CN117252917A - Marine composite board production control method based on image processing - Google Patents
Marine composite board production control method based on image processing Download PDFInfo
- Publication number
- CN117252917A CN117252917A CN202311507910.4A CN202311507910A CN117252917A CN 117252917 A CN117252917 A CN 117252917A CN 202311507910 A CN202311507910 A CN 202311507910A CN 117252917 A CN117252917 A CN 117252917A
- Authority
- CN
- China
- Prior art keywords
- pixel
- surface image
- composite board
- holes
- value
- 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
- 239000002131 composite material Substances 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 title claims abstract description 31
- 238000000195 production control method Methods 0.000 title claims abstract description 7
- 238000004519 manufacturing process Methods 0.000 claims abstract description 31
- 230000007547 defect Effects 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 27
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 12
- 239000000428 dust Substances 0.000 abstract description 10
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000013507 mapping Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 5
- 239000000945 filler Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- 238000004026 adhesive bonding Methods 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000011151 fibre-reinforced plastic Substances 0.000 description 1
- 239000011152 fibreglass Substances 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- -1 polyethylene Polymers 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Geometry (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of composite board production control, in particular to a marine composite board production control method based on image processing, which comprises the following steps: collecting surface images of the composite board, generating a surface image set, performing pixel enhancement processing on the surface image set, calculating a gray neighborhood continuous index, obtaining a plurality of characteristic areas, and calculating the confidence coefficient of each characteristic area as a normal area; and constructing and training an enhancement model according to the characteristic areas and the confidence degrees to obtain a surface image enhancement model, acquiring the surface image in real time and inputting the surface image into the surface image enhancement model, generating a target surface image for clustering, and obtaining a plurality of holes and areas corresponding to the holes. The invention can effectively remove the influence of dust on the composite board image and improve the detection precision of the defects of the composite board.
Description
Technical Field
The present invention relates generally to the field of composite panel production control. More particularly, the present invention relates to a marine composite panel production control method based on image processing.
Background
With the continuous development of computer technology and digital image processing algorithms, image processing is increasingly applied to a wider range of fields.
The marine composite board is a board formed by stacking and combining different materials, and wood, glass Fiber Reinforced Plastic (FRP), aluminum, polyethylene and the like are commonly used. The composite board has the characteristics of light weight, high strength, corrosion resistance and the like, and is widely applied to ship manufacturing. In the production process of the marine composite board, a plurality of layers of composite board surfaces are arranged, different materials are bonded together through glue by a gluing machine, and proper temperature and pressure are applied to enable the materials of the layers to be fully bonded, so that the quality and performance of a product are ensured.
The surface defect detection of the composite board can adopt methods such as visual detection, hand touch detection, spectroscope detection and the like, the spectroscope detection is used, a defect image can be processed and stored through computer software or an image recorder, dust, filler and the like are attached to the surface of the composite board due to complex production environment of the composite board, and a large obstacle is generated for the production defect detection of the composite board, so that the defect detection of the surface of the composite board is difficult to finish directly through image processing, and the proportion of manual participation is increased; in the production and detection process of the composite board, many defects on the surface of the composite board are detected by manual inspection, and production parameters are adjusted, so that the defects are subjectively judged, misjudgment is easily caused, the detection time is long, and a large amount of human resources are wasted.
Disclosure of Invention
In order to solve one or more of the above technical problems, the present invention proposes to perform image enhancement on a region of a composite board, complete determination of a defective region by adopting a conditional clustering manner based on the enhanced image, and modify relevant production parameters according to a defective area, and therefore, the present invention provides solutions in various aspects as follows.
The production control method of the marine composite board based on the image processing comprises the following steps: collecting surface images of the composite board, generating a surface image set of the composite board, and preprocessing; performing pixel enhancement processing on the surface image set, and calculating gray neighborhood continuous indexes of the surface image set after pixel enhancement to obtain a plurality of characteristic areas; calculating the confidence coefficient of the characteristic region as a normal region; constructing an enhancement model according to each characteristic region and the confidence coefficient of the surface image set; training the enhancement model according to the surface image set to obtain a surface image enhancement model, acquiring the surface image in real time and inputting the surface image into the surface image enhancement model to generate a target surface image; clustering the target surface images to obtain a plurality of holes and areas corresponding to the holes; and adjusting production data of the marine composite board according to the area of the hole.
In one embodiment, the surface image set, each surface image includes a plurality of feature regions, and the gray scale neighborhood continuous index satisfies the following relationship:
wherein,denoted as +.>A gray scale neighborhood continuous index>Expressed as +.>Pixel value of each pixel, +.>Denoted as +.>Surrounding of individual pixels->Pixel values of the neighborhood;
responsive toAnd traversing and calculating pixel values of all the surface images to obtain a plurality of characteristic areas by taking the pixel values in the adjacent areas as a characteristic area.
By adopting the technical scheme, because the production environment of the composite board is complex, dust impurities possibly exist on the surface, the picture needs to be subjected to pixel enhancement treatment, and the influence of the surface dust is filtered. Dust (normal area) appears in areas on the surface of the composite board, and the area covered by the appearance area is larger, so that the coverage area of the surface dust can be judged by calculating the gray neighborhood continuous index of each surface image.
In one embodiment, calculating the confidence that the feature region is a normal region includes:
counting the number of the pixel points contained in the characteristic region and the number of all the pixel points in each surface image;
taking the ratio of the number of the pixel points contained in each characteristic region to the number of all the pixel points in the surface image to which the characteristic region belongs as the confidence that the characteristic region is a normal region;
traversing all the characteristic areas to obtain the confidence that each characteristic area is a normal area.
By adopting the technical scheme, when the confidence is larger, the specific gravity of the whole area occupied by the characteristic region is higher, and the probability that the characteristic region is a hole is smaller. Because the area of the holes is smaller in the composite board, and filler overflows and the peeled metal blocks exist in the composite board, the pixel values are more disordered in the composite board, and therefore the characteristic areas with the holes can be found through the method.
In one embodiment, the target mapping of the surface image enhancement model satisfies the following relationship:
wherein,gray values expressed as pixels in the original surface image, < >>Gray values expressed as pixel points in the enhanced back surface image +.>、/>、/>Expressed as a constant parameter, ">Is 255, ">Has a value of-1, ">The value of (2) is 0.
In one embodiment, calculating a first function and a second function of the target map, respectively, according to a constraint, and calculating a loss function of the target map according to the first function and the second function, includes:
if it isThe first function satisfies the following relationship:
if it isThe second function satisfies the following relationship:
the loss function of the computation constraint objective map satisfies the following relationship:
wherein,representing a first function value, ">Represented as pixel +.>Confidence of->Represented as pixel +.>Is used to determine the confidence level of the (c) in the (c),represented as pixel +.>Pixel value of>Represented as pixel +.>Pixel value of>Representing a second function value, ">Represented as a loss function value for the target map.
Therefore, according to the target mapping, the contrast ratio of the normal area and the defect area in the original gray level image is enhanced, and the influence of dust on the composite board image is effectively removed.
In one embodiment, clustering the target surface image to obtain a plurality of holes and areas corresponding to the holes includes:
acquiring positions and gray values of pixel points in a target surface image, and clustering the target surface image by using a mean value clustering algorithm to obtain a clustering result;
according to the clustering result, traversing and calculating the contour coefficient of each clustering cluster to obtain an optimal clustering result;
and according to the optimal clustering result, replacing the pixel value of the target surface image in the clustering cluster with the pixel value of the corresponding position in the unreinforced image, and calculating the gray level confusion degree coefficient of the pixel value of the characteristic region to obtain a plurality of holes and areas corresponding to the holes.
In one embodiment, the plurality of holes and the gray level confusion factor of the areas corresponding to the holes satisfy the following polynomial:
wherein,expressed as a gray scale clutter level coefficient +.>Is the->Individual pixel values +.>For intra-cluster pixel values +.>Ratio of->Expressed as the number of clusters;
and responding to the cluster corresponding to the gray level confusion degree coefficient as the hole defect when the gray level confusion degree coefficient is smaller than 0.1.
Through adopting above-mentioned technical scheme, through judging the confusing degree coefficient of gray scale to confirm the possibility size that the hole exists, judge the defect detection in the composite sheet course of working better.
In one embodiment, adjusting production data of the marine composite board according to the area of the hole comprises:
setting a hole area early warning valueAnd threshold number of holes->；
Responding to the area of the hole being larger than the early warning value of the area of the holeAt the same time, or in response to the threshold number of holes being greater than the threshold number of holes +.>And when the composite board is produced, triggering an alarm mechanism to prompt a worker to adjust production and processing parameters of the composite board.
The application has the following effects:
1. according to the method and the device, the confidence coefficient of each pixel value of the target surface image is enhanced, so that the larger the difference of the confidence coefficient is, the more favorable the enhancement of the contrast ratio of the normal region and the defect region in the original gray level image of the target surface image is, the influence of dust on the composite board image is effectively removed, and the detection precision of the defects of the composite board is improved.
2. According to the method, the target surface images are clustered to obtain a plurality of clusters, and the area size of the hole defects is reflected by counting the number of the pixel points contained in each cluster, so that accurate adjustment of processing parameters in the production process is facilitated.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flowchart of a method of steps S1-S7 in a marine composite panel production control method based on image processing according to an embodiment of the present application.
Fig. 2 is a flowchart of a method of steps S30-S32 in the method for controlling production of a marine composite board based on image processing according to the embodiment of the present application.
Fig. 3 is a flowchart of a method of steps S50-S51 in the method for controlling production of a marine composite board based on image processing according to the embodiment of the present application.
Fig. 4 is a flowchart of a method of steps S60-S62 in the method for controlling production of a marine composite board based on image processing according to the embodiment of the present application.
Fig. 5 is a flowchart of a method of steps S70-S71 in the method for controlling production of a marine composite board based on image processing according to the embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the method for controlling production of the marine composite board based on image processing includes steps S1 to S7, specifically as follows:
s1: and collecting the surface image of the composite board, generating a surface image set of the composite board, and preprocessing.
S2: performing pixel enhancement processing on the surface image set, calculating a gray neighborhood continuous index of the surface image set after pixel enhancement, and obtaining a plurality of characteristic areas, wherein the method comprises the following steps:
the gray neighborhood continuous index of the plurality of feature regions satisfies the following relation:
wherein,denoted as +.>A gray scale neighborhood continuous index>Expressed as +.>Pixel value of each pixel, +.>Denoted as +.>Surrounding of individual pixels->Pixel values of the neighborhood;
responsive toAnd traversing and calculating pixel values of all the surface images to obtain a plurality of characteristic areas by taking the pixel values in the adjacent areas as a characteristic area.
Illustratively, in response toWhen the gray value of the pixel point is similar to the gray value of the neighborhood, recording the pixel point as a central pixel point, taking the pixel point of the neighborhood of the central pixel point as a new central pixel point (any pixel point in the neighborhood), and calculating the gray neighborhood continuous index of the new central pixel point;
gray neighborhood continuous index coincidence responsive to new center pixel pointRepeating the above steps until the gray neighborhood continuous index of the neighborhood pixel of the central pixel is +.>Do not meet->And stopping. All the obtained center points form a characteristic area, and the larger the characteristic area is, the more pixel value points are contained, and the higher the probability that the characteristic area is a normal area is.
S3: calculating the confidence that the feature region is a normal region, referring to fig. 2, includes steps S30-S32:
s30: counting the number of pixel points contained in the feature area and the number of all pixel points in each surface image;
s31: taking the ratio of the number of the pixel points contained in each characteristic region to the number of all the pixel points in the surface image to which the characteristic region belongs as the confidence that the characteristic region is a normal region;
s32: traversing all the characteristic areas to obtain the confidence that each characteristic area is a normal area.
Illustratively, the greater the confidence, the higher the specific gravity of the overall area occupied by the feature region, and the less likely the feature region is a hole. Because the area of the holes is smaller in the composite board, filler overflows and the peeled metal blocks exist in the composite board, and the pixel values are more disordered in the composite board, the characteristic area where the holes possibly exist can be found through the method.
S4: and constructing an enhancement model according to each characteristic region and the confidence coefficient of the surface image set.
S5: training the enhancement model according to the surface image set to obtain a surface image enhancement model, acquiring a surface image in real time and inputting the surface image into the surface image enhancement model to generate a target surface image, referring to fig. 3, comprising the steps of S50-S51:
s50: calculating a target mapping value of the surface image enhancement model, wherein the target mapping of the surface image enhancement model satisfies the following relation:
wherein,gray values expressed as pixels in the original surface image, < >>Gray values expressed as pixel points in the enhanced back surface image +.>、/>、/>Expressed as a constant parameter, ">Is 255, ">Has a value of-1, ">The value of (2) is 0.
By way of example only, and not by way of limitation,is 255, ">Has a value of-1, ">The value of (2) is 0.
S51: according to constraint conditions, respectively calculating a first function and a second function of the target mapping, and according to the first function and the second function, calculating a loss function of the target mapping, wherein the method comprises the following steps:
if it isThe first function satisfies the following relationship:
if it isThe second function satisfies the following relationship:
the loss function of the computation constraint objective map satisfies the following relationship:
wherein,representing a first function value, ">Represented as pixel +.>Confidence of->Represented as pixel +.>Is used to determine the confidence level of the (c) in the (c),represented as pixel +.>Pixel value of>Represented as pixel +.>Pixel value of>Representing a second function value, ">Represented as a loss function value for the target map.
The target surface image is expressed as a target gray image by using an arbitrary pixel point in the target gray imageAnd another arbitrary pixel point +>For example, wherein->The pixel value of the pixel point is +.>Corresponds to a confidence level->，/>The pixel value of the pixel point is +.>Corresponds to a confidence level->。
Confidence whenConfidence->When the pixel points are equal, the pixel points are +>And pixel dot->Belonging to a characteristic region without reinforcement, i.e. +.>The method comprises the steps of carrying out a first treatment on the surface of the When confidence->Confidence->If the pixels are not equal, the pixel points need to be enhanced>And pixel dot->So that the pixel after reinforcement is +.>New pixel value +.>And pixel dot->New pixel value +.>Is greater and the magnitude of the emphasis is positively correlated with the confidence. According to the reinforcement principle, the contrast ratio of the pixel values of the normal and abnormal areas in the new gray level image is increased, and the pixel gap is obviously increased.
According to the target mapping, the contrast ratio of the normal area and the defect area in the original gray level image is enhanced, the influence of dust on the composite board image is effectively removed, and the gray level value possibly being a hole area is reserved for subsequent processing.
S6: clustering the target surface images to obtain a plurality of holes and areas corresponding to the holes, referring to fig. 4, including steps S60-S62:
s60: acquiring positions and gray values of pixel points in the target surface image, and clustering the target surface image by using a mean value clustering algorithm to obtain a clustering result;
by way of example only, and not by way of limitation,is 3.
S61: according to the clustering result, traversing and calculating the contour coefficient of each clustering cluster to obtain an optimal clustering result;
s62: according to the optimal clustering result, replacing the pixel value of the target surface image in the clustering cluster with the pixel value of the corresponding position in the unreinforced image, and calculating the gray level confusion degree coefficient of the pixel value of the characteristic region to obtain a plurality of holes and areas corresponding to the holes, wherein the gray level confusion degree coefficient of the holes and the areas corresponding to the holes meets the following polynomial:
wherein,expressed as a gray scale clutter level coefficient +.>Is the->Individual pixel values +.>For intra-cluster pixel values +.>Ratio of->Represented as the number of clusters.
And responding to the cluster corresponding to the gray level confusion degree coefficient as the hole defect when the gray level confusion degree coefficient is smaller than 0.1.
For example, after the contrast of the pixel value of the target surface image is increased, the difference of the pixel values in the class is reduced, and the difference of the pixel values between the classes is increased, because the abnormal area in the enhanced gray image contains stones and holes, that is, whether the hole area exists or not cannot be directly judged through the enhanced gray image, so that whether the hole exists or not needs to be judged on the enhanced gray image.
Based on the enhanced gray level image, a defect searching mechanism is constructed, and because the gray level value of the dust area and the gray level value of the hole defect in the enhanced gray level image have obvious difference, the hole defect can be searched in a clustering mode.
The larger the degree of confusion inside the cluster, the higher the likelihood that this cluster is a hole. />The smaller the probability of clustering as holes is smaller.
Traversing each imageThe prime point is obtained finallyThe central point of each cluster is the central point of the hole area, and the number of the pixel points contained in each cluster is the area of the hole defect; the more sample points within the cluster, the greater the area of the hole defect.
S7: according to the area of the hole, the production data of the marine composite board is adjusted, referring to fig. 5, and the method comprises the steps of S70-S71:
s70: setting a hole area early warning valueAnd threshold number of holes->；
S71: responding to the area of the hole being larger than the early warning value of the area of the holeAt the same time, or in response to the threshold number of holes being greater than the threshold number of holes +.>And when the composite board is produced, triggering an alarm mechanism to prompt a worker to adjust production and processing parameters of the composite board.
Exemplary, hole area warning valuesCan be 16, the threshold value of the number of holes is +.>May be 3.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (8)
1. The production control method of the marine composite board based on the image processing is characterized by comprising the following steps of:
collecting surface images of the composite board, generating a surface image set of the composite board, and preprocessing;
performing pixel enhancement processing on the surface image set, and calculating gray neighborhood continuous indexes of the surface image set after pixel enhancement to obtain a plurality of characteristic areas;
calculating the confidence coefficient of the characteristic region as a normal region;
constructing an enhancement model according to each characteristic region and the confidence coefficient of the surface image set;
training the enhancement model according to the surface image set to obtain a surface image enhancement model, acquiring the surface image in real time and inputting the surface image into the surface image enhancement model to generate a target surface image;
clustering the target surface images to obtain a plurality of holes and areas corresponding to the holes;
and adjusting production data of the marine composite board according to the area of the hole.
2. The method for controlling production of marine composite panels based on image processing according to claim 1, wherein each surface image in the set of surface images includes a plurality of feature areas, and gray neighborhood continuous indexes of the plurality of feature areas satisfy the following relation:
wherein,denoted as +.>A gray scale neighborhood continuous index>Expressed as +.>Pixel value of each pixel, +.>Denoted as +.>Surrounding of individual pixels->Pixel values of the neighborhood;
responsive toAnd traversing and calculating pixel values of all the surface images to obtain a plurality of characteristic areas by taking the pixel values in the adjacent areas as a characteristic area.
3. The method for controlling production of marine composite panels based on image processing according to claim 1, wherein calculating the confidence that the characteristic region is a normal region comprises:
counting the number of the pixel points contained in the characteristic region and the number of all the pixel points in each surface image;
taking the ratio of the number of the pixel points contained in each characteristic region to the number of all the pixel points in the surface image to which the characteristic region belongs as the confidence that the characteristic region is a normal region;
traversing all the characteristic areas to obtain the confidence that each characteristic area is a normal area.
4. The method for controlling production of marine composite panels based on image processing according to claim 1, wherein the target map of the surface image enhancement model satisfies the following relation:
wherein,gray values expressed as pixels in the original surface image, < >>Gray values expressed as pixel points in the enhanced back surface image +.>、/>、/>Expressed as a constant parameter, ">Is 255, ">Has a value of-1, ">The value of (2) is 0.
5. The method for controlling production of marine composite panels based on image processing according to claim 4, wherein calculating a first function and a second function of the target map, respectively, according to constraint conditions, and calculating a loss function of the target map according to the first function and the second function, comprises:
if it isThe first function satisfies the following relationship:
if it isThe second function satisfies the following relationship:
the loss function of the computation constraint objective map satisfies the following relationship:
wherein,representing a first function value, ">Represented as pixel +.>Confidence of->Represented as pixel +.>Confidence of->Represented as pixel +.>Pixel value of>Represented as pixel +.>Pixel value of>Representing a second function value, ">Represented as a loss function value for the target map.
6. The method for controlling production of marine composite panels based on image processing according to claim 1, wherein clustering the target surface images to obtain a plurality of holes and areas corresponding to the holes comprises:
acquiring positions and gray values of pixel points in a target surface image, and clustering the target surface image by using a mean value clustering algorithm to obtain a clustering result;
according to the clustering result, traversing and calculating the contour coefficient of each clustering cluster to obtain an optimal clustering result;
and according to the optimal clustering result, replacing the pixel value of the target surface image in the clustering cluster with the pixel value of the corresponding position in the unreinforced image, and calculating the gray level confusion degree coefficient of the pixel value of the characteristic region to obtain a plurality of holes and areas corresponding to the holes.
7. The method for controlling production of marine composite boards based on image processing according to claim 6, wherein the plurality of holes and the gray level disturbance degree coefficients of the areas corresponding to the holes satisfy the following polynomials:
wherein,expressed as a gray scale clutter level coefficient +.>Is the->Individual pixel values +.>For intra-cluster pixel values +.>Ratio of->Expressed as the number of clusters;
and responding to the cluster corresponding to the gray level confusion degree coefficient as the hole defect when the gray level confusion degree coefficient is smaller than 0.1.
8. The method for controlling production of marine composite board based on image processing according to claim 1, wherein adjusting production data of marine composite board according to the area of the hole comprises:
setting a hole area early warning valueAnd threshold number of holes->；
Responding to the area of the hole being larger than the early warning value of the area of the holeAt the same time, or in response to the threshold number of holes being greater than the threshold number of holes +.>And when the composite board is produced, triggering an alarm mechanism to prompt a worker to adjust production and processing parameters of the composite board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311507910.4A CN117252917B (en) | 2023-11-14 | 2023-11-14 | Marine composite board production control method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311507910.4A CN117252917B (en) | 2023-11-14 | 2023-11-14 | Marine composite board production control method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117252917A true CN117252917A (en) | 2023-12-19 |
| CN117252917B CN117252917B (en) | 2024-02-02 |
Family
ID=89127955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311507910.4A Active CN117252917B (en) | 2023-11-14 | 2023-11-14 | Marine composite board production control method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117252917B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576105A (en) * | 2024-01-17 | 2024-02-20 | 高科建材（咸阳）管道科技有限公司 | Pipeline production control method and system based on artificial intelligence |
| CN117611583A (en) * | 2024-01-22 | 2024-02-27 | 张家港飞腾复合新材料股份有限公司 | Artificial intelligence-based aluminum composite panel defect detection method and system |
| CN117745751A (en) * | 2024-02-21 | 2024-03-22 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image segmentation method based on feature extraction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5825909A (en) * | 1996-02-29 | 1998-10-20 | Eastman Kodak Company | Automated method and system for image segmentation in digital radiographic images |
| CN102496023A (en) * | 2011-11-23 | 2012-06-13 | 中南大学 | Region of interest extraction method of pixel level |
| CN114140827A (en) * | 2021-12-06 | 2022-03-04 | 华东师范大学 | Hole identification method and system based on U-Net network model |
| CN115841491A (en) * | 2023-02-24 | 2023-03-24 | 杭州电子科技大学 | Quality detection method of porous metal material |
-
2023
- 2023-11-14 CN CN202311507910.4A patent/CN117252917B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5825909A (en) * | 1996-02-29 | 1998-10-20 | Eastman Kodak Company | Automated method and system for image segmentation in digital radiographic images |
| CN102496023A (en) * | 2011-11-23 | 2012-06-13 | 中南大学 | Region of interest extraction method of pixel level |
| CN114140827A (en) * | 2021-12-06 | 2022-03-04 | 华东师范大学 | Hole identification method and system based on U-Net network model |
| CN115841491A (en) * | 2023-02-24 | 2023-03-24 | 杭州电子科技大学 | Quality detection method of porous metal material |
Non-Patent Citations (1)
| Title |
|---|
| 徐凤云;: "神经网络决策树算法在钢材表面缺陷检测中的应用研究", 西昌学院学报(自然科学版), no. 02 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576105A (en) * | 2024-01-17 | 2024-02-20 | 高科建材（咸阳）管道科技有限公司 | Pipeline production control method and system based on artificial intelligence |
| CN117576105B (en) * | 2024-01-17 | 2024-03-29 | 高科建材（咸阳）管道科技有限公司 | Pipeline production control method and system based on artificial intelligence |
| CN117611583A (en) * | 2024-01-22 | 2024-02-27 | 张家港飞腾复合新材料股份有限公司 | Artificial intelligence-based aluminum composite panel defect detection method and system |
| CN117611583B (en) * | 2024-01-22 | 2024-04-19 | 张家港飞腾复合新材料股份有限公司 | Artificial intelligence-based aluminum composite panel defect detection method and system |
| CN117745751A (en) * | 2024-02-21 | 2024-03-22 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image segmentation method based on feature extraction |
| CN117745751B (en) * | 2024-02-21 | 2024-04-26 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image segmentation method based on feature extraction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117252917B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117252917B (en) | Marine composite board production control method based on image processing | |
| CN115082467B (en) | Building material welding surface defect detection method based on computer vision | |
| CN107230218B (en) | Method and apparatus for generating confidence measures for estimates derived from images captured by vehicle-mounted cameras | |
| CN116740070B (en) | Plastic pipeline appearance defect detection method based on machine vision | |
| CN116577351B (en) | Liquid crystal glass substrate polaroid quality detection method based on image data | |
| Xu et al. | An infrared thermal image processing framework based on superpixel algorithm to detect cracks on metal surface | |
| CN112434586B (en) | Multi-complex scene target detection method based on domain self-adaptive learning | |
| CN109726739A (en) | A kind of object detection method and system | |
| CN111127472B (en) | Multi-scale image segmentation method based on weight learning | |
| CN116539619B (en) | Product defect detection method, system, device and storage medium | |
| CN117237646B (en) | PET high-temperature flame-retardant adhesive tape flaw extraction method and system based on image segmentation | |
| CN115439694A (en) | High-precision point cloud completion method and device based on deep learning | |
| CN115082450A (en) | Pavement crack detection method and system based on deep learning network | |
| CN112488958A (en) | Image contrast enhancement method based on scale space | |
| CN115797361A (en) | Aluminum template surface defect detection method | |
| CN112683166B (en) | Die-cutting product size detection method | |
| CN114419078B (en) | Surface defect region segmentation method and device based on convolutional neural network | |
| CN115423787A (en) | Defect detection method and system for 3D printing layered picture | |
| CN113763261B (en) | Real-time detection method for far small target under sea fog weather condition | |
| CN115861878A (en) | Panoramic safety monitoring city abnormal event detection method based on iterative refinement | |
| CN108229071A (en) | Cutting performance degradation assessment method and system based on AR models Yu SVDD algorithms | |
| CN112750119A (en) | Detection and measurement method for weak defects on surface of white glass cover plate | |
| CN107564027B (en) | Edge vector calculation method of synthetic aperture radar image | |
| Jin et al. | Performance comparison of decision fusion strategies in BMMF-based image quality assessment | |
| CN108447051A (en) | A kind of metal product surface defect rank assessment method based on computer vision |
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 |