CN106503720A - A kind of element image-recognizing method for removing suction nozzle interference - Google Patents
A kind of element image-recognizing method for removing suction nozzle interference Download PDFInfo
- Publication number
- CN106503720A CN106503720A CN201610913757.9A CN201610913757A CN106503720A CN 106503720 A CN106503720 A CN 106503720A CN 201610913757 A CN201610913757 A CN 201610913757A CN 106503720 A CN106503720 A CN 106503720A
- Authority
- CN
- China
- Prior art keywords
- point
- suction nozzle
- minor face
- image
- candidate
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of image-recognizing method for removing suction nozzle interference, belongs to image identification technical field.The present invention removes the marginal point that the image-recognizing method of suction nozzle interference extracts part drawing picture by way of rim detection, coarse positioning is carried out to edge point using minimum enclosed rectangle, determine the long side of candidate and candidate's minor face, by calculate the number of point closer to the distance from candidate long while and candidate's minor face in determine preferably long while and best minor face, the straight-line intersection of the preferably long side of fitting and best minor face is the first summit, again by derived function, peakedness ratio compared with obtaining the second summit and the 3rd summit, you can obtain the profile of element script.The interference of suction nozzle when this image-recognizing method can effectively remove industrial camera capturing element image, it is ensured that the accuracy of Placement element, reliability.
Description
Technical field
A kind of the present invention relates to image identification technical field, more particularly to element image recognition side for removing suction nozzle interference
Method.
Background technology
Chip mounter is for realizing the equipment at a high speed, being accurately fully automatically placed with components and parts, is in whole SMT productions
Most critical, most complicated equipment, used as the capital equipment in the production line of SMT, chip mounter is from the low-speed machinery paster of early stage
Machine develops into high speed optical centering chip mounter, and to multi-functional, flexible connection modular development.The mounting head of chip mounter is designed with
Suction nozzle unit and industrial camera, suction nozzle unit are picked and placeed to element using the principle of vacuum suction, and industrial camera is then used for
Location recognition judgement is carried out to the element that suction nozzle unit is adsorbed, this is because suction nozzle unit is not ensured that in absorptive element
Element and the position angle relation of suction nozzle unit, that is to say, that element may deviate from certain distance or deflect certain angle
Degree, this is accomplished by industrial camera and the position of element is accurately identified, then by the Z axis rotary components of mounting head to element
Angular deflection carries out rotation compensation or carries out straight line compensation to position skew, therefore position, angle knowledge of the industrial camera to element
Other ability is for overall attachment operation, most important.In addition, suction nozzle unit is in absorptive element, through industrial camera
The element image outline of shooting is possible to the profile that can include suction nozzle unit, as shown in Figure 1, Figure 2 and Figure 3, suction nozzle unit in Fig. 1
Profile expose on the long side of part drawing picture, in Fig. 2, the profile of suction nozzle element exposes in the minor face of part drawing picture, suction nozzle in Fig. 3
The profile of element exposes in the apex of part drawing picture, and suction nozzle element exposes from which position of part drawing picture and can all cause
The obstacle of element profile identification, and then affect the precision of component mounter.Be accomplished by for this one kind effectively can remove suction nozzle interference,
And the method for identifying the profile of element itself exactly from part drawing picture.
Content of the invention
The technical problem to be solved, is to provide a kind of element image-recognizing method, can effectively remove suction
Mouth is disturbed and identifies element profile from part drawing picture exactly.
The present invention solves the technical scheme that adopted of above-mentioned technical problem：
The invention provides a kind of element image-recognizing method for removing suction nozzle interference, including step：Side is adopted to part drawing picture
The mode of edge detection extracts marginal point, and carries out coarse positioning using minimum enclosed rectangle to the marginal point；According to outside minimum
The each edge lengths for connecing rectangle determine two long sides of candidate and two candidate's minor faces；Each back gauge is calculated less than the point of m pixels
Number, meet the most candidate of point number for requiring long while for preferably long while, the most candidate's minor face of number is best minor face, 2
≤ m≤5, m ∈ N*；Preferably long for above-mentioned distance side and best minor face are fitted less than the point of m pixels, the two of digital simulation are straight
The intersection point of line, obtains the first summit of element profile；All marginal points are counted to the distance on preferably long side, by calculating y1=f
(x1) first derivative at each point, x1It is distance, y1For number, number peak value y is determined1max, by two maximum number peaks
Value y1maxCorresponding apart from x1maxIt is compared with component size setting value, immediate apart from x1maxAs element profile
The length of first length of side, obtains the second summit of element profile；All marginal points are counted to the distance of best minor face, by calculating
y2=f(x2) first derivative at each point, x2It is distance, y2For number, number peak value y is determined2max, by maximum two
Number peak value y2maxCorresponding apart from x2maxIt is compared with component size setting value, immediate apart from x2maxAs element wheel
The length of wide second length of side perpendicular to first length of side, obtains the 3rd summit of element profile；Determined according to three summits
Element profile.
As the further improvement of above-mentioned technical proposal, the step of to element image zooming-out marginal point before, be to element
Image carries out binary conversion treatment.
As the further improvement of above-mentioned technical proposal, the step of to element image zooming-out marginal point before, be to element
Image carries out opening operation process.
As the further improvement of above-mentioned technical proposal, use in the fit procedure of preferably long side and best minor face
Least square method.
As the further improvement of above-mentioned technical proposal, number step of each back gauge less than the point of m pixels is being calculated
In, the value of m is 3.
The invention has the beneficial effects as follows：
Element image-recognizing method of the present invention by part drawing as profile point carry out edge collecting, fitting, calculate derivation, peak value
Relatively, three summits of rectangular element, and then the profile of determination element itself finally can be accurately determined, work is effectively eliminated
The interference of suction nozzle unit during industry camera capturing element image, it is ensured that the accuracy of Placement element, reliability.
Description of the drawings
Fig. 1 is the first situation schematic diagram of element image outline comprising suction nozzle unit profile；
Fig. 2 is second situation schematic diagram of the element image outline comprising suction nozzle unit profile；
Fig. 3 is the third situation schematic diagram of element image outline comprising suction nozzle unit profile；
Fig. 4 is the edge contour schematic diagram of part drawing picture shown in Fig. 3；
Fig. 5 is the schematic diagram of the part drawing picture using minimum enclosed rectangle coarse positioning of Fig. 3；
Fig. 6 is the schematic diagram that the part drawing picture of Fig. 3 determines preferably long side and best minor face；
Fig. 7 is the length schematic diagram that the part drawing picture of Fig. 3 determines first length of side；
Fig. 8 is the length schematic diagram that the part drawing picture of Fig. 3 determines second length of side；
Fig. 9 is the schematic diagram that the part drawing picture of Fig. 3 determines element profile.
Specific embodiment
The technique effect of the design, concrete structure and generation of the present invention is carried out clearly below with reference to embodiment and accompanying drawing
Chu, it is fully described by, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this
Bright a part of embodiment, rather than whole embodiments, based on embodiments of the invention, those skilled in the art is not paying
The other embodiment obtained on the premise of creative work, belongs to the scope of protection of the invention.
The present invention removes the element image-recognizing method of suction nozzle interference and comprises the steps：
S1, pre-treatment is carried out to part drawing picture, including image binaryzation and opening operation.
Image binaryzation is exactly that the gray value of the pixel on image is set to 0 or 255, that is, by whole image is in
Reveal obvious black and white effect.The binaryzation of image is conducive to the further process of image, makes image become simple, and data
Amount reduces, and can highlight the profile of target interested.
Opening operation is referred to and first corrode the computing for being expanded again using same structural element to image, and which can eliminate unit
Little object in part image, separating objects at the very thin point smooth the border of larger object, and substantially do not change part drawing picture
Area.
S2, marginal point is extracted to part drawing picture by the way of rim detection, and using minimum enclosed rectangle to described
Marginal point carries out coarse positioning.
As shown in figure 4, part drawing picture is surrounded by five lines of a, b, c, d, e, it will be apparent that, the profile of the image contains suction nozzle
At the profile of unit, that is, outline line d.The marginal point of part drawing picture can be extracted by the way of rim detection,
Use so that subsequent step is calculated.
As shown in Figure 4 and Figure 5, after marginal point being extracted through rim detection, minimum enclosed rectangle is carried out to edge point
Approach, as can be seen that two of minimum enclosed rectangle in a with part drawing picture and b sides are substantially straight at one from schematic diagram
On line, and the two other of minimum enclosed rectangle is tangent in then d substantially with part drawing picture.
S3, two long sides of candidate and two candidate's minor faces are determined according to each edge lengths of minimum enclosed rectangle.
Minimum enclosed rectangle has four edges, according to its each bar while length determine that two candidates are long while and two candidates
Minor face.
S4, calculating to each back gauge are less than the number of the point of m pixels, meet the long side of the most candidate of the point number for requiring and are
Preferably long side, the most candidate's minor face of number be best minor face, 2≤m≤5, m ∈ N*, in the present embodiment, the value of m is preferably 3
Individual.
As shown in fig. 6,11 when determining preferably long from two candidates are long according to the method for S4 in, then short from two candidates
Best minor face 12 is determined in side.
S5, the point by preferably long for above-mentioned distance side and best minor face less than m pixels are fitted, two straight lines of digital simulation
Intersection point, obtain the first summit of element profile.
As shown in fig. 6, preferably long side 11 and best minor face 12 through fitting a straight line after intersection point be the of element profile
One summit 13, in the present embodiment, the fitting of straight line preferably adopts least square method.
S6, the distance of all marginal points of statistics to preferably long side, by calculating y1=f(x1) first derivative at each point,
x1It is distance, y1For number, number peak value y is determined1max, by two maximum number peak value y1maxCorresponding apart from x1maxWith
Component size setting value is compared, immediate apart from x1maxThe length of as first length of side of element profile.
The accurate appearance and size of rectangular element to be obtained, it is necessary to be accurately judged to the position on its at least three summit.Such as
Shown in Fig. 7, count all marginal points to the distance on preferably long side 11, in theory for same distance number peak value y1maxMost
Big value should occur in x1=L1Position, just as can be seen that x from schematic diagram1In x1maxPosition its distance preferably long side 11
Equidistant point is significantly more than x1In x11And x12Position, when by number y1Apart from x1Function carry out first derivation it
Several number peak value y is just capable of determining that afterwards1max, by two maximum number peak value y1maxCorresponding apart from x1maxWith element
Size setting value L1Be compared, distance and L1The length for being first length of side being more nearly.The length of first length of side obtains it
Afterwards, it is possible to determine the second summit 14 of element profile.
S7, the distance of all marginal points of statistics to best minor face, by calculating y2=f(x2) first derivative at each point,
x2It is distance, y2For number, number peak value y is determined2max, by two maximum number peak value y2maxCorresponding apart from x2maxWith
Component size setting value is compared, immediate apart from x2maxAs element profile is perpendicular to the second side of first length of side
Long length.
As shown in figure 8, similar to S6, count all marginal points to the distance of best minor face 12, determine two maximum
Number peak value y2maxCorresponding apart from x2max, then by two x2maxWith component size setting value L2Be compared, distance and L2More
The near length for being second length of side of adjunction.After the length of second length of side is obtained, it is possible to determine the 3rd top of element profile
Point 15.
S8, element profile is determined according to three summits.
As shown in figure 9, after the first summit 13, the second summit 14, the position on the 3rd summit 15 accurately obtain, it becomes possible to will
The profile of element is accurately judged, and then the purpose for realizing removing suction nozzle interference.
It is more than that presently preferred embodiments of the present invention is illustrated, but the present invention is not limited to the embodiment,
Those of ordinary skill in the art can also make a variety of equivalent variations or replacement on the premise of spiritual without prejudice to the present invention, this
The deformation or replacement of a little equivalents is all contained in the application claim limited range.
Claims (5)
1. the element image-recognizing method that a kind of removal suction nozzle is disturbed, it is characterised in that including step：
Marginal point is extracted to part drawing picture by the way of rim detection, and the edge is clicked through using minimum enclosed rectangle
Row coarse positioning；
Each edge lengths according to minimum enclosed rectangle determine two long sides of candidate and two candidate's minor faces；
Number of each back gauge less than the point of m pixels is calculated, it is preferably long to meet the long side of the most candidate of the point number for requiring
Side, the most candidate's minor face of number be best minor face, 2≤m≤5, m ∈ N*；
Preferably long for above-mentioned distance side and best minor face are fitted less than the point of m pixels, the intersection point of two straight lines of digital simulation,
Obtain the first summit of element profile；
All marginal points are counted to the distance on preferably long side, by calculating y1=f(x1) first derivative at each point, x1Be away from
From y1For number, number peak value y is determined1max, by two maximum number peak value y1maxCorresponding apart from x1maxWith element
Size setting value is compared, immediate apart from x1maxThe length of as first length of side of element profile, obtains element profile
The second summit；
All marginal points are counted to the distance of best minor face, by calculating y2=f(x2) first derivative at each point, x2Be away from
From y2For number, number peak value y is determined2max, by two maximum number peak value y2maxCorresponding apart from x2maxWith element
Size setting value is compared, immediate apart from x2maxAs element profile is perpendicular to second length of side of first length of side
Length, obtains the 3rd summit of element profile；
Element profile is determined according to three summits.
2. the element image-recognizing method that removal suction nozzle as claimed in claim 1 is disturbed, it is characterised in that：To part drawing picture
Before the step of extracting marginal point, binary conversion treatment to be carried out to part drawing picture.
3. the element image-recognizing method that removal suction nozzle as claimed in claim 1 is disturbed, it is characterised in that：To part drawing picture
Before the step of extracting marginal point, opening operation process to be carried out to part drawing picture.
4. the element image-recognizing method that removal suction nozzle as claimed in claim 1 is disturbed, it is characterised in that：On preferably long side and
Preferably least square method is used in the fit procedure of minor face.
5. the element image-recognizing method that removal suction nozzle as claimed in claim 1 is disturbed, it is characterised in that：Each side is arrived calculating
In number step of the distance less than the point of m pixels, the value of m is 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610913757.9A CN106503720B (en) | 2016-10-19 | 2016-10-19 | A kind of element image-recognizing method of removal suction nozzle interference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610913757.9A CN106503720B (en) | 2016-10-19 | 2016-10-19 | A kind of element image-recognizing method of removal suction nozzle interference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106503720A true CN106503720A (en) | 2017-03-15 |
| CN106503720B CN106503720B (en) | 2019-09-13 |
Family
ID=58319253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610913757.9A Active CN106503720B (en) | 2016-10-19 | 2016-10-19 | A kind of element image-recognizing method of removal suction nozzle interference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503720B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111568199A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Method and system for identifying water receiving container and storage medium |
| CN111568182A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Intelligent water outlet method, system and storage medium |
| CN111568197A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Intelligent detection method, system and storage medium |
| CN113160161A (en) * | 2021-04-14 | 2021-07-23 | 歌尔股份有限公司 | Method and device for detecting defects at edge of target |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003178299A (en) * | 2001-12-07 | 2003-06-27 | Asahi Koyo Kk | Diagram reducing compiling method and device and diagram deforming device and method |
| US20090257658A1 (en) * | 2008-04-09 | 2009-10-15 | Fuji Xerox Co., Ltd. | Image extracting apparatus, image extracting method and computer readable medium |
| CN101839690A (en) * | 2010-04-13 | 2010-09-22 | 河海大学常州校区 | Visual inspection method for chip electronic component position error based on edge fitting |
| CN104809422A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | QR code recognizing method based on image processing |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN105809705A (en) * | 2016-03-30 | 2016-07-27 | 广东工业大学 | Patch element positioning identification method based on minimum enclosing rectangle |
-
2016
- 2016-10-19 CN CN201610913757.9A patent/CN106503720B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003178299A (en) * | 2001-12-07 | 2003-06-27 | Asahi Koyo Kk | Diagram reducing compiling method and device and diagram deforming device and method |
| US20090257658A1 (en) * | 2008-04-09 | 2009-10-15 | Fuji Xerox Co., Ltd. | Image extracting apparatus, image extracting method and computer readable medium |
| CN101839690A (en) * | 2010-04-13 | 2010-09-22 | 河海大学常州校区 | Visual inspection method for chip electronic component position error based on edge fitting |
| CN104809422A (en) * | 2015-04-27 | 2015-07-29 | 江苏中科贯微自动化科技有限公司 | QR code recognizing method based on image processing |
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| CN105809705A (en) * | 2016-03-30 | 2016-07-27 | 广东工业大学 | Patch element positioning identification method based on minimum enclosing rectangle |
Non-Patent Citations (3)
| Title |
|---|
| SONG WANG 等: "Evaluating Edge Detection through Boundary Detection", 《EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING》 * |
| 余大伟: "视觉系统在贴片头定位于片状元件检测纠偏中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李小伟: "贴片元件几何尺寸精密测量系统的关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111568199A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Method and system for identifying water receiving container and storage medium |
| CN111568182A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Intelligent water outlet method, system and storage medium |
| CN111568197A (en) * | 2020-02-28 | 2020-08-25 | 佛山市云米电器科技有限公司 | Intelligent detection method, system and storage medium |
| CN111568199B (en) * | 2020-02-28 | 2023-11-07 | 佛山市云米电器科技有限公司 | Water receiving container identification method, system and storage medium |
| CN113160161A (en) * | 2021-04-14 | 2021-07-23 | 歌尔股份有限公司 | Method and device for detecting defects at edge of target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106503720B (en) | 2019-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503720A (en) | A kind of element image-recognizing method for removing suction nozzle interference | |
| WO2021138995A1 (en) | Fully automatic detection method for checkerboard corners | |
| KR920004956B1 (en) | Drawing figure recognition apparatus | |
| CN108830838A (en) | A kind of pcb board incompleteness Trigger jitter detection method of sub-pixel | |
| CN106824806B (en) | The detection method of low module plastic gear based on machine vision | |
| CN109767445B (en) | High-precision PCB defect intelligent detection method | |
| CN105290621B (en) | A kind of the high-speed, high precision lug cutting method and equipment of view-based access control model guiding | |
| CN110910359B (en) | FPC circuit detection method based on feature tracking and skeleton feature matching | |
| CN113382555B (en) | Chip mounter suction nozzle coaxiality error automatic calibration method based on machine vision | |
| CN114494045B (en) | Large spur gear geometric parameter measurement system and method based on machine vision | |
| CN113724193B (en) | PCBA part size and clearance high-precision visual measurement method | |
| WO2017128602A1 (en) | Educational toy kit, and method of detecting and positioning alignment hole thereof | |
| CN104331695B (en) | A kind of circle marker symbol shape quality detection method of robust | |
| CN105865329A (en) | Vision-based acquisition system for end surface center coordinates of bundles of round steel and acquisition method thereof | |
| CN109829910B (en) | PCB defect detection method based on neighborhood search | |
| CN109724988B (en) | PCB defect positioning method based on multi-template matching | |
| CN107480678A (en) | A kind of chessboard recognition methods and identifying system | |
| CN115187562A (en) | Gluing defect detection method and device | |
| CN107507130A (en) | A kind of quickly QFN chip pins image obtains and amplification method | |
| CN114187253A (en) | Circuit board part installation detection method | |
| CN113705564A (en) | Pointer type instrument identification reading method | |
| CN112734779A (en) | Dot calibration plate edge sub-pixel detection method | |
| CN108898584B (en) | Image analysis-based full-automatic veneered capacitor welding polarity discrimination method | |
| CN108180825A (en) | A kind of identification of cuboid object dimensional and localization method based on line-structured light | |
| CN113222990A (en) | Chip counting method based on image data enhancement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200911 Address after: 518000 Fourth Floor, First Floor and Third Floor of Block G, 52 Huangpu Road, Shangliao Community, Xinqiao Street, Baoan District, Shenzhen City, Guangdong Province Patentee after: SHENZHEN FAROAD INTELLIGENT EQUIPMENT Co.,Ltd. Address before: 518000,, Guangdong, Baoan District province Shenzhen manhole street, community 52, Whampoa Road, two floor Patentee before: SHENZHEN LUYUAN AUTOMATION EQUIPMENT Co.,Ltd. |
|
| TR01 | Transfer of patent right |