CN105957065A - Method and system for detecting omitted elements - Google Patents
Method and system for detecting omitted elements Download PDFInfo
- Publication number
- CN105957065A CN105957065A CN201610257944.6A CN201610257944A CN105957065A CN 105957065 A CN105957065 A CN 105957065A CN 201610257944 A CN201610257944 A CN 201610257944A CN 105957065 A CN105957065 A CN 105957065A
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- hsv
- value
- body color
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
- G01N2021/8893—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques providing a video image and a processed signal for helping visual decision
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N2021/95638—Inspecting patterns on the surface of objects for PCB's
-
- 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]
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Spectrometry And Color Measurement (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method and system for detecting omitted elements. The method comprises steps of: acquiring a PCB image of an area where a to-be-tested element is located and a to-be-tested image of the area; acquiring the HSV image of the PCB image and the HSV image of the to-be-tested image; according to the tonal value and the saturation value of the dominant color of the to-be-tested element and a preset tolerance value, counting the number of first pixels, matching the dominant color, in the HSV image of the PCB image and the number of second pixels, matching the dominant color, in the HSV image of the to-be-tested image, and determining whether the detection of the to-be-tested element is omitted according to a ratio of the number of the first pixels to the number of the second pixels and a first preset value. According to the scheme, the images are transformed to a HSV color space, the number of the color-matching pixels is computed according to the tonal value and the saturation value in the HSV image and the tolerance value, a lightness value is eliminated, an influence of a light change on the color-matching pixels is reduced, and the accuracy of the method is increased.
Description
Technical field
The present invention relates to automatic optics inspection field, particularly relate to element missing inspection method and system.
Background technology
Currently, detecting PCB (printed circuit board), using more is AOI (Automatic Optic
Inspection, automatic optics inspection) system, automatic optics inspection is the necessary links of industry manufacturing process, utilizes optics side
Formula obtains the apparent condition of finished product, detects foreign body or surface blemish with image processing.The Wrong, missing of electronic component, reverse-examination are surveyed and are
The common application of one in circuit board defect detection field, machine obtains image by photographic head automatic scanning circuit plate, extracts
The topography of each electronic component, and pass through image processing techniques, it is judged that whether electronic component exists Wrong, missing, anti-defect,
After the element of those suspected defects shown or be marked, conveniently check and overhaul.
In traditional AOI system, the missing part detection of electronic component is mainly by contrasting the pixel color of correspondence position
The difference of value realizes, but this method based on color contrast, it is easier to be affected by illumination variation, thus produces
Raw erroneous judgement.
Summary of the invention
Based on this, it is necessary to the problem being susceptible to erroneous judgement for existing element missing inspection detection method, it is provided that Yi Zhongyuan
Part missing inspection method and system.
A kind of element missing inspection method, comprises the following steps:
Obtain plate-making picture and the testing image of element under test region of element under test region;
Obtain the HSV image of plate-making picture, obtain the HSV image of testing image;
The tone value of the body color according to element under test and intensity value and default tolerance, statistics plate-making picture
The number of the first pixel matched with body color in HSV image, wherein, body color is in each color of element under test
A kind of color that accounting is maximum;
Tone value according to body color and intensity value and default tolerance, in the HSV image of statistics testing image
Number with the second pixel that body color matches;
Obtain the number of the first pixel and the ratio of the number of the second pixel, ratio and the first preset value are compared
Relatively, if ratio is less than the first preset value, then judge element under test missing part in testing image.
A kind of element missing inspection system, including with lower unit:
First acquiring unit, for obtaining the plate-making picture of element under test region and treating of element under test region
Altimetric image;
Second acquisition unit, for obtaining the HSV image of plate-making picture, obtains the HSV image of testing image;
First statistic unit, for the tone value according to the body color of element under test and intensity value and default tolerance
Value, the number of the first pixel matched with body color in the HSV image of statistics plate-making picture, wherein, body color is
A kind of color that in each color of element under test, accounting is maximum;
Second statistic unit, is used for the tone value according to body color and intensity value and default tolerance, and statistics is treated
The number of the second pixel matched with body color in the HSV image of altimetric image;
Comparing unit, for obtaining the ratio of the number of the number of the first pixel and the second pixel, by ratio and the
One preset value compares, if ratio is less than the first preset value, then judges element under test missing part in testing image.
According to the scheme of the invention described above, it is to obtain the plate-making picture of element under test region and unit to be measured the most respectively
The testing image of part region, then obtain the HSV image of plate-making picture and the HSV image of testing image respectively, according to be measured
The tone value of the body color of element and intensity value and default tolerance, first in the HSV image of statistics plate-making picture
The number of the second pixel in the number of pixel and the HSV image of testing image, and according to the number of the first pixel
Element under test whether missing part in testing image is determined with the ratio of number of the second pixel and the size of the first preset value.
Image is transformed into hsv color space by this scheme, utilizes the tone value in HSV image and intensity value and tolerance to count
Calculate the pixel number that matches with body color, given up brightness value, decrease illumination variation to the pixel of the color that matches
Impact, improves the accuracy of element missing inspection method.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of element missing inspection method in one of them embodiment;
Fig. 2 is the graph of relation of colored pixels number-tolerance of matching in one of them embodiment;
Fig. 3 is the structural representation of element missing inspection system in one of them embodiment;
Fig. 4 is the structural representation of element missing inspection system in one of them embodiment;
Fig. 5 is the structural representation of element missing inspection system in one of them embodiment;
Fig. 6 is the structural representation of element missing inspection system in one of them embodiment.
Detailed description of the invention
For making the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, to this
Invention is described in further detail.Should be appreciated that detailed description of the invention described herein only in order to explain the present invention,
Do not limit protection scope of the present invention.
Shown in Figure 1, for the embodiment of the element missing inspection method of the present invention.Element missing inspection method bag in this embodiment
Include following steps:
Step S101: obtain plate-making picture and the testing image of element under test region of element under test region;
Element under test can be the electronic devices and components on pcb board, such as resistance, inductance, electric capacity etc.;Plate-making picture can be
The part pcb board image of the element under test region of corresponding non-missing part in pcb board image;Testing image can be corresponding to be measured
The part pcb board image of element region, carries out actual photographed to pcb board and obtains, but whether do not determine element under test
Missing part;
Step S102: obtain the HSV image of plate-making picture, obtains the HSV image of testing image;
The HSV image of plate-making picture be plate-making picture at H (tone), S (saturation), the image of V (lightness) three passages,
Each pixel in the HSV image of plate-making picture is corresponding with each pixel of plate-making picture;The HSV image of testing image
It is that testing image is at H (tone), S (saturation), the image of V (lightness) three passages, each picture in the HSV image of testing image
Vegetarian refreshments is corresponding with each pixel of testing image;
Step S103: according to the tone value of the body color of element under test and intensity value and default tolerance, statistics
The number of the first pixel matched with body color in the HSV image of plate-making picture, wherein, body color is element under test
Each color in the maximum a kind of color of accounting;
Step S104: according to the tone value of body color and intensity value and default tolerance, statistics testing image
The number of the second pixel matched with body color in HSV image;
Step S105: obtain the number of the first pixel and the ratio of the number of the second pixel, by pre-to ratio and first
If value compares, if ratio is less than the first preset value, then judge element under test missing part in testing image.
In the present embodiment, it is plate-making picture and the element under test location obtaining element under test region the most respectively
The testing image in territory, then obtain the HSV image of plate-making picture and the HSV image of testing image respectively, according to the master of element under test
The tone value of body color and intensity value and default tolerance, the first pixel in the HSV image of statistics plate-making picture
The number of the second pixel in the HSV image of number and testing image, and according to the number of the first pixel and the second picture
The ratio of the number of vegetarian refreshments and the size of the first preset value determine element under test whether missing part in testing image.In this scheme
Image is transformed into hsv color space, utilizes the tone value in HSV image and intensity value and tolerance to calculate and main body
The pixel number that color matches, has given up brightness value, decreases the illumination variation impact on the pixel of the color that matches, and improves
The accuracy of element missing inspection method.
It addition, after ratio and the first preset value being compared relatively, if ratio is more than or equal to the first preset value, then judge to treat
Survey element non-missing part in testing image.
Should be appreciated that the term used in it " first ", " second " etc. in this article be only used for distinguish object, but these
Object should not be limited by these terms.Such as, without departing from the scope of the invention, the first pixel can be referred to as
Two pixels, are referred to as the first pixel by the second pixel.
Wherein in an embodiment, further comprising the steps of after obtaining the plate-making picture of element under test:
According to the color pixel values of body color, under different tolerances, with body color phase in statistics plate-making picture
The number of the 3rd pixel joined, obtains the relation curve of the 3rd pixel number-tolerance, by the 3rd pixel in relation curve
Number change put the most slowly correspondence tolerance as default tolerance.
In the present embodiment, default tolerance is that the relation curve according to the 3rd pixel number-tolerance determines.Face
The tolerance of color is extremely important to missing part detection, if tolerance arranges too small, and can be because of the first picture obtained when missing part detects
Vegetarian refreshments is very few and is susceptible to erroneous judgement, if tolerance arranges excessive, and can be because of the first pixel mistake obtained when missing part detects
Many and be susceptible to erroneous judgement, it is therefore desirable to arranging suitable tolerance, the relation typically choosing the 3rd pixel number-tolerance is bent
Tolerance corresponding during slope minimum in line, the colored pixels number i.e. matched with body color change is corresponding time the slowest
Tolerance.Additionally, color pixel values herein is primarily directed to the rgb pixel value of each pixel in image.
Wherein in an embodiment, the first picture matched with body color in the HSV image of statistics plate-making picture
After the step of the number of vegetarian refreshments further comprising the steps of:
If the image size that the first pixel is covered and the ratio of element under test image size in the HSV image of plate-making picture
Default tolerance more than the second preset value, is then reduced and presets step-length, and be back in the HSV image of statistics plate-making picture by value
The step of the number of the first pixel.
In the present embodiment, if the image size that covered of the first pixel and unit to be measured in the HSV image of plate-making picture
The ratio of part image size, more than the second preset value, represents default tolerance excessive, the image-region that the first pixel is covered
The most excessive, the accuracy of element missing inspection can be affected, the most now need suitably to reduce default tolerance, and again add up the first picture
The number of vegetarian refreshments and the number of the second pixel, the second preset value and default step-length freely can adjust according to practical situation.
Wherein in an embodiment, the first pixel matched with body color in the HSV image of statistics plate-making picture
Comprise the following steps before the step of the number of point:
The saturation pixel region less than preset critical is rejected in the HSV image of plate-making picture;
Wrap before the step of the number of the first pixel matched with body color in the HSV image of statistics testing image
Include following steps:
The saturation pixel region less than preset critical is rejected in the HSV image of testing image.
In the present embodiment, the saturation pixel region less than preset critical is eliminated, this is because saturation is relatively low
Color the most unstable, be unfavorable for that missing inspection judges, therefore by less than preset critical pixel region reject, preset
Marginal value freely can adjust according to practical situation.
Wherein in an embodiment, hold according to tone value and the intensity value of the body color of element under test and presetting
Difference, the step of the number of the first pixel matched with body color in the HSV image of statistics plate-making picture includes following
Step:
Pass throughAdd up the number of the first pixel;
In formula, Hx,yRepresent (x, y) tone value at coordinate, the S of the HSV image of plate-making picturex,yRepresent plate-making picture
HSV image (x, y) intensity value at coordinate, C represents default tolerance, HtargetAnd StargetRepresent body color respectively
Tone value and intensity value;
According to tone value and intensity value and default tolerance, with body color in the HSV image of statistics testing image
The step of the second pixel matched comprises the following steps:
Pass throughAdd up the number of the second pixel;
In formula, Hi,jRepresent (i, j) tone value at coordinate, the S of the HSV image of testing imagei,jRepresent testing image
(i, j) intensity value at coordinate of HSV image.
In the present embodiment, according to the formula determined by the tone value of body color and intensity value and default tolerance
Add up the second pixel in the HSV image of the first pixel in the HSV image of plate-making picture and testing image, according to public
Formula can be selected the pixel of the qualified color that matches in HSV image very easily and add up corresponding number,
Tone value i.e. HSV image is at the numerical value of H passage, and intensity value i.e. HSV image is at the numerical value of channel S.
In a specific embodiment, element missing inspection method can be divided into two parts, and one is lithography process, another
Individual is missing inspection process, and lithography process is primarily directed to plate-making picture, and missing inspection process is primarily directed to testing image;
At lithography process, obtain the plate-making picture of element under test;
Calculate in plate-making picture under different tolerances the pixel of the color that the body color with element under test matches
Number, obtains the relation curve of the colored pixels number-tolerance that matches, and by matching in relation curve, colored pixels number changes
Put slowly correspondence tolerance as default tolerance, as in figure 2 it is shown, abscissa is tolerance, vertical coordinate is the color that matches
Number of pixels, range of tolerable variance can be 0 to 50, and tolerance is that the growth of 20 phase matching color number of pixels is minimum, therefore may be used
With selection tolerance for 20, it addition, when obtaining curve, range of tolerable variance can be adjusted as required;
Then obtain the HSV image of plate-making picture, plate-making picture is transformed into hsv color space from RGB color, its
Conversion formula is as follows:
V=Cmax
Owing to the pixel value of element is easily subject to the impact of illumination, the difference of V (lightness) passage below different illumination conditions
The biggest, therefore, in order to reduce the impact of illumination, give up to fall the information of V passage, only take H (tone) passage, S (saturation) leads to
The image information in road carries out the contrast of colouring information.Simultaneously as the relatively low color of saturation is the most unstable, then will
In image, the saturation pixel region less than 30 is rejected, and is not involved in the comparison of colouring information;
Then according to the tone value of the body color of element under test and intensity value and default tolerance, statistics plate-making figure
The number of the first pixel matched with body color in the HSV image of picture;
The formula used when adding up the number of the first pixel is:
In formula, Hx,y(x, y) tone value at coordinate, S in the H passage of the HSV image of expression plate-making picturex,yRepresent plate-making
In the channel S of the HSV image of image, (x, y) intensity value at coordinate, C represents default tolerance (20), HtargetAnd Starget
Represent tone value and the intensity value of body color respectively;
After the number of statistics the first pixel, if the image area size that covered of the first pixel and plate-making figure
In the HSV image of picture, the ratio of element under test image size is more than the second preset value, then represent default tolerance (20) excessive, need
Default tolerance reduced preset difference value, if preset difference value is 1, and to be back to add up the step of the number of the first pixel,
Again the number of the first pixel is added up.
The step of lithography process only need to be carried out once during single element carries out missing inspection, to variety classes,
Just need to re-start the step of lithography process when different types of element carries out missing part.
In missing inspection process, obtain the testing image of element under test region, obtain the HSV image of testing image;
According at lithography process it has been determined that the tone value of body color and the intensity value of element under test and preset
Tolerance, the number of the second pixel matched with body color in the HSV image of statistics testing image;
The detailed process of the above-mentioned steps of missing inspection process is similar to the processing procedure of plate-making picture with lithography process,
This repeats no more;
After the number having added up the first pixel and the second pixel, obtain number and second pixel of the first pixel
The ratio of the number of point, compares ratio and the first preset value, if ratio is more than or equal to the first preset value, then judges to be measured
Element is non-missing part in testing image;If ratio is less than the first preset value, then judge element under test missing part in testing image;
First preset value can be 50%, it is also possible to according to missing part detection Stringency suitably adjust this first preset
Value.
The invention provides a kind of element missing inspection method, image is transformed into hsv color space, utilizes in HSV image
Tone value and intensity value and tolerance calculate the pixel number of the color that matches, and carry out missing part judgement on this basis,
Give up brightness value when calculating the pixel number of the color that matches, decrease the illumination variation shadow to the pixel of the color that matches
Ring, improve the accuracy of element missing inspection method.
According to said elements missing inspection method, the present invention also provides for a kind of element missing inspection system, below with regard to the element of the present invention
The embodiment of missing inspection system is described in detail.
Shown in Figure 3, for the embodiment of the element missing inspection system of the present invention.Element missing inspection system bag in this embodiment
Include with lower unit:
First acquiring unit 201, for obtaining plate-making picture and the element under test region of element under test region
Testing image;
Second acquisition unit 202, for obtaining the HSV image of described plate-making picture, obtains the HSV figure of described testing image
Picture;
First statistic unit 203, is used for tone value and the intensity value of the body color according to element under test and presets
Tolerance, the number of the first pixel matched with body color in the HSV image of statistics plate-making picture, wherein, main body face
Color be element under test each color in the maximum a kind of color of accounting;
Second statistic unit 204, is used for the tone value according to body color and intensity value and default tolerance, statistics
The number of the second pixel matched with body color in the HSV image of testing image;
Comparing unit 205, for obtaining the ratio of the number of the number of the first pixel and the second pixel, by ratio with
First preset value compares, if ratio is less than the first preset value, then judges element under test missing part in testing image.
Wherein in an embodiment, as shown in Figure 4, element missing inspection system also includes tolerance acquiring unit 206, tolerance
Value acquiring unit 206, for the color pixel values according to described body color, under different tolerances, adds up described plate-making picture
In the number of the 3rd pixel that matches with described body color, obtain the relation curve of the 3rd pixel number-tolerance, will
The number change of the 3rd pixel described in described relation curve puts the tolerance of correspondence the most slowly as described default tolerance
Value.
Wherein in an embodiment, as it is shown in figure 5, element missing inspection system also includes tolerance adjustment unit 207, tolerance
Value adjustment unit 207 is for the image area size covered at described first pixel and the HSV image of described plate-making picture
When the ratio of middle element under test image size exceedes default second ratio, described default tolerance is reduced and presets step-length;
First statistic unit 203 be additionally operable to the tone value according to described body color and intensity value and adjust after pre-
If tolerance adds up the number of described first pixel;
Second statistic unit 204 be additionally operable to the tone value according to described body color and intensity value and adjust after pre-
If tolerance adds up the number of described second pixel.
Wherein in an embodiment, as shown in Figure 6, element missing inspection system also includes pretreatment unit 208, pretreatment list
Saturation, for before adding up the number of described first pixel, is rejected little in the HSV image of described plate-making picture by unit 208
Pixel region in preset critical;
Pretreatment unit 208 is additionally operable to before adding up the number of described second pixel, at the HSV of described testing image
Image is rejected the saturation pixel region less than described preset critical.
Wherein in an embodiment, the first statistic unit 203 passes through
Add up the number of the first pixel;
In formula, Hx,yRepresent (x, y) tone value at coordinate, the S of the HSV image of plate-making picturex,yRepresent plate-making picture
HSV image (x, y) intensity value at coordinate, C represents default tolerance, HtargetAnd StargetRepresent body color respectively
Tone value and intensity value;
Second statistic unit 204 passes throughAdd up the second pixel
Number;
In formula, Hi,jRepresent (i, j) tone value at coordinate, the S of the HSV image of testing imagei,jRepresent testing image
(i, j) intensity value at coordinate of HSV image.
The element missing inspection system of the present invention and the element missing inspection method one_to_one corresponding of the present invention, in said elements missing inspection method
Embodiment illustrate technical characteristic and beneficial effect all be applicable to the embodiment of element missing inspection system.
Each technical characteristic of embodiment described above can combine arbitrarily, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic executed in example is all described, but, as long as the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope that this specification is recorded.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes more concrete and detailed, but also
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that, come for those of ordinary skill in the art
Saying, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement, these broadly fall into the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. an element missing inspection method, it is characterised in that comprise the following steps:
Obtain plate-making picture and the testing image of described element under test region of element under test region;
Obtain the HSV image of described plate-making picture, obtain the HSV image of described testing image;
The tone value of the body color according to described element under test and intensity value and default tolerance, add up described plate-making figure
The number of the first pixel matched with described body color in the HSV image of picture, wherein, described body color be described in treat
Survey a kind of color that in each color of element, accounting is maximum;
Tone value according to described body color and intensity value and default tolerance, add up the HSV figure of described testing image
The number of the second pixel matched with described body color in Xiang;
Obtain the number of described first pixel and the ratio of the number of described second pixel, described ratio and first are preset
Value compares, if described ratio is less than described first preset value, then judges described element under test missing part in described testing image.
Element missing inspection method the most according to claim 1, it is characterised in that the plate-making picture of described acquisition element under test it
The most further comprising the steps of:
According to the color pixel values of described body color, under different tolerances, add up in described plate-making picture with described main body
The number of the 3rd pixel that color matches, obtains the relation curve of the 3rd pixel number-tolerance, by described relation curve
Described in the 3rd pixel number change put the most slowly correspondence tolerance as described default tolerance.
Element missing inspection method the most according to claim 1, it is characterised in that at the HSV image adding up described plate-making picture
In further comprising the steps of after the step of the number of the first pixel that matches with described body color:
If the image size that described first pixel is covered and element under test image size in the HSV image of described plate-making picture
Ratio more than the second preset value, then described default tolerance is reduced and presets step-length, and be back to add up described plate-making picture
HSV image in the step of number of the first pixel.
Element missing inspection method the most according to claim 1, it is characterised in that:
The step of the number of the first pixel matched with described body color in the HSV image of the described plate-making picture of described statistics
Rapid the most further comprising the steps of:
The saturation pixel region less than preset critical is rejected in the HSV image of described plate-making picture;
The step of the number of the second pixel matched with described body color in the HSV image of the described testing image of described statistics
Rapid the most further comprising the steps of:
The saturation pixel region less than described preset critical is rejected in the HSV image of described testing image.
Element missing inspection method the most as claimed in any of claims 1 to 4, it is characterised in that:
The tone value of the described body color according to described element under test and intensity value and default tolerance, add up described system
The step of the number of the first pixel matched with described body color in the HSV image of domain picture comprises the following steps:
Pass throughAdd up the number of described first pixel;
In formula, Hx,yRepresent (x, y) tone value at coordinate, the S of the HSV image of described plate-making picturex,yRepresent described plate-making figure
The HSV image of picture (x, y) intensity value at coordinate, C represents default tolerance, HtargetAnd StargetRepresent described master respectively
The tone value of body color and intensity value;
The described tone value according to described body color and intensity value and default tolerance, add up described testing image
The step of the number of the second pixel matched with described body color in HSV image comprises the following steps:
Pass throughAdd up the number of described second pixel;
In formula, Hi,jRepresent (i, j) tone value at coordinate, the S of the HSV image of described testing imagei,jMapping is treated described in expression
(i, j) intensity value at coordinate of the HSV image of picture.
6. an element missing inspection system, it is characterised in that include with lower unit:
First acquiring unit, for obtaining the plate-making picture of element under test region and treating of described element under test region
Altimetric image;
Second acquisition unit, for obtaining the HSV image of described plate-making picture, obtains the HSV image of described testing image;
First statistic unit, for the tone value according to the body color of described element under test and intensity value and default tolerance
Value, adds up the number of the first pixel matched in the HSV image of described plate-making picture, wherein, institute with described body color
State a kind of color that in each color that body color is described element under test, accounting is maximum;
Second statistic unit, is used for the tone value according to described body color and intensity value and default tolerance, adds up institute
State the number of the second pixel matched in the HSV image of testing image with described body color;
Comparing unit, is used for obtaining the ratio of the number of the number of described first pixel and described second pixel, by described
Ratio and the first preset value compare, if described ratio is less than described first preset value, then judge that described element under test is described
Missing part in testing image.
Element missing inspection system the most according to claim 6, it is characterised in that also include tolerance acquiring unit, described appearance
Difference acquiring unit, for the color pixel values according to described body color, under different tolerances, adds up described plate-making picture
In the number of the 3rd pixel that matches with described body color, obtain the relation curve of the 3rd pixel number-tolerance, will
The number change of the 3rd pixel described in described relation curve puts the tolerance of correspondence the most slowly as described default tolerance
Value.
Element missing inspection system the most according to claim 6, it is characterised in that also include tolerance adjustment unit, described appearance
Difference adjustment unit is in the HSV image of the image area size covered at described first pixel and described plate-making picture
When the ratio of element under test image size exceedes default second ratio, described default tolerance is reduced and presets step-length;
Described first statistic unit be additionally operable to the tone value according to described body color and intensity value and adjust after preset
Tolerance adds up the number of described first pixel;
Described second statistic unit be additionally operable to the tone value according to described body color and intensity value and adjust after preset
Tolerance adds up the number of described second pixel.
Element missing inspection system the most according to claim 6, it is characterised in that also include pretreatment unit;
Described pretreatment unit is for before adding up the number of described first pixel, at the HSV image of described plate-making picture
Middle rejecting saturation is less than the pixel region of preset critical;
Described pretreatment unit is additionally operable to before adding up the number of described second pixel, schemes at the HSV of described testing image
The saturation pixel region less than described preset critical is rejected in Xiang.
10. according to the element missing inspection system described in any one in claim 6 to 9, it is characterised in that:
Described first statistic unit passes throughAdd up described first pixel
Number;
In formula, Hx,yRepresent (x, y) tone value at coordinate, the S of the HSV image of described plate-making picturex,yRepresent described plate-making figure
The HSV image of picture (x, y) intensity value at coordinate, C represents default tolerance, HtargetAnd StargetRepresent described master respectively
The tone value of body color and intensity value;
Described second statistic unit passes throughAdd up described second pixel
Number;
In formula, Hi,jRepresent (i, j) tone value at coordinate, the S of the HSV image of described testing imagei,jMapping is treated described in expression
(i, j) intensity value at coordinate of the HSV image of picture.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610257944.6A CN105957065A (en) | 2016-04-21 | 2016-04-21 | Method and system for detecting omitted elements |
PCT/CN2016/112886 WO2017181722A1 (en) | 2016-04-21 | 2016-12-29 | Inspection method and system for missing component |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610257944.6A CN105957065A (en) | 2016-04-21 | 2016-04-21 | Method and system for detecting omitted elements |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105957065A true CN105957065A (en) | 2016-09-21 |
Family
ID=56915512
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610257944.6A Pending CN105957065A (en) | 2016-04-21 | 2016-04-21 | Method and system for detecting omitted elements |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105957065A (en) |
WO (1) | WO2017181722A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017181722A1 (en) * | 2016-04-21 | 2017-10-26 | 广州视源电子科技股份有限公司 | Inspection method and system for missing component |
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 |
WO2018068414A1 (en) * | 2016-10-14 | 2018-04-19 | 广州视源电子科技股份有限公司 | Detection method and device for resistor having color bands, and automated optical inspection system |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110310341B (en) * | 2019-07-02 | 2021-09-24 | 广州视源电子科技股份有限公司 | Method, device, equipment and storage medium for generating default parameters in color algorithm |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080285840A1 (en) * | 2005-12-26 | 2008-11-20 | Nikon Corporation | Defect inspection apparatus performing defect inspection by image analysis |
CN103024434A (en) * | 2012-12-20 | 2013-04-03 | 广州视源电子科技股份有限公司 | Automatic test system based on image matching |
CN103808731A (en) * | 2014-01-20 | 2014-05-21 | 北京大恒图像视觉有限公司 | Defect detection method applied to presswork detection system |
CN104504375A (en) * | 2014-12-18 | 2015-04-08 | 广州视源电子科技股份有限公司 | Method and device for identifying elements of PCB (Printed Circuit Board) |
CN105184778A (en) * | 2015-08-25 | 2015-12-23 | 广州视源电子科技股份有限公司 | Detection method and apparatus |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200949241A (en) * | 2008-05-28 | 2009-12-01 | Asustek Comp Inc | Apparatus and method for detecting circuit board |
JP5234639B2 (en) * | 2009-01-31 | 2013-07-10 | 株式会社メガトレード | Through-hole inspection equipment |
CN104504703A (en) * | 2014-12-20 | 2015-04-08 | 河南机电高等专科学校 | Welding spot color image segmentation method based on chip element SMT (surface mounting technology) |
CN104899871B (en) * | 2015-05-15 | 2017-08-29 | 广东工业大学 | A kind of IC elements solder joint missing solder detection method |
CN105957065A (en) * | 2016-04-21 | 2016-09-21 | 广州视源电子科技股份有限公司 | Method and system for detecting omitted elements |
-
2016
- 2016-04-21 CN CN201610257944.6A patent/CN105957065A/en active Pending
- 2016-12-29 WO PCT/CN2016/112886 patent/WO2017181722A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080285840A1 (en) * | 2005-12-26 | 2008-11-20 | Nikon Corporation | Defect inspection apparatus performing defect inspection by image analysis |
CN103024434A (en) * | 2012-12-20 | 2013-04-03 | 广州视源电子科技股份有限公司 | Automatic test system based on image matching |
CN103808731A (en) * | 2014-01-20 | 2014-05-21 | 北京大恒图像视觉有限公司 | Defect detection method applied to presswork detection system |
CN104504375A (en) * | 2014-12-18 | 2015-04-08 | 广州视源电子科技股份有限公司 | Method and device for identifying elements of PCB (Printed Circuit Board) |
CN105184778A (en) * | 2015-08-25 | 2015-12-23 | 广州视源电子科技股份有限公司 | Detection method and apparatus |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017181722A1 (en) * | 2016-04-21 | 2017-10-26 | 广州视源电子科技股份有限公司 | Inspection method and system for missing component |
WO2018068414A1 (en) * | 2016-10-14 | 2018-04-19 | 广州视源电子科技股份有限公司 | Detection method and device for resistor having color bands, and automated optical inspection 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 |
Also Published As
Publication number | Publication date |
---|---|
WO2017181722A1 (en) | 2017-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7447353B2 (en) | Methods for qualitative evaluation of a material with at least one identification characteristic | |
CN105976354B (en) | Element localization method and system based on color and gradient | |
CN105957065A (en) | Method and system for detecting omitted elements | |
CN112394064B (en) | Point-line measuring method for screen defect detection | |
CN103440671B (en) | A kind of seal detection method and system | |
CN106355739B (en) | A kind of method and device that detection bank note is new and old | |
CN105303573B (en) | The pin detection method and system of acupuncture needle class component | |
CN117197141B (en) | Method for detecting surface defects of automobile parts | |
CN105791783B (en) | Camera imaging color adjustment method and system | |
EP4357758A2 (en) | Automatic measurement of printed sheets | |
CN102750713B (en) | Image color shift detection method | |
CN109348216A (en) | A kind of combination treatment method of bad point detection peace field calibration | |
WO2012067041A1 (en) | Method for inspecting foreign material on substrate and apparatus for inspecting foreign material on substratrate | |
CN106226033A (en) | The method and device of detection transparent substrates transmitance | |
CN103200349B (en) | Scanned image color cast automatic detection method | |
CN107633508A (en) | One kind metering product printed substrate outward appearance verification method and system | |
Park et al. | Automated defect inspection systems by pattern recognition | |
CN106529572B (en) | Detection method, device and the automatic optical detecting system of chromatic circle resistance | |
CN105389818B (en) | The localization method and system of element | |
CN115147410B (en) | Multicolor block packaging film covering defect detection method | |
CN115452844B (en) | Injection molding part detection method and system based on machine vision | |
CN116519640A (en) | Method for measuring surface glossiness of silica gel key based on machine vision system | |
CN114092437B (en) | Transformer leakage oil detection method | |
US10241000B2 (en) | Method for checking the position of characteristic points in light distributions | |
CN106931946A (en) | A kind of full-automatic mobile terminal visible detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160921 |
|
RJ01 | Rejection of invention patent application after publication |