CN106530275B - Element mistake part detection method and system - Google Patents
Element mistake part detection method and system Download PDFInfo
- Publication number
- CN106530275B CN106530275B CN201610887939.3A CN201610887939A CN106530275B CN 106530275 B CN106530275 B CN 106530275B CN 201610887939 A CN201610887939 A CN 201610887939A CN 106530275 B CN106530275 B CN 106530275B
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- feature regional
- regional images
- under test
- 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.)
- Active
Links
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Abstract
The present invention relates to a kind of element mistake part detection method and systems, wherein method positions the feature regional images of the element under test the following steps are included: the original image of acquisition element under test on circuit boards from the original image；Wherein, the feature regional images include the characteristic information of the element under test, and the characteristic information is for distinguishing the element under test with other elements；The pixel value of pixel each in the feature regional images is compared with the pixel value of corresponding pixel points in the characteristic area template image prestored respectively, obtains the pixel similarity of the feature regional images Yu the characteristic area template image；If the pixel similarity is less than preset similarity threshold, the element under test mistake part is determined.Said elements mistake part detection method and system realize the automation of element mistake part detection, can effectively improve detection efficiency and accuracy.
Description
Technical field
The present invention relates to automatic optics inspection technical fields, more particularly to a kind of element mistake part detection method and system.
Background technique
AOI (Automatic Optic Inspection, automatic optics inspection) is to be welded using optical principle to circuit board
The equipment that the common deficiency occurred in producing of delivering a child is detected.For the circuit board of plug-in unit, common defects detection includes
Missing part detection, wrong part detection, the detection of anti-part, more than one piece detection etc..Wherein, wrong part detection refers to the feature for extracting element to be detected,
And be compared with template, to judge whether the element for being inserted into circuit board is correct.
Currently, the wrong part of element detects mainly by manually being detected, still, this detection mode efficiency is lower, moreover,
Testing result is easy error, and detection accuracy is lower.
Summary of the invention
Based on this, it is necessary to which the problem low for prior art detection efficiency, accuracy is low provides a kind of element mistake part inspection
Survey method and system.
A kind of element mistake part detection method, comprising the following steps:
The original image of element under test on circuit boards is obtained, the spy of the element under test is positioned from the original image
Levy area image；Wherein, the feature regional images include the element under test characteristic information, the characteristic information for pair
The element under test is distinguished with other elements；
By the pixel value of pixel each in the feature regional images respectively and in the characteristic area template image that prestores
The pixel value of corresponding pixel points is compared, and obtains the pixel phase of the feature regional images with the characteristic area template image
Like degree；
If the pixel similarity is less than preset similarity threshold, the element under test mistake part is determined.
A kind of element mistake part detection system, comprising:
Locating module positions institute for obtaining the original image of element under test on circuit boards from the original image
State the feature regional images of element under test；Wherein, the feature regional images include the characteristic information of the element under test, described
Characteristic information is for distinguishing the element under test with other elements；
Comparison module, for by the pixel value of pixel each in the feature regional images respectively with the characteristic area that prestores
The pixel value of corresponding pixel points is compared in the template image of domain, obtains the feature regional images and the characteristic area template
The pixel similarity of image；
Judgment module determines that the element under test is wrong if being less than preset similarity threshold for the pixel similarity
Part.
Said elements mistake part detection method and system work as feature regional images by detecting the characteristic area of element under test
When smaller with the pixel similarity of characteristic area template image, element under test mistake part is determined, realize the detection of element mistake part oneself
Dynamicization can effectively improve detection efficiency and accuracy.
Detailed description of the invention
Fig. 1 is the element mistake part detection method flow chart of one embodiment；
Fig. 2 is the character zone image through contours extract；
Fig. 3 is the character zone image after correction；
Fig. 4 is the structural schematic diagram of the element mistake part detection system of one embodiment.
Specific embodiment
Technical solution of the present invention is illustrated with reference to the accompanying drawing.
Fig. 1 is the element mistake part detection method flow chart of one embodiment.As shown in Figure 1, the element mistake part detection side
Method can comprise the following steps that
S1 obtains the original image of element under test on circuit boards, the element under test is positioned from the original image
Feature regional images；Wherein, the feature regional images include the characteristic information of the element under test, and the characteristic information is used
In being distinguished to the element under test with other elements；
Feature of the present invention may include the word in the body region of the color of element under test, shape and element under test
Symbol information etc. is convenient for the information for distinguishing element under test and other elements.It is carried out so that the feature is character information as an example below
Explanation.The character information can be text, symbol, pattern etc..
Before detection, the original image of the element under test can be oriented from the image of whole circuit board first, then
The feature regional images of the element under test are oriented from the original image.When having multiple element under tests on one piece of circuit board
When requiring to carry out the detection of wrong part, the original image of each element under test can be obtained respectively, then respectively from each original image
In orient the feature regional images of each element under test.It can be according to the position of each element under test on circuit boards to each
The corresponding feature regional images of element under test carry out sequential storage, in order to the execution of subsequent detection operation.A reality wherein
It applies in example, can also be each feature regional images serial number, in order to the execution of subsequent detection operation.
S2, by the pixel value of pixel each in the feature regional images respectively with the characteristic area template image that prestores
The pixel value of middle corresponding pixel points is compared, and obtains the pixel of the feature regional images Yu the characteristic area template image
Similarity；
In this step, characteristic area is too small in order to prevent, is unfavorable for subsequent operation, can be with before being compared
Processing is amplified to feature regional images.The enhanced processing refers to the amplification of size, i.e., amplifies the length and width of image respectively
To original n times, n can be arranged according to actual demand, ordinary circumstance n=2.
It, can be right in order to eliminate the influence of stain and the factors such as background color and pattern to testing result on circuit board
The feature regional images carry out noise reduction process.Specifically, gray proces can be carried out to the feature regional images, obtains ash
Image is spent, and binary conversion treatment is carried out to the gray level image according to preset pixel threshold.Shown gray proces can basis
Following formula carries out:
Gray=0.299*R+0.587*G+0.114*B；
In formula, R, G and B are respectively three color components of RGB color, and Gray is the gray value after binaryzation.Institute
A certain gray value can be set as the pixel that gray value is greater than preset gray threshold by stating binaryzation, and pixel value is less than or is waited
Another gray value is set as in the pixel of preset gray threshold.Wherein, the gray threshold, which can be, makes following objective function
The maximum gray value of functional value:
G (t)=ω0*(μ0-μ)2+ω1*(μ1-μ)2；
Wherein, μ=ω0*μ0+ω1*μ1；
In formula, ω0For ratio of the corresponding pixel of the characteristic information in the feature regional images, μ0It is described
The mean value of the pixel value of the corresponding pixel of characteristic information, ω1For background image pixel in the feature regional images
Ratio, μ1For the mean value of the pixel value of the pixel of background image.It in this way, can be by the gray value of gray level image
It is divided into two parts, and grey value difference between two parts is maximum, the gray difference between each part is minimum.
Although the noise reduction process of image can reduce the interference of noise, the interference of noise can not be completely eliminated.
Under normal conditions, noise is comparatively fine in the picture, discrete, and character zone is more continuous.So determining in order to be more accurate
Position character zone can carry out Morphological scale-space to the image of binaryzation, character zone is connected together to form a panel region, and
Contours extract is carried out, contour area the best part is character area.Character zone image such as Fig. 2 institute through contours extract
Show.
Since character area has the rotation of certain angle, image can be corrected.Specifically, to through shape
After the feature regional images of state processing carry out contours extract, can also the contour images be carried out with minimum matrix fitting,
Obtain fitting image；Obtain the coordinate value on three vertex in the fitting image；According to the coordinate value and the original seat prestored
Scale value calculates the transfer matrix rotated to the contour images；According to the transfer matrix to the picture on the contour images
Vegetarian refreshments is coordinately transformed；Contour images through coordinate transform are set as feature regional images.
Wherein, the transfer matrix can be denoted as:
The point on the feature regional images can be coordinately transformed according to the following formula:
In formula, (x, y) is the coordinate value of the pixel on the image through contours extract before coordinate transform, and (x', y') is to sit
The coordinate value of pixel after mark transformation on the image through contours extract.Assuming that the seat in the rectangle upper left corner, the lower left corner and the upper right corner
Mark is respectively (x1,y1)、(x2,y2)、(x3,y3), it is corrected after the coordinate of rectangle be (0,0), (0, h), (w, 0), wherein w
With h indicate correction after rectangle width and height, and in order to guarantee correction after rectangle it is close or identical with original image, should meet:
Six elements that original image transforms to the affine transformation matrix M of the image after correction are set as a result,.Word after correction
It is as shown in Figure 3 to accord with area image.
When comparing, the similarity can be calculated according to the following formula:
In formula, (x, y) indicates that the coordinate value of the pixel in the feature regional images, (x+d, y+d) indicate the spy
Levy the coordinate in region template image with the corresponding pixel of pixel that coordinate value in the feature regional images is (x, y)
Value, I (x, y) indicate pixel value of the coordinate value for the pixel of (x, y), M (x+d, y+d) expression institute in the feature regional images
The pixel value for the pixel that coordinate value in characteristic area template image is (x+d, y+d) is stated, C indicates the similarity.
If storing multiple feature regional images in step S1, this step can respectively by each feature regional images with it is right
The characteristic area template image answered carries out the comparison of pixel value.In one embodiment, each characteristic area template image can be with
It is stored sequentially in local in advance, phase storage order can be set to or phase identical as the storage order of each feature regional images
It answers.Alternatively, can number for each characteristic area template image, number can be set to deposit with each feature regional images
Storage sequence is identical or corresponding.It, can be in order to by way of sequential storage feature regional images and/or characteristic area template image
Concurrently multiple element under tests are compared, to improve element mistake part detection efficiency.
S3 determines the element under test mistake part if the pixel similarity is less than preset similarity threshold.
In this step, if the feature regional images of element under test and the pixel similarity of characteristic area reference picture are less than
Preset similarity threshold then shows that the feature regional images of element under test are differed with the character zone of characteristic area reference picture
It is larger, so as to determine the element under test mistake part；Conversely, if the feature regional images of element under test and characteristic area refer to
The pixel similarity of image is greater than or equal to preset similarity threshold, then shows the feature regional images and feature of element under test
The character zone of area reference image is more similar, so as to determine the not wrong part of the element under test.
The similarity threshold can sets itself according to the actual situation, in general, the value of the similarity threshold is got over
Greatly, detection accuracy is higher.
Element mistake part detection method of the invention realizes the automation of element mistake part detection, can effectively improve detection effect
Rate and accuracy.Especially in the color of element and/or more similar shape feature, by extracting the character on element under test
Information, and be compared with formwork element, it whether similar can determine well.
With said elements mistake part detection method correspondingly, the present invention also provides a kind of element mistake part detection systems.Such as Fig. 2
It is shown, the element mistake part detection system can include:
Locating module 10 is positioned from the original image for obtaining the original image of element under test on circuit boards
The feature regional images of the element under test；Wherein, the feature regional images include the characteristic information of the element under test, institute
Characteristic information is stated for distinguishing to the element under test with other elements；
Feature of the present invention may include the word in the body region of the color of element under test, shape and element under test
Symbol information etc. is convenient for the information for distinguishing element under test and other elements.It is carried out so that the feature is character information as an example below
Explanation.The character information can be text, symbol, pattern etc..
Before detection, the original image of the element under test can be oriented from the image of whole circuit board first, then
The feature regional images of the element under test are oriented from the original image.When having multiple element under tests on one piece of circuit board
When requiring to carry out the detection of wrong part, the original image of each element under test can be obtained respectively, then respectively from each original image
In orient the feature regional images of each element under test.It can be according to the position of each element under test on circuit boards to each
The corresponding feature regional images of element under test carry out sequential storage, in order to the execution of subsequent detection operation.A reality wherein
It applies in example, can also be each feature regional images serial number, in order to the execution of subsequent detection operation.
Comparison module 20, for by the pixel value of pixel each in the feature regional images respectively with the feature that prestores
The pixel value of corresponding pixel points is compared in region template image, obtains the feature regional images and the characteristic area mould
The pixel similarity of plate image；
Characteristic area is too small in order to prevent, is unfavorable for subsequent operation, can also be to feature regional before being compared
As amplifying processing.The enhanced processing refers to the amplification of size, i.e., the length and width of image is amplified to original n times, n respectively
It can be arranged according to actual demand, ordinary circumstance n=2.
It, can be right in order to eliminate the influence of stain and the factors such as background color and pattern to testing result on circuit board
The feature regional images carry out noise reduction process.Specifically, gray proces can be carried out to the feature regional images, obtains ash
Image is spent, and binary conversion treatment is carried out to the gray level image according to preset pixel threshold.Shown gray proces can basis
Following formula carries out:
Gray=0.299*R+0.587*G+0.114*B；
In formula, R, G and B are respectively three color components of RGB color, and Gray is the gray value after binaryzation.Institute
A certain gray value can be set as the pixel that gray value is greater than preset gray threshold by stating binaryzation, and pixel value is less than or is waited
Another gray value is set as in the pixel of preset gray threshold.Wherein, the gray threshold, which can be, makes following objective function
The maximum gray value of functional value:
G (t)=ω0*(μ0-μ)2+ω1*(μ1-μ)2；
Wherein, μ=ω0*μ0+ω1*μ1；
In formula, ω0For ratio of the corresponding pixel of the characteristic information in the feature regional images, μ0It is described
The mean value of the pixel value of the corresponding pixel of characteristic information, ω1For background image pixel in the feature regional images
Ratio, μ1For the mean value of the pixel value of the pixel of background image.It in this way, can be by the gray value of gray level image
It is divided into two parts, and grey value difference between two parts is maximum, the gray difference between each part is minimum.
Although the noise reduction process of image can reduce the interference of noise, the interference of noise can not be completely eliminated.
Under normal conditions, noise is comparatively fine in the picture, discrete, and character zone is more continuous.So determining in order to be more accurate
Position character zone can carry out Morphological scale-space to the image of binaryzation, character zone is connected together to form a panel region, and
Contours extract is carried out, contour area the best part is character area.Character zone image such as Fig. 2 institute through contours extract
Show.
Since character area has the rotation of certain angle, image can be corrected.Specifically, to through shape
After the feature regional images of state processing carry out contours extract, can also the contour images be carried out with minimum matrix fitting,
Obtain fitting image；Obtain the coordinate value on three vertex in the fitting image；According to the coordinate value and the original seat prestored
Scale value calculates the transfer matrix rotated to the contour images；According to the transfer matrix to the picture on the contour images
Vegetarian refreshments is coordinately transformed；Contour images through coordinate transform are set as feature regional images.
Wherein, the transfer matrix can be denoted as:
The point on the feature regional images can be coordinately transformed according to the following formula:
In formula, (x, y) is the coordinate value of the pixel on the image through contours extract before coordinate transform, and (x', y') is to sit
The coordinate value of pixel after mark transformation on the image through contours extract.Assuming that the seat in the rectangle upper left corner, the lower left corner and the upper right corner
Mark is respectively (x1,y1)、(x2,y2)、(x3,y3), it is corrected after the coordinate of rectangle be (0,0), (0, h), (w, 0), wherein w
With h indicate correction after rectangle width and height, and in order to guarantee correction after rectangle it is close or identical with original image, should meet:
Six elements that original image transforms to the affine transformation matrix M of the image after correction are set as a result,.Word after correction
It is as shown in Figure 3 to accord with area image.
When comparing, the similarity can be calculated according to the following formula:
In formula, (x, y) indicates that the coordinate value of the pixel in the feature regional images, (x+d, y+d) indicate the spy
Levy the coordinate in region template image with the corresponding pixel of pixel that coordinate value in the feature regional images is (x, y)
Value, I (x, y) indicate pixel value of the coordinate value for the pixel of (x, y), M (x+d, y+d) expression institute in the feature regional images
The pixel value for the pixel that coordinate value in characteristic area template image is (x+d, y+d) is stated, C indicates the similarity.
If storing multiple feature regional images in locating module 10, comparison module 20 can be respectively by each characteristic area
Image is compared with corresponding characteristic area template image carries out pixel value.In one embodiment, each characteristic area template
Image can be stored sequentially in local in advance, and phase storage order can be set to the storage order phase with each feature regional images
It is same or corresponding.Alternatively, can number for each characteristic area template image, number be can be set to and each feature regional
The storage order of picture is identical or corresponding.It, can by way of sequential storage feature regional images and/or characteristic area template image
In order to be concurrently compared to multiple element under tests, to improve element mistake part detection efficiency.
Judgment module 30 determines the element under test if being less than preset similarity threshold for the pixel similarity
Wrong part.
If the feature regional images of element under test are less than preset similar to the pixel similarity of characteristic area reference picture
Threshold value is spent, then shows that the feature regional images of element under test differ larger with the character zone of characteristic area reference picture, thus
It can be determined that the element under test mistake part；Conversely, if the picture of the feature regional images of element under test and characteristic area reference picture
Plain similarity is greater than or equal to preset similarity threshold, then shows that the feature regional images of element under test and characteristic area refer to
The character zone of image is more similar, so as to determine the not wrong part of the element under test.
The similarity threshold can sets itself according to the actual situation, in general, the value of the similarity threshold is got over
Greatly, detection accuracy is higher.
Element mistake part detection system of the invention realizes the automation of element mistake part detection, can effectively improve detection effect
Rate and accuracy.Especially in the color of element and/or more similar shape feature, by extracting the character on element under test
Information, and be compared with formwork element, it whether similar can determine well.
Element mistake part detection system of the invention and element mistake part detection method of the invention correspond, in said elements
Technology character and its advantages that the embodiment of wrong part detection method illustrates are suitable for the implementation of element mistake part detection system
In example, hereby give notice that.
Each technology character of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technology character in example to be all described, as long as however, the combination of these technology characters is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. a kind of element mistake part detection method, which comprises the following steps:
The original image of element under test on circuit boards is obtained, the characteristic area of the element under test is positioned from the original image
Area image；Wherein, the feature regional images include the characteristic information of the element under test, and the characteristic information is used for described
Element under test is distinguished with other elements；
The pixel value of pixel each in the feature regional images is corresponding with the characteristic area template image prestored respectively
The pixel value of pixel is compared, and it is similar to the pixel of the characteristic area template image to obtain the feature regional images
Degree；
If the pixel similarity is less than preset similarity threshold, the element under test mistake part is determined；
The step of feature regional images of the element under test are positioned from the original image include:
Morphological scale-space is carried out to the feature regional images；
Contours extract is carried out to the feature regional images through Morphological scale-space, obtains contour images；
Contour area the best part in the contour images is set as feature regional images；
The characteristic information is character information.
2. element mistake part detection method according to claim 1, which is characterized in that will in the feature regional images it is each
Before the pixel value of a pixel is compared with the pixel value of corresponding pixel points in the characteristic area template image prestored respectively,
It is further comprising the steps of:
Processing is amplified to the feature regional images.
3. element mistake part detection method according to claim 1, which is characterized in that carry out shape to the feature regional images
State processing the step of include:
Gray proces are carried out to the feature regional images, obtain gray level image；
Binary conversion treatment is carried out to the gray level image according to preset gray threshold；
Morphological scale-space is carried out to the gray level image of binaryzation.
4. element mistake part detection method according to claim 3, which is characterized in that the preset gray threshold be make with
The maximum gray value of functional value of lower objective function:
G (t)=ω0*(μ0-μ)2+ω1*(μ1-μ)2；
Wherein, μ=ω0*μ0+ω1*μ1；
In formula, ω0For ratio of the corresponding pixel of the characteristic information in the feature regional images, μ0For the feature
The mean value of the pixel value of the corresponding pixel of information, ω1For ratio of the pixel in the feature regional images of background image
Example, μ1For the mean value of the pixel value of the pixel of background image.
5. element mistake part detection method according to claim 1, which is characterized in that the characteristic area through Morphological scale-space
It is further comprising the steps of after area image carries out contours extract:
Minimum matrix fitting is carried out to the contour images, obtains fitting image；
Obtain the coordinate value on three vertex in the fitting image；
The transfer matrix rotated to the contour images is calculated with the original coordinates value prestored according to the coordinate value；
The pixel on the contour images is coordinately transformed according to the transfer matrix；
Contour images through coordinate transform are set as feature regional images.
6. element mistake part detection method according to claim 5, which is characterized in that according to the transfer matrix to the wheel
The step of pixel on wide image is coordinately transformed include:
The point on the feature regional images is coordinately transformed according to the following formula:
In formula, M is transfer matrix, and (x, y) is the coordinate value of the pixel before coordinate transform on the image through contours extract, (x',
It y' is) coordinate value of the pixel on the image through contours extract after coordinate transform.
7. element mistake part detection method according to claim 1, which is characterized in that obtain the feature regional images and institute
The step of stating the pixel similarity of characteristic area template image include:
The similarity is calculated according to the following formula:
In formula, (x, y) indicates that the coordinate value of the pixel in the feature regional images, (x+d, y+d) indicate the characteristic area
In the template image of domain with coordinate value in the feature regional images be (x, y) the corresponding pixel of pixel coordinate value, I
(x, y) indicates pixel value of the coordinate value for the pixel of (x, y), M (x+d, y+d) the expression spy in the feature regional images
The pixel value for the pixel that coordinate value in region template image is (x+d, y+d) is levied, C indicates the similarity.
8. a kind of element mistake part detection system characterized by comprising
Locating module, for obtaining the original image of element under test on circuit boards, positioned from the original image it is described to
Survey the feature regional images of element；Wherein, the feature regional images include the characteristic information of the element under test, the feature
Information is for distinguishing the element under test with other elements；
Comparison module, for by the pixel value of pixel each in the feature regional images respectively with the characteristic area mould that prestores
The pixel value of corresponding pixel points is compared in plate image, obtains the feature regional images and the characteristic area template image
Pixel similarity；
Judgment module determines the element under test mistake part if being less than preset similarity threshold for the pixel similarity；
The locating module is by carrying out Morphological scale-space to the feature regional images；To the characteristic area through Morphological scale-space
Image carries out contours extract, obtains contour images；Contour area the best part in the contour images is set as characteristic area
Image；
The characteristic information is character information.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610887939.3A CN106530275B (en) | 2016-10-11 | 2016-10-11 | Element mistake part detection method and system |
| PCT/CN2016/113146 WO2018068415A1 (en) | 2016-10-11 | 2016-12-29 | Detection method and system for wrong part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610887939.3A CN106530275B (en) | 2016-10-11 | 2016-10-11 | Element mistake part detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106530275A CN106530275A (en) | 2017-03-22 |
| CN106530275B true CN106530275B (en) | 2019-06-11 |
Family
ID=58331466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610887939.3A Active CN106530275B (en) | 2016-10-11 | 2016-10-11 | Element mistake part detection method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106530275B (en) |
| WO (1) | WO2018068415A1 (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504231A (en) * | 2016-10-11 | 2017-03-15 | 广州视源电子科技股份有限公司 | Component defects detection method and system |
| CN107330879A (en) * | 2017-06-21 | 2017-11-07 | 广州视源电子科技股份有限公司 | A kind of inspection method of device, device, equipment and storage medium |
| CN109870117A (en) * | 2017-12-05 | 2019-06-11 | 英业达科技有限公司 | Binaryzation outline detection system and its method |
| CN110544640A (en) * | 2018-05-28 | 2019-12-06 | 长鑫存储技术有限公司 | method and apparatus for inspecting semiconductor substrate |
| CN109614879B (en) * | 2018-11-19 | 2022-12-02 | 温州大学 | Hopper particle detection method based on image recognition |
| CN109685781B (en) * | 2018-12-17 | 2022-11-29 | 江苏蜂奥生物科技有限公司 | Multi-target rapid identification method based on certain rules and applied to propolis soft capsules |
| CN112308814A (en) * | 2019-07-26 | 2021-02-02 | 北京四方继保自动化股份有限公司 | Method and system for automatically identifying switch on-off position state of disconnecting link of power system |
| CN111553376B (en) * | 2019-12-24 | 2023-05-23 | 西安元智系统技术有限责任公司 | Cultural relic contour monitoring method |
| CN111209944B (en) * | 2019-12-31 | 2023-09-01 | 上海索广映像有限公司 | Self-adaptive image detection system and image detection method |
| CN111462035B (en) * | 2020-01-21 | 2024-03-08 | 北京明略软件系统有限公司 | Picture detection method and device |
| CN111476782B (en) * | 2020-04-10 | 2023-04-07 | 南通大学 | Automobile rear camera extension line terminal image detection system |
| CN111539933B (en) * | 2020-04-22 | 2023-06-06 | 大连日佳电子有限公司 | Direct-insert element detection method and system |
| CN111738247B (en) * | 2020-05-15 | 2023-07-25 | 上海望友信息科技有限公司 | Polarity identification recognition method, polarity identification recognition device, electronic equipment and storage medium |
| CN112750116B (en) * | 2021-01-15 | 2023-08-11 | 北京市商汤科技开发有限公司 | Defect detection method, device, computer equipment and storage medium |
| CN112801987B (en) * | 2021-02-01 | 2022-11-08 | 上海万物新生环保科技集团有限公司 | Mobile phone part abnormity detection method and equipment |
| CN113034488B (en) * | 2021-04-13 | 2024-04-19 | 荣旗工业科技(苏州)股份有限公司 | Visual inspection method for ink-jet printed matter |
| CN114332069B (en) * | 2022-01-05 | 2024-02-20 | 合肥工业大学 | Connector detection method and device based on machine vision |
| CN114441499B (en) * | 2022-04-11 | 2022-07-12 | 天津美腾科技股份有限公司 | Grade detection method and device, identification equipment, ore pulp grade instrument and storage medium |
| WO2024044913A1 (en) * | 2022-08-29 | 2024-03-07 | Siemens Aktiengesellschaft | Method, apparatus, electronic device, storage medium and computer program product for detecting circuit board assembly defect |
| CN115482234B (en) * | 2022-10-08 | 2023-09-15 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN115564779B (en) * | 2022-12-08 | 2023-05-26 | 东莞先知大数据有限公司 | Part defect detection method, device and storage medium |
| CN115797361B (en) * | 2023-02-13 | 2023-06-27 | 山东淼泰建筑科技有限公司 | Aluminum template surface defect detection method |
| CN116152251B (en) * | 2023-04-20 | 2023-07-14 | 成都数之联科技股份有限公司 | Television backboard detection method, model training method, device, equipment and medium |
| CN116205919B (en) * | 2023-05-05 | 2023-06-30 | 深圳市智宇精密五金塑胶有限公司 | Hardware part production quality detection method and system based on artificial intelligence |
| CN117152145B (en) * | 2023-10-31 | 2024-02-23 | 威海天拓合创电子工程有限公司 | Board card process detection method and device based on image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222328A (en) * | 2011-07-01 | 2011-10-19 | 杭州电子科技大学 | Edge-preserving self-adaptive weighted filtering method for natural scene images |
| CN103810478A (en) * | 2014-02-21 | 2014-05-21 | 广东小天才科技有限公司 | Sitting posture detection method and device |
| CN104363449A (en) * | 2014-10-31 | 2015-02-18 | 华为技术有限公司 | Method and relevant device for predicting pictures |
| CN104931907A (en) * | 2015-05-13 | 2015-09-23 | 中国矿业大学 | Digital display electrical measurement instrument quality group-detection system based on robot visual sense |
| CN105957059A (en) * | 2016-04-20 | 2016-09-21 | 广州视源电子科技股份有限公司 | Electronic component missing detection method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055620B (en) * | 2006-04-12 | 2011-04-06 | 富士通株式会社 | Shape comparison device and method |
| CN102831381B (en) * | 2011-06-15 | 2016-05-04 | 罗普特（厦门）科技集团有限公司 | image difference comparison system and method |
| CN104463178A (en) * | 2014-12-29 | 2015-03-25 | 广州视源电子科技股份有限公司 | Electronic component recognizing method and system |
-
2016
- 2016-10-11 CN CN201610887939.3A patent/CN106530275B/en active Active
- 2016-12-29 WO PCT/CN2016/113146 patent/WO2018068415A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222328A (en) * | 2011-07-01 | 2011-10-19 | 杭州电子科技大学 | Edge-preserving self-adaptive weighted filtering method for natural scene images |
| CN103810478A (en) * | 2014-02-21 | 2014-05-21 | 广东小天才科技有限公司 | Sitting posture detection method and device |
| CN104363449A (en) * | 2014-10-31 | 2015-02-18 | 华为技术有限公司 | Method and relevant device for predicting pictures |
| CN104931907A (en) * | 2015-05-13 | 2015-09-23 | 中国矿业大学 | Digital display electrical measurement instrument quality group-detection system based on robot visual sense |
| CN105957059A (en) * | 2016-04-20 | 2016-09-21 | 广州视源电子科技股份有限公司 | Electronic component missing detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018068415A1 (en) | 2018-04-19 |
| CN106530275A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106530275B (en) | Element mistake part detection method and system | |
| JP7297018B2 (en) | System and method for line detection with a vision system | |
| CN105608671B (en) | A kind of image split-joint method based on SURF algorithm | |
| CN109816673B (en) | Non-maximum value inhibition, dynamic threshold value calculation and image edge detection method | |
| CN103729632B (en) | A kind of localization method of Circular Mark point based on connected region filtering | |
| CN105976354B (en) | Element localization method and system based on color and gradient | |
| CN105352437B (en) | Board method for detecting position and device | |
| CN103279956B (en) | A kind of method detecting chip mounter components and parts positioning precision | |
| WO2018068417A1 (en) | Component defect detection method and system | |
| CN110111330B (en) | Mobile phone screen detection method | |
| CN110473165A (en) | A kind of welding quality of circuit board detection method and device | |
| CN106033544A (en) | Test content area extraction method based on template matching | |
| CN109325381B (en) | QR code positioning and correcting method | |
| JP2023120281A (en) | System and method for detecting line in vision system | |
| CN109752392A (en) | A kind of pcb board defect type detection system and method | |
| CN105354816B (en) | A kind of electronic units fix method and device | |
| CN106709952B (en) | A kind of automatic calibration method of display screen | |
| CN114266764A (en) | Character integrity detection method and device for printed label | |
| CN108709500A (en) | A kind of circuit board component position matching method | |
| CN110288040A (en) | A kind of similar evaluation method of image based on validating topology and equipment | |
| Zhang et al. | A new algorithm for accurate and automatic chessboard corner detection | |
| CN106530485A (en) | Image boundary obtaining method and apparatus | |
| CN1898555B (en) | Substrate inspection device | |
| CN109003257A (en) | A kind of optical character verification method | |
| CN105389818B (en) | The localization method and system of element |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |