CN116596929A - Automobile rearview mirror production quality monitoring system - Google Patents
Automobile rearview mirror production quality monitoring system Download PDFInfo
- Publication number
- CN116596929A CN116596929A CN202310875882.5A CN202310875882A CN116596929A CN 116596929 A CN116596929 A CN 116596929A CN 202310875882 A CN202310875882 A CN 202310875882A CN 116596929 A CN116596929 A CN 116596929A
- Authority
- CN
- China
- Prior art keywords
- degree
- lamp strip
- small lamp
- abnormal
- image
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 20
- 238000012544 monitoring process Methods 0.000 title claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims abstract description 75
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000005856 abnormality Effects 0.000 claims description 50
- 238000000034 method Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 8
- 230000011218 segmentation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- 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)
- Multimedia (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the field of image data processing, in particular to a production quality monitoring system of an automobile rearview mirror, which comprises the following components: the image data acquisition and preprocessing module is used for acquiring an image and preprocessing the image to obtain a lamp band image; the image anomaly detection module is used for obtaining the anomaly degree of the distance between the center points of the adjacent small lamp strip communicating domains according to the center point of each small lamp strip communicating domain and marking the anomaly degree as a first anomaly degree; obtaining the abnormal degree of the central point of any small lamp strip communicating domain according to the first abnormal degree and the included angle between the connecting line of the central points of the adjacent small lamp strip communicating domains and the small lamp strip direction, and marking the abnormal degree as a second abnormal degree; obtaining the relative abnormal degree of each small lamp strip communicating domain according to the second abnormal degree, and marking the relative abnormal degree as a third abnormal degree; and the scratch judgment module is used for judging scratches according to the third abnormal degree and a preset threshold value. The application obtains the abnormal degree of the center point of each small lamp strip by using image data processing, so that the judgment of scratches is more accurate.
Description
Technical Field
The application relates to the technical field of image data processing, in particular to a production quality monitoring system of an automobile rearview mirror.
Background
In the production and assembly process of automobile parts, the steering lamp of the automobile rearview mirror shell may be worn or scratched, namely, quality problems and appearance defects exist, and the overall quality and normal sales of the automobile are affected. The area of the rear view mirror strip is located on the rear view mirror housing of the vehicle head, which gives a signal to pedestrians and vehicles in front of the vehicle when the vehicle turns, so that the turn light of the rear view mirror housing is also very important, wherein the turn light of the rear view mirror housing is composed of a row of light strips. Because the turn signal strip of the rearview mirror housing is easily damaged by external factors, the surface scratch of the turn signal strip of the rearview mirror housing is the most common appearance quality problem.
In the detection process, scratches in the gray level map near the turn light strip are similar to the gray level value of the turn light, and are difficult to distinguish. Therefore, whether the rearview mirror has appearance quality defects or not is judged by visually detecting the lamp strip communicating areas of the steering lamp.
Disclosure of Invention
The application provides a production quality monitoring system of an automobile rearview mirror, which aims to solve the existing problems.
The application relates to a production quality monitoring system of an automobile rearview mirror, which adopts the following technical scheme:
one embodiment of the application provides a production quality monitoring system for an automobile rearview mirror, which comprises:
the image data acquisition and preprocessing module is used for acquiring an image and preprocessing the image to obtain a lamp band image;
the image anomaly detection module is used for acquiring the central point of each small lamp strip communication domain according to the lamp strip image, and acquiring the anomaly degree of the distance between the central points of the adjacent small lamp strip communication domains according to the central point of each small lamp strip communication domain, and recording the anomaly degree as a first anomaly degree; obtaining an included angle between a connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction according to the central point of the small lamp strip communicating domain, obtaining an abnormal degree of the central point of any small lamp strip communicating domain according to the first abnormal degree and the included angle between the connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction, and recording the abnormal degree as a second abnormal degree; obtaining the relative abnormal degree of each small lamp strip communicating domain according to the second abnormal degree, and marking the relative abnormal degree as a third abnormal degree;
and the scratch judgment module is used for normalizing the third abnormal degree to obtain the normalized third abnormal degree, and judging the scratches of the lamp strip image according to the normalized third abnormal degree and a preset threshold value.
Further, the specific obtaining formula of the first abnormality degree is as follows:
in the formula, the z-th small lamp strip communicating region and the next adjacent small lamp strip communicating region are marked as target combinations,representing the variance of the distance between the central points of every two adjacent small light bar connected domains except the target combination, and the ∈>Representing the variance of the distance between the central points of all two adjacent small light bar connected domains +.>And the degree of abnormality of the distance between the central points of two adjacent small light bar connected domains in the target combination is expressed, namely, the first degree of abnormality.
Further, the specific acquisition method of the included angle between the connecting line of the central point of the communicating region of the adjacent small lamp strips and the direction of the small lamp strips comprises the following steps:
the direction of the small light bar refers to the direction in which the smallest external rectangle long axis of the small light bar communicating region is positioned, and finally, the included angle between the connecting line of the central point of the adjacent small light bar communicating region and the direction of the small light bar is obtained.
Further, the specific obtaining formula of the second abnormality degree is as follows:
in the method, in the process of the application,indicating the degree of abnormality of the y-th block in the lamp band image, and recording it as the second degree of abnormality,/->Indicating the abnormal degree of the distance between the center point of the x-th small lamp strip communicating region in the y-th block and the center point of the adjacent small lamp strip communicating region, < > in->The included angle between the connecting line of the central point of the x-th small lamp strip connecting domain in the y-th block and the central point of the adjacent small lamp strip connecting domain and the x-th small lamp strip direction is represented, and n represents the number of the small lamp strip connecting domains in any block.
Further, the specific obtaining formula of the third abnormality degree is as follows:
in the method, in the process of the application,indicating the relative abnormality degree of the y-th block in the lamp band image, and recording as the third abnormality degree,/->Indicating the degree of abnormality of the y-th bar in the strip image,/->Indicating the degree of abnormality of the w-th block in the lamp band image,/->Indicating the number of preset blocks.
Further, the judging specific operation of the scratch is as follows:
performing linear normalization on the third abnormal degree to obtain the relative abnormal degree of each block after normalization, and marking the relative abnormal degree as a group of relative abnormal data; and when the data larger than the preset threshold value exists in the relative abnormal data, judging that scratches exist on the steering lamp of the rearview mirror housing.
The technical scheme of the application has the beneficial effects that: the application has the following advantages compared with the prior art: the probability of existence of scratches in the area can be judged according to the abnormal degree of the distance between the light bars, and the confidence level is constructed to optimize the probability, so that existence of the scratch defects in the area of the light band can be accurately judged.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of an automobile rearview mirror production quality monitoring system in accordance with the present application;
FIG. 2 is a schematic view of a lamp strip of an automobile rearview mirror production quality monitoring system according to the present application;
FIG. 3 is a schematic diagram of a small light bar of the system for monitoring the production quality of the automobile rearview mirror;
fig. 4 is a schematic diagram of scratch of a system for monitoring production quality of an automobile rearview mirror.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of an automobile rearview mirror production quality monitoring system according to the application with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme of the production quality monitoring system for the automobile rearview mirror provided by the application with reference to the accompanying drawings.
Referring to fig. 1, a system block diagram of an automobile rearview mirror production quality monitoring system according to an embodiment of the present application is shown, the system includes:
module S001: and the image data acquisition and preprocessing module is used for acquiring an image and preprocessing the image to obtain a lamp band image.
Because this embodiment detects the scratch that appears at the in-process of installing the rear-view mirror, so after the rear-view mirror installation, park whole car in appointed detection area, in car quality testing process like this, adjust ambient light to even degree, reduce ambient light to the influence of detection. The background color is distinguished from the white light color during image acquisition, the dark background is selected to facilitate the subsequent removal of the background, the reflector light area is separated, and the image is acquired by using a fixed camera.
And carrying out graying treatment on the acquired image to obtain a gray image. In the image at this time, the lamp band connected domain is acquired through the Otsu algorithm, and the lamp band region image can be extracted by multiplying the lamp band connected domain with the original image for subsequent image recognition and processing, as shown in fig. 2.
The longer area of the light strip, the texture characteristic of the light strip can also lead to uneven surface reflection, and the single threshold segmentation can lead to incomplete segmentation of partial images. Therefore, the image is segmented, each block is processed independently, the influence of reflection on image analysis can be reduced, and an ideal binary segmentation effect is obtained.
Because whether scratches exist or not is judged according to the integrity of the small light bar connected domains, the integrity of the small light bar connected domains needs to be maintained as much as possible in the blocking process, and therefore the blocking is carried out in the direction perpendicular to the light band. And processing the original gray level image Otsu algorithm to obtain a lamp band communicating region, and taking the upper left point and the upper right point of the lamp band communicating region as straight lines, thereby describing the extending direction of the lamp band. The preset block number threshold is a, where the embodiment is described by taking a=4 as an example, and the embodiment is not specifically limited, where a may be determined according to the specific implementation, and the image is averagely divided into a blocks perpendicular to the line for subsequent image processing analysis. As shown in fig. 3.
After the image is segmented, the image can be subjected to binarization segmentation by using a single threshold value because the illumination intensity is uniform in a single area, the optimal segmentation threshold value is respectively obtained for each area image by using an Ojin method, and the corresponding lamp area is subjected to binarization processing.
The preset area threshold is d, where the embodiment is described by taking d=10 as an example, and the embodiment is not specifically limited, where d may be determined according to the specific implementation situation. In order to reduce the image analyzed by partial noise, the connected domain with the area smaller than 1/d of the largest connected domain in the image is removed.
The scratches on the lamp strip of the automobile reflector turn lamp can divide the vertical small lamp strip communication domain on the lamp strip into two communication domains, so that whether the scratches exist or not can be judged, and as shown in fig. 4, θ represents an angle.
So far, a binary image and a preprocessed lamp band image are obtained.
Module S002: the image anomaly detection module is used for acquiring the central point of each small lamp strip communication domain according to the lamp strip image, and acquiring the anomaly degree of the distance between the central points of the adjacent small lamp strip communication domains according to the central point of each small lamp strip communication domain, and recording the anomaly degree as a first anomaly degree; obtaining an included angle between a connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction according to the central point of the small lamp strip communicating domain, obtaining an abnormal degree of the central point of any small lamp strip communicating domain according to the first abnormal degree and the included angle between the connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction, and recording the abnormal degree as a second abnormal degree; and obtaining the relative abnormal degree of each small lamp strip connected domain according to the second abnormal degree, and marking the relative abnormal degree as a third abnormal degree.
In the binary image, the scratch may cause the single small light bar connected domain to be disconnected and divided into two connected domains, resulting in the offset of the center point of the small light bar connected domain. So the degree of abnormality of the central point of the single small lamp strip connected domain is obtained by analysis. After the abnormal degree of the single point is obtained, calculating the whole abnormal degree according to the link line direction of the central points of the adjacent connected domains of the small lamp strip as a weight. The scratch existing region is obtained according to the difference between the blocks. Therefore, the present embodiment processes the lamp band image to obtain a process of a relative degree of abnormality for each block.
It should be further noted that, by removing the distance between any two adjacent center points, the weight change in the variance is determined, so as to obtain the variance weight, and the higher the variance weight is, the more the distance between the two adjacent center points is abnormal. After threshold segmentation, the difference between the distance between the central points of any two adjacent small light bar communicating domains and the average distance between the central points of all the adjacent small light bars is larger, and the occupied weight is higher in the calculation process of the distance variance between the central points of all the adjacent small light bars, so that the adjacent central points are abnormal. If the distance between the center point of one of the communicating areas and the adjacent center point is eliminated in the calculation process of the distance variance between all adjacent center points, the calculation result is compared with the distance variance between all adjacent center points, and the influence of the distance between the center point of any one communicating area and the adjacent center point on the distance variance between all adjacent center points can be judged. After the distance between the center point of any connected domain and the adjacent center point is eliminated, the larger the value variation amplitude of the distance variance between all the adjacent center points is, the larger the abnormality degree of the distance between the center point and the adjacent center point is.
Any two adjacent small light bar communicating domains are marked as target combinations, in the embodiment, the z-th small light bar communicating domain and the z+1th small light bar communicating domain are marked as target combinations, and the Euclidean distance of the center points of the two communicating domains in the target combinations can be marked as。
Obtaining Euclidean distances of central points of all adjacent small lamp strip connected domains, and recording variances of the Euclidean distances as；
Except for the target combination, the Euclidean distances of the central points of the connecting domains of the rest adjacent small lamp bars are obtained, and the variances of the Euclidean distances are recorded as。
The degree of abnormality of the two adjacent small light bar connected domains in the target combination is:
in the method, in the process of the application,representing the variance of Euclidean distance between the corresponding central points of every two adjacent small light bar connected domains except the target combination>Representing the variance of Euclidean distance between the central points of all adjacent two small lamp strip connected domains, ++>And the abnormal degree of the distance between two adjacent small light bar connected domains in the target combination is represented.
And similarly, obtaining the abnormal degree of the distance between the central points of all adjacent small lamp strip communicating areas.
Wherein whenThe larger the value of (c) is, the more the distance between the center point and the adjacent center point deviates from the normal value, and the higher the probability of scratch existence is.
It should be noted that, according to the degree of abnormality of the central point of the connected domain of the adjacent small light bars, the direction of the connecting line between the connected domains of the adjacent two small light bars is used as the weight value, and the degree of abnormality of the central point of the connected domain of the whole small light bars is calculated.
It should be further noted that, the direction of the small light bar connected domain is perpendicular to the direction of the light strip, and the small light bar connected domains are uniformly distributed, so that the direction of the connecting line of the central points of the adjacent small light bar connected domains should be the same as the direction of the light strip, when the central points of the connected domains of the small light bar deviate due to scratches, the direction of the connecting line of the central points of the adjacent small light bar connected domains can be changed, so that the confidence of the abnormal degree of the central point can be calculated by the included angle between the direction of the connecting line of the central point of the small light bar connected domains and the direction of the light bar, and the confidence is used as the weight for calculating the abnormal degree of the central point of the whole small light bar connected domain. The direction of the small lamp strip is determined, then the connecting line is determined through the coordinates of the adjacent central points, and finally the included angle between the connecting line of the adjacent central points and the direction of the small lamp strip is determined.
The following description will take any preset block as an example.
The degree of abnormality of the preset block is:
in the method, in the process of the application,indicating the degree of abnormality of the y-th block in the lamp band image,/->Indicating the abnormal degree of the distance between the center point of the x-th small lamp strip communicating region in the y-th block and the center point of the adjacent small lamp strip communicating region, < > in->The included angle between the connecting line of the central point of the x-th small lamp strip connecting domain in the y-th block and the central point of the adjacent small lamp strip connecting domain and the x-th small lamp strip direction is represented, and n represents the number of the small lamp strip connecting domains in the y-th block. The direction of the small light bar refers to the direction of the smallest circumscribed rectangle long axis of the small light bar connected domain.
And similarly, obtaining the abnormality degree of all the preset blocks. And judging scratches according to the abnormal degree of each block.
Wherein whenThe larger the value of (2), the higher the probability of scratches in the small light bar; when->The larger the value of (2), namely the larger the included angle, the higher the degree confidence of abnormality of the central point of the small light bar connected domain; />The confidence coefficient of the degree of abnormality of the central point of the x-th small lamp strip communicating domain in the y-th block is represented, namely, the central point of the x-th small lamp strip communicating domain is connected with the central point of the adjacent small lamp strip communicating domain, the sine function value of the included angle between the central point of the x-th small lamp strip communicating domain and the direction of the lamp strip is taken as the adjusting coefficient of the degree of abnormality corresponding to the x-th small lamp strip communicating domain, namely, the corresponding confidence coefficient is represented, when the included angle between the direction of the central point of the x-th small lamp strip communicating domain connected with the direction of the lamp strip is 0, the abnormal confidence coefficient is 0 at the minimum, and when the included angle between the direction of the central point of the x-th small lamp strip communicating domain connected with the direction of the lamp strip is 90 degrees, the abnormal confidence coefficient is 1 at the maximum.
After obtaining the degree of abnormality of each block, the relative abnormality value of each block is calculated according to the difference in degree of abnormality between blocks. The degree of abnormality of the normal region is small and close, and the degree of abnormality of the abnormal region is large and discrete relative to the degree of abnormality of the normal region.
The relative degree of abnormality per block is:
in the method, in the process of the application,indicating the relative degree of abnormality of the y-th block in the lamp band image,/->Indicating the degree of abnormality of the y-th block in the lamp band image,/->Indicating the degree of abnormality of the w-th block in the lamp band image,/->Indicating a preset number of blocks.
Wherein,,describe->To->Sum of the numerical value-size distances of +.>Then indicate +.>The higher the degree of abnormality of the block is, the more the degree of abnormality deviates from the normal region, the greater the relative degree of abnormality is, when +>The larger the value of (2), the greater the probability of scratch abnormality being present inside.
Based on this, the relative degree of abnormality of each block is the third degree of abnormality.
Module S003: and the scratch judgment module is used for normalizing the third abnormal degree to obtain the normalized third abnormal degree, and judging the scratches of the lamp strip image according to the normalized third abnormal degree and a preset threshold value.
A threshold b is preset, where the embodiment is described by taking b=0.5 as an example, and the embodiment is not specifically limited, where b may be determined according to the specific implementation.
Performing linear normalization processing on the third abnormal degree of the scratch according to the third abnormal degree of the image block, obtaining the third abnormal degree of all blocks after normalization, and marking the third abnormal degree as a group of relative abnormal data; when the data larger than the threshold b exists in the group of relative abnormal data, the scratch is judged to exist on the turn signal lamp of the rearview mirror housing, and the replacement is needed.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the application.
Claims (6)
1. A quality monitoring system for automobile rearview mirror production, the system comprising:
the image data acquisition and preprocessing module is used for acquiring an image and preprocessing the image to obtain a lamp band image;
the image anomaly detection module is used for acquiring the central point of each small lamp strip communication domain according to the lamp strip image, and acquiring the anomaly degree of the distance between the central points of the adjacent small lamp strip communication domains according to the central point of each small lamp strip communication domain, and recording the anomaly degree as a first anomaly degree; obtaining an included angle between a connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction according to the central point of the small lamp strip communicating domain, obtaining an abnormal degree of the central point of any small lamp strip communicating domain according to the first abnormal degree and the included angle between the connecting line of the central point of the small lamp strip communicating domain and the small lamp strip direction, and recording the abnormal degree as a second abnormal degree; obtaining the relative abnormal degree of each small lamp strip communicating domain according to the second abnormal degree, and marking the relative abnormal degree as a third abnormal degree;
and the scratch judgment module is used for normalizing the third abnormal degree to obtain the normalized third abnormal degree, and judging the scratches of the lamp strip image according to the normalized third abnormal degree and a preset threshold value.
2. The automobile rearview mirror production quality monitoring system as claimed in claim 1, wherein the specific acquisition formula of the first abnormality degree is:
in the formula, the firstThe combination of the z small lamp strip communicating domains and the adjacent small lamp strip communicating domains is marked as a target combination,representing the variance of the distance between the central points of every two adjacent small light bar connected domains except the target combination, and the ∈>Representing the variance of the distance between the central points of all two adjacent small light bar connected domains +.>And the degree of abnormality of the distance between the central points of two adjacent small light bar connected domains in the target combination is expressed, namely, the first degree of abnormality.
3. The automobile rearview mirror production quality monitoring system according to claim 1, wherein the specific acquisition method of the included angle between the connecting line of the central point of the adjacent small lamp strip communicating region and the small lamp strip direction is as follows:
the direction of the small light bar refers to the direction in which the smallest external rectangle long axis of the small light bar communicating region is positioned, and finally, the included angle between the connecting line of the central point of the adjacent small light bar communicating region and the direction of the small light bar is obtained.
4. The automobile rearview mirror production quality monitoring system as claimed in claim 1, wherein the specific obtaining formula of the second abnormality degree is:
in the method, in the process of the application,indicating the degree of abnormality of the y-th block in the lamp band image, and recording it as the second degree of abnormality,/->Indicating the abnormal degree of the distance between the center point of the x-th small lamp strip communicating region in the y-th block and the center point of the adjacent small lamp strip communicating region, < > in->The included angle between the central point of the x-th small lamp strip communicating domain in the y-th block and the central point of the adjacent small lamp strip communicating domain and the direction of the x-th small lamp strip is represented, and n represents the number of the small lamp strip communicating domains in any block.
5. The automobile rearview mirror production quality monitoring system as claimed in claim 1, wherein the specific obtaining formula of the third abnormality degree is:
in the method, in the process of the application,indicating the relative abnormality degree of the y-th block in the lamp band image, and recording as the third abnormality degree,/->Indicating the degree of abnormality of the y-th bar in the strip image,/->Indicating the degree of abnormality of the w-th block in the lamp band image,/->Indicating the number of preset blocks.
6. The system according to claim 1, wherein the determining means for the scratch is operative to:
performing linear normalization on the third abnormal degree to obtain the relative abnormal degree of each block after normalization, and marking the relative abnormal degree as a group of relative abnormal data; and when the data larger than the preset threshold value exists in the relative abnormal data, judging that scratches exist on the steering lamp of the rearview mirror housing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875882.5A CN116596929B (en) | 2023-07-18 | 2023-07-18 | Automobile rearview mirror production quality monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875882.5A CN116596929B (en) | 2023-07-18 | 2023-07-18 | Automobile rearview mirror production quality monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596929A true CN116596929A (en) | 2023-08-15 |
| CN116596929B CN116596929B (en) | 2023-10-20 |
Family
ID=87599490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310875882.5A Active CN116596929B (en) | 2023-07-18 | 2023-07-18 | Automobile rearview mirror production quality monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596929B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003130806A (en) * | 2001-10-29 | 2003-05-08 | National Institute Of Advanced Industrial & Technology | Method and device for detecting surface flaw of the like |
| CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
| JP2016212060A (en) * | 2015-05-13 | 2016-12-15 | 国立大学法人岐阜大学 | Mirror surface inspecting device |
| CN110038822A (en) * | 2019-04-20 | 2019-07-23 | 东莞中科蓝海智能视觉科技有限公司 | The visible detection method of reflective annulus part |
| CN114486939A (en) * | 2022-04-08 | 2022-05-13 | 欧普康视科技股份有限公司 | Lens scratch detection system and method |
| CN216926601U (en) * | 2021-11-12 | 2022-07-08 | 宁波知日智能设备有限公司 | Full-automatic detection equipment of automobile rearview mirror |
| CN115049638A (en) * | 2022-07-21 | 2022-09-13 | 启东晶尧光电科技有限公司 | Screen printing glass defect detection method and device based on image processing |
| US20230024259A1 (en) * | 2021-07-20 | 2023-01-26 | United Microelectronics Corp. | Wafer backside defect detection method and wafer backside defect detection apparatus |
| CN116205903A (en) * | 2023-03-28 | 2023-06-02 | 上汽大众汽车有限公司 | Method for detecting defects of vehicle body finish paint |
-
2023
- 2023-07-18 CN CN202310875882.5A patent/CN116596929B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003130806A (en) * | 2001-10-29 | 2003-05-08 | National Institute Of Advanced Industrial & Technology | Method and device for detecting surface flaw of the like |
| CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
| JP2016212060A (en) * | 2015-05-13 | 2016-12-15 | 国立大学法人岐阜大学 | Mirror surface inspecting device |
| CN110038822A (en) * | 2019-04-20 | 2019-07-23 | 东莞中科蓝海智能视觉科技有限公司 | The visible detection method of reflective annulus part |
| US20230024259A1 (en) * | 2021-07-20 | 2023-01-26 | United Microelectronics Corp. | Wafer backside defect detection method and wafer backside defect detection apparatus |
| CN216926601U (en) * | 2021-11-12 | 2022-07-08 | 宁波知日智能设备有限公司 | Full-automatic detection equipment of automobile rearview mirror |
| CN114486939A (en) * | 2022-04-08 | 2022-05-13 | 欧普康视科技股份有限公司 | Lens scratch detection system and method |
| CN115049638A (en) * | 2022-07-21 | 2022-09-13 | 启东晶尧光电科技有限公司 | Screen printing glass defect detection method and device based on image processing |
| CN116205903A (en) * | 2023-03-28 | 2023-06-02 | 上汽大众汽车有限公司 | Method for detecting defects of vehicle body finish paint |
Non-Patent Citations (3)
| Title |
|---|
| 王昌书等: "一种基于机器视觉的曲面玻璃划痕缺陷检测方法", 自动化技术与应用, no. 01 * |
| 郑文斌等: "汽车玻璃黑边区域划痕的视觉检测技术", 福建工程学院学报, no. 01 * |
| 郝磊等: "基于线激光和CCD组合测量的动车车轴表面划痕检测分析", 电子测量技术, no. 13 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596929B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| CN116758061B (en) | Casting surface defect detection method based on computer vision | |
| CN116721106B (en) | Profile flaw visual detection method based on image processing | |
| CN114494210B (en) | Plastic film production defect detection method and system based on image processing | |
| CN109242853B (en) | PCB defect intelligent detection method based on image processing | |
| CN115984271B (en) | Metal burr identification method based on corner detection | |
| US9224052B2 (en) | Method for in-image periodic noise pixel inpainting | |
| CN115330767B (en) | Method for identifying production abnormity of corrosion foil | |
| CN116012357A (en) | Automobile circular trailer hole air line defect detection method based on machine vision | |
| CN116311079B (en) | Civil security engineering monitoring method based on computer vision | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN117173661B (en) | Asphalt road quality detection method based on computer vision | |
| CN111738256B (en) | Composite CT image segmentation method based on improved watershed algorithm | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN116777907A (en) | Sheet metal part quality detection method | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN116110053A (en) | Container surface information detection method based on image recognition | |
| CN117252882A (en) | Cylinder head quality detection method and system | |
| CN112461845A (en) | Solar cell panel rainbow texture detection method based on double-light integration | |
| CN116596929B (en) | Automobile rearview mirror production quality monitoring system | |
| CN116883446A (en) | Real-time monitoring system for grinding degree of vehicle-mounted camera lens | |
| CN116993719A (en) | OCA optical film surface defect visual detection method and system | |
| CN115311288B (en) | Method for detecting damage of automobile film | |
| CN113052833A (en) | Non-vision field imaging method based on infrared thermal radiation | |
| CN114078107A (en) | Method, storage medium, device and system for identifying strip-shaped trim of vehicle |
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 |