CN110018174A - A kind of method and apparatus of detection object appearance - Google Patents
A kind of method and apparatus of detection object appearance Download PDFInfo
- Publication number
- CN110018174A CN110018174A CN201910431015.6A CN201910431015A CN110018174A CN 110018174 A CN110018174 A CN 110018174A CN 201910431015 A CN201910431015 A CN 201910431015A CN 110018174 A CN110018174 A CN 110018174A
- Authority
- CN
- China
- Prior art keywords
- lines
- appearance
- condition
- default
- length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- 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
- G01N21/8851—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of method and apparatus of detection object appearance.The application finds the four edges in the face laptop B by the method for image procossing, and the face laptop B is adjusted to normal place, to reduce influence of the face the laptop B folding angle to testing result.
Description
Technical field
This application involves computer network fields, and in particular to the method and detection object appearance of detection object appearance
Device.
Background technique
(Automatic Optical Inspection, letter are detected using appearance of the intelligent vision system to product
Claim AOI) it is a kind of common detection means.Carrying out detection to the face laptop B appearance using the method for intelligent vision is to protect
Demonstrate,prove the important means of the critical components presentation qualities such as business designaton (Logo), the camera in the face laptop B.
Currently, the scheme detected to the face laptop B is based on conventional product appearance detection scheme.User is first
First pass through the user interface in computer selects several default localization regions as reference in the standard photographs of a real scene shooting.When
When detecting to the product of production line, the actual location region in product image is searched, and according to actual location region and in advance
If the relationship of localization region, position is carried out to product image and is become a full member.Then product image after becoming a full member to position it is each to be detected
It is detected in region.
Since the folding angle in the face laptop B is adjustable.When laptop is examined by the AOI of production line
When survey station, the folding angle in the face B is not fixed.Cause product image actual location region and default localization region there may be
Deviation on certain angle searches for the probability that there is very fiasco in actual location region directly in product image.Therefore, current
On laptop production line, the failure rate of the AOI detection in the face A and the face B is very high.So that the actual AOI inspection of laptop
In survey, the detection function in the face A and the face B is usually disabled.
Summary of the invention
The application provides a kind of method of detection object appearance, a kind of device of detection object appearance；To solve AOI detection
When the high problem of failure rate.
In order to solve the above-mentioned technical problem, the embodiment of the present application provides the following technical solution:
This application provides a kind of methods of detection object appearance, comprising:
Obtain multiple fisrt feature point information of the first profile lines of the first object appearance images；Wherein, described first
Object appearance images include the first component image of multiple components to be detected；
The first transformation model is obtained according to the fisrt feature point information and corresponding preset reference point；
The first object appearance images are adjusted to second adjustment image according to first transformation model；Wherein, institute
Stating first component Image Adjusting is the second component image in the second adjustment image；
Successively obtain the similarity mode result of the second component image with corresponding preset reference image；
Judge whether all similarity mode results meet default acceptance condition；
If so, determining that the first object appearance is qualified.
Optionally, in multiple fisrt feature point information of the first profile lines for obtaining the first object appearance images
Before, further includes:
Multiple first appearance lines of the first object appearance images are obtained according to default lines model；
Determine that the first appearance lines obtain first profile lines according to default profile condition；
Multiple fisrt feature point information of the first profile lines are obtained according to default characteristic point condition.
Optionally, the default characteristic point condition, comprising: determine the condition in two lines crosspoint and/or determine circular arc circle
The condition of heart point.
Optionally, the default lines model, is the algorithm of Hough fitting a straight line.
Optionally, the front view of first object is rectangle；
The default profile condition, comprising: determine the left lines of the first profile lines presets left lines condition, really
The upper lines of the right lines of the fixed first profile lines preset right lines condition, determine the first profile lines are preset
The lower lines of online condition and/or the determining first profile lines preset offline condition；
It is described to preset left lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images Far Left；
It is described to preset right lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images rightmost；
It is described to preset online condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images are topmost；
It is described to preset offline condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value.
Optionally, described to preset offline condition, further includes: the ratio of the first height and the first length is less than or equal to described
The practical length to height ratio of the rectangle of first object；
Wherein, first height is the midpoint of the upper lines to the length at the midpoint of the first appearance lines；Institute
Stating the first length is the midpoint of the left lines to the length at the midpoint of the right lines.
Optionally, described to preset online condition or described preset offline condition, further includes: the first appearance lines
The average color that first area is preset in top meets default the below default first color threshold and the first appearance lines
The average color in two regions meets default second color threshold.
Optionally, the fisrt feature point information, be the left lines, the right lines, the upper lines and it is described under
The crosspoint of lines.
Optionally, first transformation model is perspective transformation matrix.
This application provides a kind of devices of detection object appearance, comprising:
Obtain feature dot element, multiple fisrt feature points of the first profile lines for obtaining the first object appearance images
Information；Wherein, the first object appearance images include the first component image of multiple components to be detected；
Transformation model unit is obtained, for obtaining the according to the fisrt feature point information and corresponding preset reference point
One transformation model；
Adjustment unit, for the first object appearance images to be adjusted to second adjustment according to first transformation model
Image；Wherein, the first component Image Adjusting is the second component image in the second adjustment image
Matching unit, for successively obtaining the similarity of the second component image with corresponding preset reference image
With result；
Judging unit, for judging whether all similarity mode results meet default acceptance condition；
Judging unit determines that the first object appearance is closed if the output result for the judging unit is "Yes"
Lattice.
Disclosure based on the above embodiment can know, the embodiment of the present application have it is following the utility model has the advantages that
This application provides a kind of method and apparatus of detection object appearance, which comprises obtains outside the first object
See multiple fisrt feature point information of the first profile lines of image；Wherein, the first object appearance images include it is multiple to
The first component image of detection part；The first conversion is obtained according to the fisrt feature point information and corresponding preset reference point
Model；The first object appearance images are adjusted to second adjustment image according to first transformation model；Wherein, described
One image of component is adjusted to the second component image in the second adjustment image；Successively obtain the second component image and phase
The similarity mode result of corresponding preset reference image；Judge whether the similarity mode result meets default qualification respectively
Condition；If so, determining that component to be detected associated with the second component image is qualified.
The application finds the four edges in the face laptop B by the method for image procossing, and the face laptop B tune
It is whole to arrive normal place, to reduce influence of the face the laptop B folding angle to testing result.
Detailed description of the invention
Fig. 1 is the flow chart of the method for detection object appearance provided by the embodiments of the present application；
Fig. 2 is the unit block diagram of the device of detection object appearance provided by the embodiments of the present application.
Specific embodiment
In the following, being described in detail in conjunction with specific embodiment of the attached drawing to the application, but not as the restriction of the application.
It should be understood that various modifications can be made to disclosed embodiments.Therefore, description above should not regard
To limit, and only as the example of embodiment.Those skilled in the art will expect in the scope and spirit of the present application
Other modifications.
The attached drawing being included in the description and forms part of the description shows embodiments herein, and with it is upper
What face provided is used to explain the application together to substantially description and the detailed description given below to embodiment of the application
Principle.
By the description of the preferred form with reference to the accompanying drawings to the embodiment for being given as non-limiting example, the application's
These and other characteristic will become apparent.
It is also understood that although the application is described referring to some specific examples, those skilled in the art
Member realizes many other equivalents of the application in which can determine, they have feature as claimed in claim and therefore all
In the protection scope defined by whereby.
When read in conjunction with the accompanying drawings, in view of following detailed description, above and other aspect, the feature and advantage of the application will become
It is more readily apparent.
The specific embodiment of the application is described hereinafter with reference to attached drawing；It will be appreciated, however, that the disclosed embodiments are only
Various ways implementation can be used in the example of the application.Known and/or duplicate function and structure and be not described in detail to avoid
Unnecessary or extra details makes the application smudgy.Therefore, specific structural and functionality disclosed herein is thin
Section is not intended to restrictions, but as just the basis of claim and representative basis be used to instructing those skilled in the art with
Substantially any appropriate detailed construction diversely uses the application.
This specification can be used phrase " in one embodiment ", " in another embodiment ", " in another embodiment
In " or " in other embodiments ", it can be referred to one or more of the identical or different embodiment according to the application.
To first embodiment provided by the present application, i.e., a kind of embodiment of the method for detection object appearance.
The present embodiment is described in detail below with reference to Fig. 1, wherein Fig. 1 is detectable substance provided by the embodiments of the present application
The flow chart for the method seen in vitro.
Step S101 obtains multiple fisrt feature point information of the first profile lines of the first object appearance images；Wherein,
The first object appearance images include the first component image of multiple components to be detected.
First profile lines, refer to edge lines, that is, object periphery lines or figure outline border lines.
The fisrt feature point information refers to the point for capableing of expression thing body appearance profile on first profile lines.For example, two
The crosspoint of straight line.
The purpose of the present embodiment detection object appearance is exactly for the appearance of automatic testing product.For example, detection notebook
Whether the position of the face computer B business designaton (Logo) is correct, and whether the installation of camera misplaces；Wherein, the portion to be detected
Part refers to business designaton (Logo) and camera etc.；But due to relative to the camera for obtaining the first object appearance images, notes
The folding angle in the face this computer B is not fixed, and therefore, brings certain uncertainty to automatic detection.
Step S102 obtains the first transformation model according to the fisrt feature point information and corresponding preset reference point.
Multiple features in preset reference point, that is, the lines of outline of standard appearance images correctly installed of display unit
Point information.Preset reference point is corresponding with fisrt feature point information.Setting standard appearance images and the purpose of preset reference point are just
It is the position in order to which the first object appearance images to be adjusted to standard appearance images as reference, so as to by the first object outside drawing
Image of component to be detected as in is compared with preset reference image.
The position of preset reference point in the picture is associated with the size in the face laptop B.
Optionally, first transformation model is perspective transformation matrix.
For example, the face laptop B is a rectangle, the fisrt feature point information is the crosspoint of 4 rectangles；According to
The position on 4 vertex of the position and preset reference point on 4 vertex, is regarded by computer in the appearance images of the face laptop B
Perspective transform in feel obtains 4 vertex in the face a laptop B appearance images and is transformed into one of preset reference point thoroughly
Depending on transformation matrix.
The first object appearance images are adjusted to second adjustment figure according to first transformation model by step S103
Picture；Wherein, the first component Image Adjusting is the second component image in the second adjustment image.
For example, continuing above-mentioned example, by above-mentioned perspective transformation matrix, the face laptop B appearance images are adjusted to
Standard picture position, wherein business designaton (Logo) image and camera image for including in the appearance images of the face laptop B
Also it is adjusted simultaneously.
Step S104 successively obtains the similarity mode knot of the second component image with corresponding preset reference image
Fruit.
Preset reference image, exactly for determining the whether correct standard picture of second component image.Outside the first object
Seeing in image has several image of component to be detected, just there is several preset reference images corresponding with component to be detected.
For example, continuing above-mentioned example, this second component image is saved in production management system (for example, business designaton
(Logo) image and camera image) position, size, pass through the screenshot of the available detection zone of these information, recycle
Whether screenshot and preset reference image multilevel iudge corresponding component are qualified.
Step S105, judges whether all similarity mode results meet default acceptance condition.
Step S106, if so, determining that the first object appearance is qualified.
When judgement, it can judge whether the similarity mode result meets default acceptance condition respectively.If so, determining
Component to be detected associated with the second component image.
When all component qualifications to be detected in the first object appearance, then the first object appearance is qualified.
Before multiple fisrt feature point information of the first profile lines for obtaining the first object appearance images, also wrap
It includes:
Step S100-1 obtains multiple first appearance lines of the first object appearance images according to default lines model.
First appearance lines refer to all identifiable lines in the first object appearance images.Wherein, including first profile
Lines.
The default lines model, is the algorithm of Hough fitting a straight line.
It can be found by the algorithm of the Hough fitting a straight line in computer vision all in the first object appearance images
First appearance lines.However, it is desirable to find the first profile lines of the first object appearance images from all first appearance lines.
Step S100-2 determines that the first appearance lines obtain first profile lines according to default profile condition.
Step S100-3 believes according to multiple fisrt feature points that default characteristic point condition obtains the first profile lines
Breath.
The profile of one object is mainly made of lines, including straight line and curve.And curve is made of circular arc.Cause
This, determines that the key of contour of object is crosspoint and the circular arc centre point of two lines.Object can be drawn by obtaining these points
Profile.
Therefore, the default characteristic point condition, comprising: determine the condition in two lines crosspoint and/or determine the circular arc center of circle
The condition of point.
For the method for detection object appearance, the first application scenarios are present embodiments provided.First object is faced
Figure is rectangle.
The default profile condition, comprising: determine the left lines of the first profile lines presets left lines condition, really
The upper lines of the right lines of the fixed first profile lines preset right lines condition, determine the first profile lines are preset
The lower lines of online condition and/or the determining first profile lines preset offline condition.
It is described to preset left lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images Far Left.
It is described to preset right lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images rightmost.
It is described to preset online condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images are topmost.
It is described to preset offline condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value.
Optionally, described to preset offline condition, further include the first height and the first length ratio be less than or equal to it is described
The practical length to height ratio of the rectangle of first object.Wherein, first height is the midpoint of the upper lines to first appearance
The length at the midpoint of lines；First length is the midpoint of the left lines to the length at the midpoint of the right lines.
For example, the process for finding the face laptop B bottom edge straight line will receive the interference of straight line on keyboard.Sky on keyboard
Lattice key fits 2 straight lines.Interference vulnerable to the straight line formed on keyboard.When the face laptop B is complete and camera is vertical
When, it is equal to discuss aspect ratio for the ratio of height and width and laptop B foliation in the true picture of the face laptop B；But in reality
In border, the angle of the face laptop B and camera can not be entirely 90 degree；The face the B image formed in camera has
Certain inclination makes the ratio that height is wide in the face the laptop B image before ajusting be less than the ratio of actual height and width；If quasi-
The aspect ratio that the straight line closed is formed is greater than the aspect ratio of B foliation opinion, and the straight line on the bottom edge being fitted to is necessarily on keyboard
Straight line；By this limitation, straight line bring on some keyboards can be excluded and interfered.
Optionally, described to preset online condition or described preset offline condition, further includes: the first appearance lines
The average color that first area is preset in top meets default the below default first color threshold and the first appearance lines
The average color in two regions meets default second color threshold.
For example, the face laptop B is since the shaft with system end is connect, interference of the lower lines vulnerable to other lines,
And be dark areas below the lower lines in the face laptop B, it is bright area above lower lines, by judging lower lines or more face
Color difference exclusive PCR lines identify lower lines.
Optionally, the fisrt feature point information, be the left lines, the right lines, the upper lines and it is described under
The crosspoint of lines.
Optionally, the first slope threshold value is greater than 2.Optionally, second slope threshold value is less than 0.3.
The absolute value of straight slope is bigger, and straight line is more vertical in plane right-angle coordinate.On the contrary, straight slope is absolute
It is worth smaller, straight line is more horizontal in plane right-angle coordinate.Therefore, the purpose of straight line of the searching slope absolute value greater than 2 is exactly
Find vertical line.For example, due to when laptop is stood after testing position be not fixed, the folding angle in the face laptop B
It is not fixed, the straight line that the face laptop B both sides are formed is not fully vertical.
Therefore, a threshold value is set, thinks to may be the face laptop B both sides shape when straight slope is greater than this threshold value
At line.
The present embodiment finds the four edges in the face laptop B by the method for image procossing, and the face laptop B
It is adjusted to normal place, to reduce influence of the face the laptop B folding angle to testing result.
It is corresponding with first embodiment provided by the present application, present invention also provides second embodiment, i.e., a kind of detectable substance
The device seen in vitro.Since second embodiment is substantially similar to first embodiment, so describe fairly simple, relevant part
Refer to the corresponding explanation of first embodiment.Installation practice described below is only schematical.
Fig. 2 shows a kind of embodiments of the device of detection object appearance provided by the present application.Fig. 2 is the embodiment of the present application
The unit block diagram of the device of the detection object appearance of offer.
Shown in Figure 2, the application provides a kind of device of detection object appearance, comprising:
Feature dot element 201 is obtained, it is special for obtaining multiple the first of first profile lines of the first object appearance images
Sign point information；Wherein, the first object appearance images include the first component image of multiple components to be detected；
Transformation model unit 202 is obtained, for obtaining according to the fisrt feature point information and corresponding preset reference point
Take the first transformation model；
Adjustment unit 203, for the first object appearance images to be adjusted to second according to first transformation model
Adjust image；Wherein, the first component Image Adjusting is the second component image in the second adjustment image
Matching unit 204, it is similar with corresponding preset reference image for successively obtaining the second component image
Spend matching result；
Judging unit 205, for judging whether all similarity mode results meet default acceptance condition；
Judging unit 206 determines the first object appearance if the output result for the judging unit is "Yes"
It is qualified.
In said device, further includes: pretreatment unit, it is special for obtaining multiple first according to the first object appearance images
Sign point information；
In the pretreatment unit, comprising:
The first appearance lines subelement is obtained, for obtaining the multiple of the first object appearance images according to default lines model
First appearance lines；
First contour line bar subelement is obtained, for determining that the first appearance lines obtain the according to presetting profile condition
One lines of outline；
Fisrt feature point information sub-elements are obtained, for obtaining the first profile lines according to default characteristic point condition
Multiple fisrt feature point information.
Optionally, the default characteristic point condition, comprising: determine the condition in two lines crosspoint and/or determine circular arc circle
The condition of heart point.
Optionally, the default lines model, is the algorithm of Hough fitting a straight line.
Optionally, the front view of first object is rectangle；
The default profile condition, comprising: determine the left lines of the first profile lines presets left lines condition, really
The upper lines of the right lines of the fixed first profile lines preset right lines condition, determine the first profile lines are preset
The lower lines of online condition and/or the determining first profile lines preset offline condition；
It is described to preset left lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images Far Left；
It is described to preset right lines condition, comprising: the length of the first appearance lines meets default first length threshold, and
The slope absolute value of the first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images rightmost；
It is described to preset online condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value, and the midpoint of the first appearance lines is located at
The first object appearance images are topmost；
It is described to preset offline condition, comprising: the length of the first appearance lines meets default second length threshold, and
The slope absolute value of the first appearance lines meets default second slope threshold value.
Optionally, described to preset offline condition, further includes: the ratio of the first height and the first length is less than first object
The practical length to height ratio of the rectangle of body；
Wherein, first height is the midpoint of the upper lines to the length at the midpoint of the first appearance lines；Institute
Stating the first length is the midpoint of the left lines to the length at the midpoint of the right lines.
Optionally, described to preset online condition or described preset offline condition, further includes: the first appearance lines
The average color that first area is preset in top meets default the below default first color threshold and the first appearance lines
The average color in two regions meets default second color threshold.
Optionally, the fisrt feature point information, be the left lines, the right lines, the upper lines and it is described under
The crosspoint of lines.
Optionally, first transformation model is perspective transformation matrix.
The present embodiment finds the four edges in the face laptop B by the method for image procossing, and the face laptop B
It is adjusted to normal place, to reduce influence of the face the laptop B folding angle to testing result.
Above embodiments are only the exemplary embodiment of the application, are not used in limitation the application, the protection scope of the application
It is defined by the claims.Those skilled in the art can make respectively the application in the essence and protection scope of the application
Kind modification or equivalent replacement, this modification or equivalent replacement also should be regarded as falling within the scope of protection of this application.
Claims (10)
1. a kind of method of detection object appearance characterized by comprising
Obtain multiple fisrt feature point information of the first profile lines of the first object appearance images；Wherein, first object
Appearance images include the first component image of multiple components to be detected；
The first transformation model is obtained according to the fisrt feature point information and corresponding preset reference point；
The first object appearance images are adjusted to second adjustment image according to first transformation model；Wherein, described
One image of component is adjusted to the second component image in the second adjustment image；
Successively obtain the similarity mode result of the second component image with corresponding preset reference image；
Judge whether all similarity mode results meet default acceptance condition；
If so, determining that the first object appearance is qualified.
2. the method according to claim 1, wherein in the first profile for obtaining the first object appearance images
Before multiple fisrt feature point information of lines, further includes:
Multiple first appearance lines of the first object appearance images are obtained according to default lines model；
Determine that the first appearance lines obtain first profile lines according to default profile condition；
Multiple fisrt feature point information of the first profile lines are obtained according to default characteristic point condition.
3. according to the method described in claim 2, it is characterized in that, the default characteristic point condition, comprising: determine that two lines are handed over
The condition of crunode and/or the condition for determining circular arc centre point.
4. according to the method described in claim 2, it is characterized in that, the default lines model, is the calculation of Hough fitting a straight line
Method.
5. according to the method described in claim 2, it is characterized in that, the front view of first object is rectangle；
The default profile condition, comprising: determine the left lines of the first profile lines presets left lines condition, determines institute
It is online to state presetting for the upper lines of the right lines of first profile lines preset right lines condition, determine the first profile lines
Condition and/or determine that the lower lines of the first profile lines preset offline condition；
It is described to preset left lines condition, comprising: the length of the first appearance lines meets default first length threshold, and described
The slope absolute value of first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is positioned at described
First object appearance images Far Left；
It is described to preset right lines condition, comprising: the length of the first appearance lines meets default first length threshold, and described
The slope absolute value of first appearance lines meets default first slope threshold value, and the midpoint of the first appearance lines is positioned at described
First object appearance images rightmost；
It is described to preset online condition, comprising: the length of the first appearance lines meets default second length threshold, and described
The slope absolute value of first appearance lines meets default second slope threshold value, and the midpoint of the first appearance lines is positioned at described
First object appearance images are topmost；
It is described to preset offline condition, comprising: the length of the first appearance lines meets default second length threshold, and described
The slope absolute value of first appearance lines meets default second slope threshold value.
6. according to the method described in claim 5, it is characterized in that, described preset offline condition, further includes: the first height with
The ratio of first length is less than or equal to the practical length to height ratio of the rectangle of first object；
Wherein, first height is the midpoint of the upper lines to the length at the midpoint of the first appearance lines；Described
One length is the midpoint of the left lines to the length at the midpoint of the right lines.
7. according to the method described in claim 5, it is characterized in that, described preset online condition or described preset the offline rule
Part, further includes: preset above the first appearance lines first area average color meet default first color threshold and
The average color that second area is preset below the first appearance lines meets default second color threshold.
8. according to the described in any item methods of claim 5-7, which is characterized in that the fisrt feature point information, is the left side
The crosspoint of lines, the right lines, the upper lines and the lower lines.
9. the method according to claim 1, wherein first transformation model is perspective transformation matrix.
10. a kind of device of detection object appearance characterized by comprising
Feature dot element is obtained, multiple fisrt feature points letter of the first profile lines for obtaining the first object appearance images
Breath；Wherein, the first object appearance images include the first component image of multiple components to be detected；
Transformation model unit is obtained, for obtaining first turn according to the fisrt feature point information and corresponding preset reference point
Mold changing type；
Adjustment unit, for the first object appearance images to be adjusted to second adjustment figure according to first transformation model
Picture；Wherein, the first component Image Adjusting is the second component image in the second adjustment image
Matching unit, for successively obtaining the similarity mode knot of the second component image with corresponding preset reference image
Fruit；
Judging unit, for judging whether all similarity mode results meet default acceptance condition；
Judging unit determines that the first object appearance is qualified if the output result for the judging unit is "Yes".
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431015.6A CN110018174B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting object appearance |
| CN202110950345.3A CN113588667B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting appearance of object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431015.6A CN110018174B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting object appearance |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110950345.3A Division CN113588667B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting appearance of object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110018174A true CN110018174A (en) | 2019-07-16 |
| CN110018174B CN110018174B (en) | 2021-10-22 |
Family
ID=67194316
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431015.6A Active CN110018174B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting object appearance |
| CN202110950345.3A Active CN113588667B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting appearance of object |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110950345.3A Active CN113588667B (en) | 2019-05-22 | 2019-05-22 | Method and device for detecting appearance of object |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110018174B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192250A (en) * | 2019-12-30 | 2020-05-22 | 合肥联宝信息技术有限公司 | Data processing method and device, computer storage medium and computer |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619574A (en) * | 2003-10-07 | 2005-05-25 | 索尼株式会社 | Image matching method, program, and image matching system |
| US20100007719A1 (en) * | 2008-06-07 | 2010-01-14 | Alexander Frey | Method and apparatus for 3D digitization of an object |
| CN102622614A (en) * | 2012-02-24 | 2012-08-01 | 山东鲁能智能技术有限公司 | Knife switch closing reliability judging method based on distance between knife switch arm feature point and fixing end |
| CN103020945A (en) * | 2011-09-21 | 2013-04-03 | 中国科学院电子学研究所 | Remote sensing image registration method of multi-source sensor |
| CN103052971A (en) * | 2010-07-30 | 2013-04-17 | 松下电器产业株式会社 | Detection device and method for transition area in space |
| CN103175843A (en) * | 2011-12-20 | 2013-06-26 | 西安扩力机电科技有限公司 | Product quality inspection instrument based on image processing |
| KR101364046B1 (en) * | 2012-11-05 | 2014-02-19 | 재단법인대구경북과학기술원 | Method and apparatus for object tracking in video sequences |
| CN103605979A (en) * | 2013-12-03 | 2014-02-26 | 苏州大学张家港工业技术研究院 | Object identification method and system based on shape fragments |
| CN103916588A (en) * | 2012-12-28 | 2014-07-09 | 三星电子株式会社 | Image transformation apparatus and method |
| CN104237249A (en) * | 2014-09-11 | 2014-12-24 | 苏州佳祺仕信息科技有限公司 | Tag appearance inspection and detection technological method |
| CN104915957A (en) * | 2015-05-29 | 2015-09-16 | 何再兴 | Matching rectification method for improving three dimensional visual sense identification precision of industrial robot |
| CN106327483A (en) * | 2016-08-12 | 2017-01-11 | 广州视源电子科技股份有限公司 | Method, system and device for attaching logo of detection equipment |
| CN106501271A (en) * | 2016-11-24 | 2017-03-15 | 深圳市博视科技有限公司 | product appearance detection method |
| CN109738450A (en) * | 2019-01-09 | 2019-05-10 | 合肥联宝信息技术有限公司 | The detection method and device of keyboard of notebook computer |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2798349B2 (en) * | 1993-11-08 | 1998-09-17 | 松下電器産業株式会社 | Vehicle position detection device |
| KR100819614B1 (en) * | 2006-06-20 | 2008-04-04 | 호서대학교 산학협력단 | How to create an image for inspection of flat panel for display device |
| ES2415240B1 (en) * | 2011-12-21 | 2014-05-21 | Abengoa Solar New Technologies, S.A. | METHOD FOR AUTOMATED INSPECTION OF PHOTOVOLTAIC SOLAR COLLECTORS INSTALLED IN PLANTS. |
| CN105096299B (en) * | 2014-05-08 | 2019-02-26 | 北京大学 | Polygon detection method and polygon detection device |
| KR101705762B1 (en) * | 2015-09-02 | 2017-02-14 | 주식회사 미르기술 | Method for Correcting tilt of 3D shape measuring device |
| KR101761641B1 (en) * | 2015-10-20 | 2017-08-08 | 주식회사 셀바스에이아이 | Device and method for obtaining edge line by detecting outline |
| CN105654097B (en) * | 2015-12-29 | 2019-04-16 | 上海珍岛信息技术有限公司 | The detection method of quadrangle marker in image |
| CN107561087A (en) * | 2017-08-31 | 2018-01-09 | 广东工业大学 | A kind of mouse logo positioning and defect inspection method based on machine vision |
| CN107607542A (en) * | 2017-08-31 | 2018-01-19 | 苏州诺维博得智能装备科技有限公司 | notebook appearance quality detection method and device |
-
2019
- 2019-05-22 CN CN201910431015.6A patent/CN110018174B/en active Active
- 2019-05-22 CN CN202110950345.3A patent/CN113588667B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619574A (en) * | 2003-10-07 | 2005-05-25 | 索尼株式会社 | Image matching method, program, and image matching system |
| US20100007719A1 (en) * | 2008-06-07 | 2010-01-14 | Alexander Frey | Method and apparatus for 3D digitization of an object |
| CN103052971A (en) * | 2010-07-30 | 2013-04-17 | 松下电器产业株式会社 | Detection device and method for transition area in space |
| CN103020945A (en) * | 2011-09-21 | 2013-04-03 | 中国科学院电子学研究所 | Remote sensing image registration method of multi-source sensor |
| CN103175843A (en) * | 2011-12-20 | 2013-06-26 | 西安扩力机电科技有限公司 | Product quality inspection instrument based on image processing |
| CN102622614A (en) * | 2012-02-24 | 2012-08-01 | 山东鲁能智能技术有限公司 | Knife switch closing reliability judging method based on distance between knife switch arm feature point and fixing end |
| KR101364046B1 (en) * | 2012-11-05 | 2014-02-19 | 재단법인대구경북과학기술원 | Method and apparatus for object tracking in video sequences |
| CN103916588A (en) * | 2012-12-28 | 2014-07-09 | 三星电子株式会社 | Image transformation apparatus and method |
| CN103605979A (en) * | 2013-12-03 | 2014-02-26 | 苏州大学张家港工业技术研究院 | Object identification method and system based on shape fragments |
| CN104237249A (en) * | 2014-09-11 | 2014-12-24 | 苏州佳祺仕信息科技有限公司 | Tag appearance inspection and detection technological method |
| CN104915957A (en) * | 2015-05-29 | 2015-09-16 | 何再兴 | Matching rectification method for improving three dimensional visual sense identification precision of industrial robot |
| CN106327483A (en) * | 2016-08-12 | 2017-01-11 | 广州视源电子科技股份有限公司 | Method, system and device for attaching logo of detection equipment |
| CN106501271A (en) * | 2016-11-24 | 2017-03-15 | 深圳市博视科技有限公司 | product appearance detection method |
| CN109738450A (en) * | 2019-01-09 | 2019-05-10 | 合肥联宝信息技术有限公司 | The detection method and device of keyboard of notebook computer |
Non-Patent Citations (2)
| Title |
|---|
| YINGGE WANG 等: ""Direct Visual Odometry Using Lines for a Monocular Camera"", 《JOURNAL OF PHYSICS: CONFERENCE SERIES》 * |
| 刘坤 等: ""弱纹理环境下基于线条的图像位姿恢复"", 《信息技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192250A (en) * | 2019-12-30 | 2020-05-22 | 合肥联宝信息技术有限公司 | Data processing method and device, computer storage medium and computer |
| CN111192250B (en) * | 2019-12-30 | 2022-02-08 | 合肥联宝信息技术有限公司 | Computer B-side frame detection method and device, computer storage medium and computer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113588667A (en) | 2021-11-02 |
| CN113588667B (en) | 2024-06-14 |
| CN110018174B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10922794B2 (en) | Image correction method and device | |
| US7197166B2 (en) | Iris extraction method capable of precisely determining positions and sizes of irises in a digital face image | |
| US6181806B1 (en) | Apparatus for identifying a person using facial features | |
| US11317081B2 (en) | Gaze correction of multi-view images | |
| US6252976B1 (en) | Computer program product for redeye detection | |
| US7436430B2 (en) | Obstacle detection apparatus and method | |
| US6292574B1 (en) | Computer program product for redeye detection | |
| US8577151B2 (en) | Method, apparatus, and program for detecting object | |
| CN101930543B (en) | Method for adjusting eye image in self-photographed video | |
| EP1394723A2 (en) | Method for detecting red-eye effect in digital images | |
| US20200356800A1 (en) | Polygonal region detection | |
| EP2528035B1 (en) | Apparatus and method for detecting a vertex of an image | |
| CN113378790B (en) | Viewpoint positioning method, apparatus, electronic device, and computer-readable storage medium | |
| CN110059611A (en) | A kind of intelligence vacant seat recognition methods in classroom | |
| Nouri et al. | 3d blind mesh quality assessment index | |
| US7848545B2 (en) | Method of and system for image processing and computer program | |
| KR20220073824A (en) | Image processing method, image processing apparatus, and electronic device applying the same | |
| CN115170567A (en) | Method for detecting defects of waterproof steel plate for ship | |
| CN117623031A (en) | Elevator non-inductive control system and method | |
| CN110018174A (en) | A kind of method and apparatus of detection object appearance | |
| US20150371102A1 (en) | Method for recognizing and locating object | |
| Girard et al. | Simultaneous macula detection and optic disc boundary segmentation in retinal fundus images | |
| CN110658918A (en) | Method, apparatus, and medium for positioning an eye-tracking camera of video glasses | |
| Lay et al. | Rectification of QR-code images using the parametric cylindrical surface model | |
| US20050180612A1 (en) | Method of correcting deviation of detection position for human face, correction system, and correction program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |