CN114240888A - Furniture assembly paint spraying defect repairing method and system based on image processing - Google Patents
Furniture assembly paint spraying defect repairing method and system based on image processing Download PDFInfo
- Publication number
- CN114240888A CN114240888A CN202111552442.3A CN202111552442A CN114240888A CN 114240888 A CN114240888 A CN 114240888A CN 202111552442 A CN202111552442 A CN 202111552442A CN 114240888 A CN114240888 A CN 114240888A
- Authority
- CN
- China
- Prior art keywords
- defect
- gray level
- probability
- obtaining
- pixel point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 164
- 239000003973 paint Substances 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005507 spraying Methods 0.000 title abstract description 12
- 238000010422 painting Methods 0.000 claims description 18
- 230000008439 repair process Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000002950 deficient Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000007591 painting process Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007665 sagging Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a furniture assembly paint spraying defect repairing method and system based on image processing. The method expresses style information of a neighborhood range through the arrangement entropy in the neighborhood range of the pixel points. And obtaining a background gray level through the gray level histogram, and obtaining the defect probability of each pixel point by utilizing the gray level difference and style information of the pixel point and the background gray level. And judging whether the sliding window area is a defect area according to the set discrete degree of the defect probability of the pixel points in the sliding window, and finally obtaining the whole defect area in the paint surface image. According to the method, the defect probability of the pixel points is determined through the style information, and the defect position is judged through the fluctuation of the defect probability, so that the orange peel defect is positioned, and the defects are repaired in a targeted manner.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a furniture assembly paint spraying defect repairing method and system based on image processing.
Background
The painting is an important link in the furniture production process, and the quality of the painting determines the quality of the finished furniture product. During the painting process, various painting defects can occur on the surface of the furniture due to the influence of the environment and the process. Common obvious defects such as sagging, raised lines, pinholes, orange peel and the like.
In a conventional paint defect detection process, in order to improve detection efficiency, the features of a paint image are extracted by using an image processing method, and defects are judged or classified according to the features. However, for the defects of the orange peel, the paint surface is uneven and shaped like the peel of an orange, the defect characteristics are uniformly distributed, effective obvious characteristics cannot be extracted for defect detection, the color of the paint surface changes due to the influence of a light source and the like, the extracted defect characteristics are directly classified, error detection is easily caused, and the defects of the orange peel cannot be effectively identified and repaired in a targeted manner.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a furniture assembly paint spraying defect repairing method and system based on image processing, and the adopted technical scheme is as follows:
the invention provides a furniture assembly paint spraying defect repairing method based on image processing, which comprises the following steps:
obtaining a paint surface image; acquiring a pixel difference sequence in a preset neighborhood range of each pixel point in the paint surface image; obtaining the arrangement entropy of the pixel difference sequence of each pixel point;
obtaining a gray level histogram of the paint surface image; obtaining the background probability of each pixel point according to the occurrence frequency of each gray level in the gray level histogram; obtaining a background gray level according to the background probability;
obtaining the gray level difference between the gray level corresponding to each pixel point and the background gray level; obtaining the defect probability of each pixel point according to the gray level difference and the arrangement entropy;
arranging a sliding window on the painting surface image; obtaining the discrete degree of the defect probability of the pixel points in the sliding window; if the discrete degree is larger than or equal to a preset discrete threshold value, taking the sliding window area as a defect area; traversing the whole paint surface image according to the sliding window to obtain an integral defect area;
and repairing the painted surface according to the integral defect area.
Further, the obtaining the background probability of each pixel point according to the occurrence frequency of each gray level in the gray level histogram includes:
performing Gaussian fitting according to the occurrence frequency to obtain a background probability Gaussian model; and obtaining the background probability corresponding to the gray level of each pixel point according to the background probability Gaussian model.
Further, the obtaining a background gray level according to the background probability comprises:
obtaining the background probability corresponding to all gray levels; and taking the gray level corresponding to the maximum background probability as the background gray level.
Further, the obtaining the defect probability of each pixel point according to the gray level difference and the permutation entropy includes:
obtaining the defect probability according to a defect probability formula; the defect probability formula comprises:
wherein P is the defect probability, H (m)' is the arrangement entropy of the m-th pixel point, ImFor the gray level corresponding to the mth pixel point, ImIs the background gray level.
Further, the obtaining the discrete degree of the defect probability of the pixel points in the sliding window includes:
and taking the variance of the defect probability in the sliding window as the discrete degree.
Further, the step of traversing the whole paint surface image according to the sliding window to obtain the whole defect area comprises the following steps:
traversing the whole paint surface image according to the sliding window; and reserving all the defect areas, and removing other areas to obtain the whole defect area.
Further, the repairing the paint surface according to the whole defect area comprises:
constructing a defect heat map according to the discrete degree of the sliding window corresponding to each pixel point in the whole defect area; the pixel value of each pixel point in the defect heat map is the discrete degree of the sliding window with the pixel point as a central point;
if the pixel value of the pixel point in the defect heat map is larger than a preset judgment threshold value, the corresponding position is considered as a serious defect area; otherwise, the corresponding position is regarded as a mild defect area;
obtaining the area ratio of the serious defect area in the paint surface image; if the area ratio is larger than a preset ratio threshold, repairing the whole defect area; otherwise, respectively carrying out repair treatment of different degrees on the serious defect area and the light defect area.
The invention also provides a furniture assembly paint spraying defect repairing system based on image processing, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one of the steps of the furniture assembly paint spraying defect repairing method based on image processing when executing the computer program.
The invention has the following beneficial effects:
the style information in the range is represented by the arrangement entropy in the pixel point neighborhood range. Namely, the more disordered the arrangement entropy, the more defective points are, and the difference is larger compared with other normal pixel points. The background gray level is further determined by analyzing the gray level of the image. And acquiring the defect probability according to the difference between the gray level of the pixel point and the background gray level and the corresponding arrangement entropy. Because the defect points of the orange peel defect are uniformly distributed, the more disordered the style information represented by the arrangement entropy, the larger the difference between the pixel level and the background pixel level, and the larger the probability of representing the orange peel defect. The whole paint image is processed through the sliding window, and the chaos degree of other isolated noise points and pixel difference characteristics influenced by illumination is not high compared with the orange peel defect, so that an effective discrete threshold value is set, and the final defect region can be ensured to be the orange peel defect region.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of 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 other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a furniture assembly painting defect repair method based on image processing according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a defect in orange peel according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an orange peel defect in a non-uniform state of a light source according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a furniture component painting defect repairing method and system based on image processing according to the present invention, with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof, the structure, the features and the effects thereof. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the furniture assembly paint spraying defect repairing method and system based on image processing in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a furniture assembly paint defect repairing method based on image processing according to an embodiment of the present invention is shown, where the method includes:
step S1: obtaining a paint surface image; acquiring a pixel difference sequence in a preset neighborhood range of each pixel point in a paint surface image; and obtaining the arrangement entropy of the pixel difference sequence of each pixel point.
The furniture assembly is dried after the painting by the painting equipment is completed. In order to realize automatic defect detection, in the embodiment of the invention, the dried furniture components are placed on a workshop conveyor belt, and a gray-scale camera is arranged on the conveyor belt, so that the paint surface images of different visual angles of each furniture component can be acquired. It should be noted that, the paint image needs to ensure the furniture assembly paint information to be complete and clear as much as possible. The speed of the conveyor belt and the sampling frequency of the camera are adjusted so that clear paint images of each furniture component on the conveyor belt can be accurately acquired.
Referring to fig. 2, a schematic diagram of a defect of orange peel according to an embodiment of the present invention is shown. The orange peel defects usually appear on the painted surface in a flaky manner, and the unevenness degree is small, so that the difference between the pixel characteristics of the abnormal region and the pixel characteristics of the normal region is not obvious, and the defect characteristics cannot be obtained directly through threshold segmentation or edge detection.
The main pixel characteristics of the orange peel defect appear on the pixel fluctuation, namely a large number of pixel points with similar gray level styles are distributed in the image, and the distribution is disordered. If the image has independent isolated noise points, similar gray level difference exists between the image and a plurality of neighborhood pixel points, and isolated characteristics are obvious. Fig. 3 is a schematic diagram illustrating an orange peel defect in a non-uniform state of a light source according to an embodiment of the present invention. If the image has pixel difference due to uneven illumination, the pixel points with gray scale change due to illumination are distributed more intensively, and an edge with obvious gray scale gradient exists in the image compared with the neighborhood normal pixel points. Therefore, the style information of a region can be reflected by the disorder degree of the gray level difference in the region in the image, that is, the probability that the corresponding style is the defect style is higher as the disorder degree of the gray level difference is higher. It should be noted that, in the case of fig. 3, the chaotic characteristic of the pixel difference can be analyzed in the highlight region, and although the pixel value changes, the defective pixel point can be identified in the subsequent analysis process.
And acquiring a pixel difference sequence in a preset neighborhood range of each pixel point in the paint surface image. The arrangement entropy of the pixel difference sequence is further calculated. The permutation entropy introduces the permutation idea while measuring the sequence complexity, and the more regular the sequence is, the smaller the corresponding permutation entropy is; the more complex the sequence, the greater the corresponding permutation entropy. The entropy size can be arranged as a neighborhood of style information for each pixel point. It should be noted that the permutation entropy calculation method is a technical means well known to those skilled in the art, and will not be described in detail herein.
In the embodiment of the present invention, the neighborhood range is set to be 8 neighborhood ranges, that is, the length of the pixel difference sequence is 8.
Step S2: obtaining a gray level histogram of the paint surface image; obtaining the background probability of each pixel point according to the occurrence frequency of each gray level in the gray level histogram; and obtaining the background gray level according to the background probability.
Most pixel points in the paint image are normal paint pixel points, and for defect detection, the normal paint pixel points are background pixel points, and the defect pixel points are foreground pixel points. Therefore, the appearance frequency P corresponding to each gray level in the paint image can be intuitively obtained through the gray histogramiI.e. by
Wherein, PiIs the frequency of occurrence of the ith gray level, AiThe number of appearance frequencies corresponding to the ith gray level is B, and the total number of pixel points in the paint image is B. The background probability corresponding to each pixel point can be obtained through the occurrence frequency, and the method specifically comprises the following steps:
and performing Gaussian fitting according to the occurrence frequency to obtain a background probability Gaussian model. Because the gray level of the background pixel point is necessarily located between the frequency maximum value and the average value of the gray histogram, the gray level i corresponding to the maximum occurrence frequency in the background probability Gaussian model can be considered to accord with the Gaussian distributionmAnd mean value of gray value
Mean value of gray values between as model mean value mu0Gray value i corresponding to the maximum frequency of occurrencemAnd mean value of gray value
The variance of gray values between them is the model variance σ0 2Namely:
wherein, mu0Is the mean value of the model and is,
is the mean of the grey values in the image of the paint surface, imFor the gray value corresponding to the maximum frequency of occurrence, piThe frequency of occurrence of the ith gray level.
Wherein σ0 2As model variance, μ0Is the mean value of the model and is,
is the mean of the grey values in the image of the paint surface, imThe gray value corresponding to the maximum frequency of occurrence is obtained.
Obtaining a background probability corresponding to the gray level of each pixel point according to the background probability Gaussian model, namely:
wherein, FiBackground probability, σ, for ith gray level0 2As model variance, μ0Is the model mean. The paint surface picture can be obtained by the formulaAnd obtaining the background probability corresponding to all the gray levels by using the background probability that the gray level corresponding to each pixel point belongs to the background, and taking the gray level corresponding to the maximum background probability as the background gray level.
Step S3: obtaining the gray level difference between the gray level corresponding to each pixel point and the background gray level; and obtaining the defect probability of each pixel point according to the gray level difference and the arrangement entropy.
For the orange peel defective pixel point, the pixel characteristics are different from those of the background pixel point, and the style information in the neighborhood range is comparatively chaotic, so that the gray level difference between the gray level corresponding to each pixel point and the background gray level is obtained, and the defect probability of each pixel point can be obtained by combining the arrangement entropy, which specifically comprises the following steps:
obtaining the defect probability according to a defect probability formula; the defect probability formula comprises:
wherein P is defect probability, H (m)' is arrangement entropy of mth pixel point, ImFor the gray level corresponding to the mth pixel point, ImIs the background gray level.
The defect probability formula considers the style information and the pixel information in the neighborhood range of the pixel point at the same time, the defect probability can be judged through the style information and the pixel information at the same time, the defect probability with strong reference is obtained, and the false detection and the omission caused by only considering a single factor are prevented.
Step S4: arranging a sliding window on the painting surface image; obtaining the discrete degree of the defect probability of the pixel points in the sliding window; if the discrete degree is greater than or equal to a preset discrete threshold value, taking the sliding window area as a defect area; and traversing the whole paint surface image according to the sliding window to obtain the whole defect area.
Through the processing of step S3, each pixel point in the paint image has a defect probability. The probability of local defects in the paint image can be analyzed by a sliding window of fixed size. Because the defective pixel points of the orange peel defect are distributed in a disordered and uneven manner, the discrete degree of the defect probability of the pixel points in the sliding window is calculated. The larger the discrete degree is, the larger the defect probability of the pixel points in the sliding window is, the distribution is dispersed, the fluctuation degree of the pixels in the sliding window area is large, and the corresponding area is an orange peel defect area. And if the discrete degree in the sliding window is greater than or equal to a preset discrete threshold value, taking the sliding window area as a defect area.
Preferably, the variance of the defect probability in the sliding window is used as the discrete degree. In an embodiment of the invention, the discrete threshold is set to 1.5 and the sliding window size is set to 20 x 20.
And traversing the sliding window through the whole paint surface image, reserving all the defect areas, and removing other areas to obtain the whole defect area. The whole defect area is an image which is as large as the paint surface image and only contains the information of the orange peel defect area.
It should be noted that, in order to facilitate the sliding window processing, a probability distribution map may be constructed according to the defect probability of each pixel point of the paint surface, and it should be noted that, in the embodiment of the present invention, the neighborhood size adopted in the style information calculation process is 8 neighborhoods, so that the style analysis is not performed on the pixel points at the edge of the paint surface image, that is, the edge pixel points do not have defect probability, so the size of the probability distribution map is shrunk by one pixel inward compared with the paint surface image, and the shrunk probability distribution map does not affect the defect determination.
Step S5: and repairing the painted surface according to the whole defect area.
In order to specifically repair the orange peel defect, the severity of the current orange peel defect needs to be analyzed, and a comprehensive repair measure is selected or a specific repair is performed on an area with different severity of the defect, specifically including:
and constructing a defect heat map according to the discrete degree of the sliding window corresponding to each pixel point in the whole defect area. The pixel value of each pixel point in the defect heat map is the discrete degree of a sliding window taking the pixel point as a central point.
The larger the discrete degree in the sliding window is, the larger the fluctuation of the gray characteristic of the pixel points is, the larger the degree of the unevenness of the surface of the paint is, and the more serious the corresponding orange peel defect is. And if the pixel value of the pixel point in the defect heat map is larger than a preset judgment threshold value, the corresponding position is considered as a serious defect area. Otherwise, the corresponding position is considered as a mild defect area.
The area ratio of the serious defect area in the paint surface image is obtained. And if the area ratio is larger than the preset ratio threshold, repairing the whole defect area. Otherwise, respectively carrying out repair treatment of different degrees on the serious defect area and the light defect area.
In the embodiment of the present invention, the determination threshold is set to 2.25, and the proportional threshold is set to 0.3. The repair treatment method for the whole defect area is to re-spray the paint surface. The repairing treatment methods which need to be respectively carried out to different degrees comprise the following steps: and re-spraying the serious defect area, and grinding and polishing the light defect area.
In summary, the style information of the neighborhood range is represented by the arrangement entropy in the neighborhood range of the pixel point. And obtaining a background gray level through the gray level histogram, and obtaining the defect probability of each pixel point by utilizing the gray level difference and style information of the pixel point and the background gray level. And judging whether the sliding window area is a defect area according to the set discrete degree of the defect probability of the pixel points in the sliding window, and finally obtaining the whole defect area in the paint surface image. According to the embodiment of the invention, the defect probability of the pixel point is determined through the style information, and the defect position is judged through the fluctuation of the defect probability, so that the orange peel defect positioning is realized, and the targeted repair of the defect is facilitated.
The invention also provides a furniture assembly paint spraying defect repairing system based on image processing, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the computer program, any one of the steps of the furniture assembly paint spraying defect repairing method based on image processing is realized.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An image processing-based furniture assembly painting defect repairing method is characterized by comprising the following steps:
obtaining a paint surface image; acquiring a pixel difference sequence in a preset neighborhood range of each pixel point in the paint surface image; obtaining the arrangement entropy of the pixel difference sequence of each pixel point;
obtaining a gray level histogram of the paint surface image; obtaining the background probability of each pixel point according to the occurrence frequency of each gray level in the gray level histogram; obtaining a background gray level according to the background probability;
obtaining the gray level difference between the gray level corresponding to each pixel point and the background gray level; obtaining the defect probability of each pixel point according to the gray level difference and the arrangement entropy;
arranging a sliding window on the painting surface image; obtaining the discrete degree of the defect probability of the pixel points in the sliding window; if the discrete degree is larger than or equal to a preset discrete threshold value, taking the sliding window area as a defect area; traversing the whole paint surface image according to the sliding window to obtain an integral defect area;
and repairing the painted surface according to the integral defect area.
2. The method for repairing painting defect of furniture assembly based on image processing as claimed in claim 1, wherein said obtaining background probability of each pixel point according to occurrence frequency of each gray level in said gray histogram comprises:
performing Gaussian fitting according to the occurrence frequency to obtain a background probability Gaussian model; and obtaining the background probability corresponding to the gray level of each pixel point according to the background probability Gaussian model.
3. The image processing-based furniture assembly painting defect repairing method according to claim 1, wherein the obtaining a background gray level according to the background probability comprises:
obtaining the background probability corresponding to all gray levels; and taking the gray level corresponding to the maximum background probability as the background gray level.
4. The method for repairing paint defects of furniture components based on image processing as claimed in claim 1, wherein the obtaining the defect probability of each pixel point according to the gray level difference and the arrangement entropy comprises:
obtaining the defect probability according to a defect probability formula; the defect probability formula comprises:
wherein P is the defect probability, H (m)' is the arrangement entropy of the m-th pixel point, ImFor the gray level corresponding to the mth pixel point, ImIs the background gray level.
5. The method for repairing painting defect of furniture assembly based on image processing as claimed in claim 1, wherein said obtaining the discrete degree of probability of defect of pixel points in the sliding window comprises:
and taking the variance of the defect probability in the sliding window as the discrete degree.
6. The image processing-based furniture assembly painting defect repairing method according to claim 1, wherein the step of traversing the whole painting surface image according to the sliding window to obtain the whole defect area comprises the following steps:
traversing the whole paint surface image according to the sliding window; and reserving all the defect areas, and removing other areas to obtain the whole defect area.
7. The image processing-based furniture assembly painting defect repair method according to claim 1, wherein the repairing of the painted surface according to the overall defect area comprises:
constructing a defect heat map according to the discrete degree of the sliding window corresponding to each pixel point in the whole defect area; the pixel value of each pixel point in the defect heat map is the discrete degree of the sliding window with the pixel point as a central point;
if the pixel value of the pixel point in the defect heat map is larger than a preset judgment threshold value, the corresponding position is considered as a serious defect area; otherwise, the corresponding position is regarded as a mild defect area;
obtaining the area ratio of the serious defect area in the paint surface image; if the area ratio is larger than a preset ratio threshold, repairing the whole defect area; otherwise, respectively carrying out repair treatment of different degrees on the serious defect area and the light defect area.
8. An image processing based furniture component painting defect repair system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111552442.3A CN114240888B (en) | 2021-12-17 | 2021-12-17 | Furniture assembly paint spraying defect repairing method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111552442.3A CN114240888B (en) | 2021-12-17 | 2021-12-17 | Furniture assembly paint spraying defect repairing method and system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114240888A true CN114240888A (en) | 2022-03-25 |
| CN114240888B CN114240888B (en) | 2022-09-20 |
Family
ID=80758047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111552442.3A Active CN114240888B (en) | 2021-12-17 | 2021-12-17 | Furniture assembly paint spraying defect repairing method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114240888B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693650A (en) * | 2022-03-31 | 2022-07-01 | 南通俊朗智能科技有限公司 | Intelligent control method of mixing machine based on machine vision |
| CN114708325A (en) * | 2022-03-31 | 2022-07-05 | 南通华烨塑料工业有限公司 | Method for quickly positioning rubber production problem based on rubber blooming defect |
| CN114841939A (en) * | 2022-04-24 | 2022-08-02 | 启东市鸿盛纺织有限公司 | Grey cloth defect degree analysis method based on image processing |
| CN114878574A (en) * | 2022-03-31 | 2022-08-09 | 南通东德纺织科技有限公司 | Cloth defect detection method, device and system based on machine vision |
| CN114897772A (en) * | 2022-03-31 | 2022-08-12 | 南通奥尔嘉橡塑有限公司 | Method for regulating and controlling positive vulcanization of rubber based on machine vision |
| CN114998187A (en) * | 2022-03-31 | 2022-09-02 | 江苏仙岳材料科技有限公司 | Glass fiber separator defect detection method and system |
| CN115082418A (en) * | 2022-07-14 | 2022-09-20 | 山东聊城富锋汽车部件有限公司 | Precise identification method for automobile parts |
| CN115294144A (en) * | 2022-10-10 | 2022-11-04 | 雷戈锘智能家居(南通)有限公司 | Method for identifying surface defects of furniture composite board |
| CN117078679A (en) * | 2023-10-16 | 2023-11-17 | 东莞百舜机器人技术有限公司 | Automatic assembly line production detection method for cooling fan based on machine vision |
| CN117218115A (en) * | 2023-11-07 | 2023-12-12 | 江苏玫源新材料有限公司 | Auto part paint surface abnormality detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107490579A (en) * | 2016-06-09 | 2017-12-19 | 本田技研工业株式会社 | Defect detecting method and its equipment |
| CN109377485A (en) * | 2018-10-12 | 2019-02-22 | 龙口味美思环保科技有限公司 | A kind of instant noodles packaging defect machine vision detection method |
| CN109461149A (en) * | 2018-10-31 | 2019-03-12 | 泰州市创新电子有限公司 | The intelligent checking system and method for lacquered surface defect |
| CN110530883A (en) * | 2019-09-30 | 2019-12-03 | 凌云光技术集团有限责任公司 | A kind of defect inspection method |
| CN111654719A (en) * | 2020-06-11 | 2020-09-11 | 三峡大学 | Video micro-motion detection method based on permutation entropy algorithm |
| CN112414715A (en) * | 2020-11-05 | 2021-02-26 | 西安工程大学 | Bearing fault diagnosis method based on mixed feature and improved gray level co-occurrence algorithm |
| CN112991305A (en) * | 2021-03-24 | 2021-06-18 | 苏州亚朴智能科技有限公司 | Visual inspection method for surface defects of paint spraying panel |
| CN113610767A (en) * | 2021-07-14 | 2021-11-05 | 温州大学 | Medical image multi-threshold segmentation method based on improved goblet sea squirt group algorithm |
-
2021
- 2021-12-17 CN CN202111552442.3A patent/CN114240888B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107490579A (en) * | 2016-06-09 | 2017-12-19 | 本田技研工业株式会社 | Defect detecting method and its equipment |
| CN109377485A (en) * | 2018-10-12 | 2019-02-22 | 龙口味美思环保科技有限公司 | A kind of instant noodles packaging defect machine vision detection method |
| CN109461149A (en) * | 2018-10-31 | 2019-03-12 | 泰州市创新电子有限公司 | The intelligent checking system and method for lacquered surface defect |
| CN110530883A (en) * | 2019-09-30 | 2019-12-03 | 凌云光技术集团有限责任公司 | A kind of defect inspection method |
| CN111654719A (en) * | 2020-06-11 | 2020-09-11 | 三峡大学 | Video micro-motion detection method based on permutation entropy algorithm |
| CN112414715A (en) * | 2020-11-05 | 2021-02-26 | 西安工程大学 | Bearing fault diagnosis method based on mixed feature and improved gray level co-occurrence algorithm |
| CN112991305A (en) * | 2021-03-24 | 2021-06-18 | 苏州亚朴智能科技有限公司 | Visual inspection method for surface defects of paint spraying panel |
| CN113610767A (en) * | 2021-07-14 | 2021-11-05 | 温州大学 | Medical image multi-threshold segmentation method based on improved goblet sea squirt group algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 钱诚 等: ""基于排列组合熵和灰度特征的纹理分割"", 《计算机应用》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897772B (en) * | 2022-03-31 | 2024-05-14 | 河南省开仑化工有限责任公司 | Method for regulating and controlling forward vulcanization of rubber based on machine vision |
| CN114708325A (en) * | 2022-03-31 | 2022-07-05 | 南通华烨塑料工业有限公司 | Method for quickly positioning rubber production problem based on rubber blooming defect |
| CN114878574A (en) * | 2022-03-31 | 2022-08-09 | 南通东德纺织科技有限公司 | Cloth defect detection method, device and system based on machine vision |
| CN114897772A (en) * | 2022-03-31 | 2022-08-12 | 南通奥尔嘉橡塑有限公司 | Method for regulating and controlling positive vulcanization of rubber based on machine vision |
| CN114998187A (en) * | 2022-03-31 | 2022-09-02 | 江苏仙岳材料科技有限公司 | Glass fiber separator defect detection method and system |
| CN114693650A (en) * | 2022-03-31 | 2022-07-01 | 南通俊朗智能科技有限公司 | Intelligent control method of mixing machine based on machine vision |
| CN114693650B (en) * | 2022-03-31 | 2024-05-24 | 无锡市慧航智能科技有限公司 | Intelligent control method of mixer based on machine vision |
| CN114841939A (en) * | 2022-04-24 | 2022-08-02 | 启东市鸿盛纺织有限公司 | Grey cloth defect degree analysis method based on image processing |
| CN114841939B (en) * | 2022-04-24 | 2024-05-24 | 杭州丰越丝绸织造有限公司 | Grey cloth defect degree analysis method based on image processing |
| CN115082418A (en) * | 2022-07-14 | 2022-09-20 | 山东聊城富锋汽车部件有限公司 | Precise identification method for automobile parts |
| CN115294144A (en) * | 2022-10-10 | 2022-11-04 | 雷戈锘智能家居(南通)有限公司 | Method for identifying surface defects of furniture composite board |
| CN117078679B (en) * | 2023-10-16 | 2023-12-15 | 东莞百舜机器人技术有限公司 | Automatic assembly line production detection method for cooling fan based on machine vision |
| CN117078679A (en) * | 2023-10-16 | 2023-11-17 | 东莞百舜机器人技术有限公司 | Automatic assembly line production detection method for cooling fan based on machine vision |
| CN117218115B (en) * | 2023-11-07 | 2024-02-20 | 江苏玫源新材料有限公司 | Auto part paint surface abnormality detection method |
| CN117218115A (en) * | 2023-11-07 | 2023-12-12 | 江苏玫源新材料有限公司 | Auto part paint surface abnormality detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114240888B (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114240888B (en) | Furniture assembly paint spraying defect repairing method and system based on image processing | |
| CN114972357B (en) | Roller surface defect detection method and system based on image processing | |
| CN113498528B (en) | Image defect determining method and device, electronic equipment and storage medium | |
| CN109242853B (en) | PCB defect intelligent detection method based on image processing | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN103543394A (en) | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment | |
| CN116168026A (en) | Water quality detection method and system based on computer vision | |
| CN116758083A (en) | Quick detection method for metal wash basin defects based on computer vision | |
| CN115222743B (en) | Furniture surface paint spraying defect detection method based on vision | |
| CN108664839B (en) | Image processing method and device | |
| CN112378350B (en) | Flatness detection method for PIN PIN of network transformer | |
| WO2021118463A1 (en) | Defect detection in image space | |
| CN111739012A (en) | Camera module white spot detecting system based on turntable | |
| CN115330767A (en) | Method for identifying production abnormity of corrosion foil | |
| CN115100174B (en) | Ship sheet metal part paint surface defect detection method | |
| Savelli et al. | Illumination correction by dehazing for retinal vessel segmentation | |
| CN105869135A (en) | Tire defect detection method and device | |
| CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
| Truong et al. | Automatic multi-thresholds selection for image segmentation based on evolutionary approach | |
| CN115797314A (en) | Part surface defect detection method, system, equipment and storage medium | |
| CN112288682A (en) | Electric power equipment defect positioning method based on image registration | |
| CN114937003A (en) | Multi-type defect detection system and method for glass panel | |
| CN113129265A (en) | Method and device for detecting surface defects of ceramic tiles and storage medium | |
| CN114882387B (en) | Bearing raceway bruise identification and automatic polishing positioning method in grinding process |
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 |