit board | |
| CN110111301A (en) | Metal based on frequency-domain transform aoxidizes surface defect visible detection method | |
| Alférez et al. | Automatic classification of atypical lymphoid B cells using digital blood image processing | |
| Tien et al. | Automated visual inspection for microdrills in printed circuit board production | |
| US20200134805A1 (en) | Characterization method for fine-grained sedimentary rock laminar texture | |
| CN115797361A (en) | Aluminum template surface defect detection method | |
| CN117911353A (en) | Method for detecting surface defects of circular crystal oscillator wafer | |
| CN113643274A (en) | Method and device for screening two-dimensional code candidate area | |
| CN110458042B (en) | Method for detecting number of probes in fluorescent CTC | |
| Hamghalam et al. | Automatic counting of leukocytes in giemsa-stained images of peripheral blood smear | |
| CN107024416A (en) | With reference to similitude and the quasi-circular particle mean size detection method of discontinuity | |
| CN116468689A (en) | Flaw identification method based on gray scale characteristics | |
| CN102494987A (en) | Automatic category rating method for microscopic particles in nodular cast iron | |
| CN109615630A (en) | Semi-continuous casting alusil alloy Analysis on Microstructure method based on image processing techniques | |
| CN112102277A (en) | Device and method for detecting tumor cells in pleural fluid fluorescence image | |
| CN112651368A (en) | DNA ploidy analysis method for large-size cell microscopic image | |
| CN111028258A (en) | Self-adaptive threshold value extraction method for large-scale gray level image |
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 |