CN111652091B - Method for detecting lamination compliance of cooling fins - Google Patents

Method for detecting lamination compliance of cooling fins Download PDF

Info

Publication number
CN111652091B
CN111652091B CN202010423895.5A CN202010423895A CN111652091B CN 111652091 B CN111652091 B CN 111652091B CN 202010423895 A CN202010423895 A CN 202010423895A CN 111652091 B CN111652091 B CN 111652091B
Authority
CN
China
Prior art keywords
cooling fin
fin group
feature
image
positioning
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010423895.5A
Other languages
Chinese (zh)
Other versions
CN111652091A (en
Inventor
杨振
任宁
蒋贵勤
曹惠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Heng Yi Intelligent Technology Co ltd
Original Assignee
Shanghai Heng Yi Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Heng Yi Intelligent Technology Co ltd filed Critical Shanghai Heng Yi Intelligent Technology Co ltd
Priority to CN202010423895.5A priority Critical patent/CN111652091B/en
Publication of CN111652091A publication Critical patent/CN111652091A/en
Application granted granted Critical
Publication of CN111652091B publication Critical patent/CN111652091B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/20Scenes; Scene-specific elements in augmented reality scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/25Determination of region of interest [ROI] or a volume of interest [VOI]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/56Extraction of image or video features relating to colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

The method for detecting the lamination compliance of the cooling fins, provided by the invention, comprises the following steps: s1, setting a view finding direction of an image acquisition device, acquiring a side image of a stacked cooling fin group, performing binarization pretreatment, selecting a characteristic region on the side of the cooling fin group, intercepting the characteristic region as a template image, and inputting the template image into image recognition software; s2, positioning datum lines above and below the cooling fin group, and positioning an axis datum of the cooling fin group through matching of the axis positioning templates; s3, determining the deviation of the first feature in the image through matching of the first feature module according to the reference line positioned in the S2; performing preset offset according to the reference line positioned in the S2, selecting a number of detection areas, and counting the number of connected domains meeting the conditions according to a first operation rule; s4, sorting the connected domains identified in the S3, determining a feature layer according to the number of layers of the cooling fin group where the first feature is preset, establishing a first feature matching area through preset offset so as to match with the first feature template, and obtaining a key bit matching result.

Description

Method for detecting lamination compliance of cooling fins
Technical Field
The invention relates to the field of visual image processing, in particular to a method for detecting the lamination compliance of cooling fins with a specific lamination structure.
Background
The traditional Chiller (refrigeration system) relates to a press fitting process of cooling fins in the assembly production process, for example, the Chiller is assembled according to the preset number of the cooling fins and the shapes of the cooling fins in a certain sequence.
However, such cooling fins usually have very small individual shape differences, so that errors are easily generated when the cooling fins are manually discharged in the machining process, and the defective rate is increased.
However, the existing visual image recognition technology is not common in the field of stacked cooling fin detection, and because the cooling fins are arranged closely in the stacking process and the characteristic points are fine, the accuracy rate of detecting the stacking compliance of the cooling fins by directly adopting the prior art is not high, and therefore the accuracy rate of detecting by waiting for a scheme in the field is improved.
Disclosure of Invention
The invention mainly aims to provide a method for detecting the lamination compliance of cooling fins, so as to improve the accuracy of the visual image processing technology on the lamination compliance detection of the cooling fins.
In order to achieve the above object, the present invention provides a method for detecting the lamination compliance of cooling fins, comprising the steps of:
s1, setting a viewing direction of an image acquisition device, acquiring a side image of a cooling fin group after stacking processing, performing binarization pretreatment, selecting a characteristic region on the side of the cooling fin group, intercepting the characteristic region as a template image, and inputting image recognition software, wherein the template image comprises: an axis positioning template, a first characteristic template;
s2, acquiring a side image of the cooling fin group to be detected, performing binarization processing, positioning reference lines above and below the cooling fin group, and positioning an axis reference of the cooling fin group through axis positioning template matching;
s3, detecting a side image of the detected cooling fin group, and determining the left and right deviation of the first feature positioned in the image through matching of the first feature module according to the reference line positioned in the step S2; performing preset offset according to the datum line positioned in the step S2, selecting a number of detection areas, counting the number of connected domains meeting the conditions according to a first operation rule, and identifying the number of cooling fin groups;
wherein the first operation rule comprises: carrying out image binarization processing on the quantity detection area, and carrying out opening operation and closing operation in morphological analysis, wherein the steps comprise: opening the quantity detection areas by using a circular mask with a parameter radius of 1.5 pixels, then closing the obtained result by using a rectangular mask with 5 x 5 pixels, opening the result by using a rectangular mask with 30 x 3 pixels to divide the quantity detection areas to form a plurality of connected areas, and then screening the connected areas according to a preset size;
s4, sorting the connected domains identified in the step S3, determining a feature layer according to the number of layers of the cooling fin group where the first feature is preset, establishing a first feature matching area through preset offset so as to match with the first feature template, and obtaining a key bit matching result.
Optionally, the steps further comprise:
s5, according to the cooling fin group axis datum and upper and lower datum lines, determining a verification region in a side image of the measured cooling fin group through preset deviation, carrying out binarization processing, carrying out opening operation by using a circular mask with a parameter radius of 3.5 pixels, separating a connected region of a processing result into independent regions, screening the connected regions according to a preset size, and counting the number of the connected regions meeting the requirement for comparison and judgment with the preset number.
Optionally, the step of positioning the cooling fin group lower reference line comprises:
s2.1, coarse positioning, namely manually selecting a bottom positioning detection area of the cooling fin set, and carrying out binarization processing on the bottom positioning detection area;
s2.2, performing opening operation on the bottom positioning detection area by using a circular mask with a parameter radius of 1.5 pixels, and removing burrs/bulges;
and S2.3, separating the bottom positioning detection area processed in the step S2.2 into independent communication areas, performing characteristic screening according to a preset size, and then sorting to select the independent communication area close to the upper part of the cooling fin group and set the independent communication area as a reference line below the cooling fin group.
Optionally, the step of positioning the upper datum line of the cooling fin group comprises:
s2.4, coarse positioning, manually selecting a top positioning detection area of the cooling fin group, and carrying out binarization processing on the top positioning detection area;
s2.5, the top positioning detection area is divided into different communication areas, the largest communication area is selected for opening operation, then an external rectangle of the communication area is selected, and the edge of the lowest position of the external rectangle is used as an upper datum line of the cooling fin group.
Preferably, step S4 further comprises: and when the matching of the first characteristic template fails, shifting the preset pixel position again to obtain a second small detection area, and if the white area of the area is judged to be a connected domain larger than the preset pixel value, confirming that the matching is successful.
The method for detecting the lamination compliance of the cooling fins can effectively detect the lamination compliance of the cooling fins and further ensure the accuracy, greatly saves the detection time and labor cost compared with manual detection, integrally improves the detection efficiency, prevents the problem that the lamination is directly scrapped to cause waste because the error press-mounting semi-finished product continuously flows into the next process, effectively saves the cost, has the advantages of high accuracy, good stability, no fatigue after long-time work and the like in visual detection, and can greatly improve the productivity of a production line.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart illustrating the steps of fabricating a mold plate in the method for testing the lamination compliance of cooling fins according to the present invention;
FIG. 2 is a schematic flow chart illustrating the overall steps of the method for detecting the lamination compliance of cooling fins according to the present invention;
FIG. 3 is a schematic view of a template image in the method for detecting the lamination compliance of cooling fins according to the present invention;
FIG. 4 is a schematic view of a datum line positioning process below a cooling plate stack;
FIG. 5 is a schematic view of a cooling fin set axis datum locating process;
FIG. 6 is a schematic view of a datum line locating process over a cooling plate stack;
FIG. 7 is a schematic view of a process for identifying the number of cooling fin groups;
FIG. 8 is a schematic view of a process for identifying the number of cooling fin groups;
FIG. 9 is a schematic view of a process for identifying the number of cooling fin groups;
FIG. 10 is a schematic view of a process for identifying the number of cooling fin groups;
FIG. 11 is a schematic diagram of a first feature template matching identification process;
fig. 12 is a schematic view of the number verification and identification of cooling fin assembly laminations.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "S1," "S2," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
In the present embodiment, the method for detecting the lamination compliance of cooling fins of the present invention is preferably described by taking the cooling fins with round-mouth and/or triangular-mouth feature points on the side as an example, but it should be understood by those skilled in the art that the foregoing feature points do not limit any implementation of the present invention, and those skilled in the art can implement the same implementation with the embodiments of the present invention according to different structures of the feature points on the cooling fins to be actually detected, so that any implementation manner that can be implemented under the same conditions by combining the detection schemes of the present invention to detect the side feature points of the cooling fins is within the disclosure and protection scope of the present invention.
Furthermore, the prior art Halcon algorithm library/software is preferred as the visual image processing technology used in the embodiments of the present invention, but it should be understood by those skilled in the art that the foregoing prior art visual image processing software is not limited to any implementation possibility of the present invention, and those skilled in the art can implement the embodiments of the present invention equally according to any possible or disclosed visual image processing technology/software, and therefore any equivalent implementation manner that can be implemented by using the prior art visual image processing technology and combining the embodiments of the present invention under the equal condition is within the disclosure and protection scope of the present invention.
Referring to fig. 1 to 12, the method for detecting the lamination compliance of cooling fins provided by the present invention includes the steps of:
s1, setting a viewing direction of an image acquisition device, acquiring a side image of a cooling fin group after stacking processing, performing binarization pretreatment, selecting a characteristic region on the side of the cooling fin group, intercepting the characteristic region as a template image, and inputting image recognition software, wherein the template image comprises: an axis positioning template, a first characteristic template;
in the embodiment, as shown in fig. 3, since two triangular opening and round opening features exist on the qualified product of the cooling plate set, the present application is established as a first feature template by selecting the triangular opening feature, and as shown in the figure, one more round opening feature is added to the lower part of the right side of the cooling plate set, so that the present application establishes an axis positioning template by using the 4 round opening features as references.
In this embodiment, the image recognition software is preferably Halcon software, so that after the parameters are initialized, the determined axis positioning template and the first characteristic template are input, and thus the template manufacturing is completed.
S2, acquiring a side image of the cooling fin group to be detected, performing binarization processing, positioning reference lines above and below the cooling fin group, and positioning an axis reference of the cooling fin group through axis positioning template matching; it should be noted that the positioning of the axis datum is mainly used for the positioning reference of the subsequent features, and therefore, as shown in fig. 5, in this embodiment, it is preferable that a row of a plurality of round mouth features with round notches on the last cooling fin at the bottom be used as the identification template, so that the axis datum of the cooling fin group is positioned here, and the offset calculation is convenient to perform subsequently.
Because the product position of the cooling fin group on the production line is relatively fixed, the error is slightly small, the detection region is scribed, binaryzation is carried out on the detection region, blob analysis is carried out, and the reference line below the cooling fin group can be obtained and positioned through gray scale, area and width characteristic detection, so that the step shown in fig. 4 comprises the following steps:
s2.1, coarse positioning, preferably manually selecting a bottom positioning detection area of the cooling fin group, and performing binarization processing on the bottom positioning detection area;
s2.2, performing opening operation on the bottom positioning detection area by using a circular mask with a parameter radius of 1.5 pixels, and removing burrs/bulges;
s2.3 separating the bottom positioning detection area processed in step S2.2 into independent connected areas, and sorting the independent connected areas after feature screening according to a preset size, so as to select the independent connected area close to the upper side of the cooling fin group and set the independent connected area as a reference line below the cooling fin group, wherein in this embodiment, the preset size of the screening is preferably: the width is greater than 300 pixels and the height is in the area between 5 and 30 pixels.
Because the positions of the cooling fin groups on the production line are relatively fixed and the error is slightly small, when the upper reference line of the cooling fin groups is positioned, the detection area can be actively drawn manually, so that blob analysis is performed, the detection area is detected through characteristics of gray scale, area and width, the area is subjected to morphological operation and calculation, fine bulges on the edge are removed, then a circumscribed rectangle is obtained for the processed area, namely the row number of the uppermost, lowermost, leftmost and rightmost rows of the area is obtained, and the row number of the lowermost point of the circumscribed rectangle is the obtained positioning upper reference position, so that the step shown in fig. 6 comprises the following steps:
s2.4, coarse positioning, manually selecting a top positioning detection area of the cooling fin group, and carrying out binarization processing on the top positioning detection area;
s2.5, the top positioning detection area is divided into different communication areas, the largest communication area is selected for opening operation, then an external rectangle of the communication area is selected, and the edge of the lowest position of the external rectangle is used as an upper datum line of the cooling fin group.
And then, carrying out feature detection of a designated region on the side image of the cooling fin group, wherein the step is as follows:
s3, detecting a side image of the detected cooling fin group, and determining a first characteristic, namely left and right deviation of the triangular opening in the image through matching of a first characteristic module according to the datum line positioned in the step S2, so that on one hand, the front and back sides of the cooling fin group can be known, and the method can also be used for detecting whether the arrangement of the cooling fins is wrong; then, performing preset offset according to the datum line positioned in the step S2 to select a number of detection areas, counting the number of connected domains meeting the conditions according to a first operation rule, and identifying the number of cooling fin groups;
it should be noted that, as shown in fig. 7 to fig. 10, the first operation rule includes: carrying out image binarization processing on the quantity detection area, and carrying out opening operation and closing operation in morphological analysis, wherein the steps comprise: opening the quantity detection area by using a circular mask with the parameter radius of 1.5 pixels, and then closing the obtained result by using a rectangular mask with 5 multiplied by 5 pixels, wherein the step is to prevent the selected quantity detection area from being divided into two halves although the quantity detection area is at the same height due to the fact that some products are slightly bright;
then, performing opening operation on the result by using a rectangular mask with 30 multiplied by 3 pixels to cut off links among different areas, dividing a number of detection areas to form a plurality of connected domains, and then screening the connected domains according to a preset size; in the preferred embodiment, the connected component is divided into independent areas, and the connected component is screened by setting the width of the connected component to be more than 50 pixels, the height to be more than 4 pixels and the area characteristic to be more than 400 pixels, so as to count the number of the connected components which finally meet the condition. Therefore, the number of the lamination sheets of the cooling sheet group can be counted, and whether the number of the cooling sheets is correct or not can be identified.
In order to further determine whether the key feature point in the cooling fin group exists, if the cooling fin group is 32 fins in the embodiment, and the key feature point may be located at the 19 th fin from last, the determining step includes:
s4, sorting the connected domains identified in the step S3, presetting the number of layers of the cooling fin group according to the first feature, determining a feature layer, for example, counting 19 sheets in the reciprocal manner, positioning the 19 th layer according to the calculation result of the step S3, establishing a first feature matching area through preset offset, and obtaining a key bit matching result by matching with the first feature template.
As shown in fig. 11, for example, to determine whether there is a triangle feature in a specific position of the 19 th layer, it is first required to arrange the connected domains in S3 to determine the position of the layers, so as to position the layers according to the preset layers, such as 19 layers, and then obtain the detection region of the inverted triangle by shifting, for example, the left shift is 522 pixels according to the axis reference of the cooling plate set, a rectangle of 60 × 100 pixels is drawn, and the matching of the first feature template is performed on the region, if the matching is successful, it is proved that the key feature point of the cooling plate set meets the requirement, if the matching is failed, a second small detection region can be obtained by shifting the preset pixel position again, if the white area of the region is determined, there is a connected domain with an area greater than 80 pixels, it is considered that the inverted triangle exists, the matching is successful, and if there is not, it is determined that the inverted triangle matching fails, thereby determining that the product belongs to a defective product.
In order to further detect whether the cooling fin assembly lamination is correct, it is preferable in this embodiment to detect whether the lamination layer number meets the requirement, as shown in fig. 12, where the steps further include: s5, according to the axis datum and upper and lower datum lines of the cooling fin group, determining a verification region in a side image of the measured cooling fin group through preset offset, carrying out binarization processing, carrying out opening operation by using a circular mask with a parameter radius of 3.5 pixels, separating a connected region of a processing result into independent regions, screening the connected region according to a preset size, and if the width of the screened connected region is 25-35 pixels, the height is 20-60 pixels, and the area is more than 400 pixels, counting the number of the connected regions meeting the requirement, wherein if the number of the layers is the same as the number of the layers of a set value, the lamination sequence is correct, and if the number of the layers is not the same, the lamination is wrong.
In addition, the detection and judgment processes described in the above embodiments may be combined or individually made as a basis for judging whether the product is qualified according to actual requirements, and it can be seen that the above disclosed preferred embodiments of the present invention are only used to help illustrate the present invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand the invention for and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof, and any modification, equivalent replacement, or improvement made within the spirit and principle of the invention should be included in the protection scope of the invention.
The method for detecting the lamination compliance of the cooling fins can effectively detect the lamination compliance of the cooling fins and further ensure the accuracy, greatly saves the detection time and labor cost compared with manual detection, integrally improves the detection efficiency, prevents the problem that the lamination is directly scrapped to cause waste because the error press-mounting semi-finished product continuously flows into the next process, effectively saves the cost, has the advantages of high accuracy, good stability, no fatigue after long-time work and the like in visual detection, and can greatly improve the productivity of a production line.
It will be appreciated by those skilled in the art that, in addition to implementing the system, apparatus and various modules thereof provided by the present invention in the form of pure computer readable program code, the same procedures may be implemented entirely by logically programming method steps such that the system, apparatus and various modules thereof provided by the present invention are implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
In addition, all or part of the steps of the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.

Claims (5)

1. A method for testing the lamination compliance of cooling fins, comprising the steps of:
s1, setting a viewing direction of an image acquisition device, acquiring a side image of a cooling fin group after stacking processing, performing binarization pretreatment, selecting a characteristic region on the side of the cooling fin group, intercepting the characteristic region as a template image, and inputting image recognition software, wherein the template image comprises: an axis positioning template, a first characteristic template;
s2, acquiring a side image of the cooling fin group to be detected, performing binarization processing, positioning reference lines above and below the cooling fin group, and positioning an axis reference of the cooling fin group through axis positioning template matching;
s3, detecting a side image of the detected cooling fin group, and determining the left and right deviation of the first feature positioned in the image through matching of the first feature module according to the reference line positioned in the step S2; performing preset offset according to the datum line positioned in the step S2, selecting a number of detection areas, counting the number of connected domains meeting the conditions according to a first operation rule, and identifying the number of cooling fin groups;
wherein the first operation rule comprises: carrying out image binarization processing on the quantity detection area, and carrying out opening operation and closing operation in morphological analysis, wherein the steps comprise: opening the quantity detection areas by using a circular mask with a parameter radius of 1.5 pixels, then closing the obtained result by using a rectangular mask with 5 x 5 pixels, opening the result by using a rectangular mask with 30 x 3 pixels to divide the quantity detection areas to form a plurality of connected areas, and then screening the connected areas according to a preset size;
s4, sorting the connected domains identified in the step S3, determining a feature layer according to the number of layers of the cooling fin group where the first feature is preset, establishing a first feature matching area through preset offset so as to match with the first feature template, and obtaining a key bit matching result.
2. The method of detecting cooling fin stacking compliance of claim 1, wherein the steps further comprise:
s5, according to the cooling fin group axis datum and upper and lower datum lines, determining a verification region in a side image of the measured cooling fin group through preset deviation, carrying out binarization processing, carrying out opening operation by using a circular mask with a parameter radius of 3.5 pixels, separating a connected region of a processing result into independent regions, screening the connected regions according to a preset size, and counting the number of the connected regions meeting the requirement for comparison and judgment with the preset number.
3. The method of detecting cooling fin stacking compliance of claim 1, wherein the step of locating a datum line below the set of cooling fins comprises:
s2.1, coarse positioning, namely manually selecting a bottom positioning detection area of the cooling fin set, and carrying out binarization processing on the bottom positioning detection area;
s2.2, performing opening operation on the bottom positioning detection area by using a circular mask with a parameter radius of 1.5 pixels, and removing burrs/bulges;
and S2.3, separating the bottom positioning detection area processed in the step S2.2 into independent communication areas, performing characteristic screening according to a preset size, and then sequencing to select the independent communication area close to the upper part of the cooling fin group and set the independent communication area as a reference line below the cooling fin group.
4. The method of detecting cooling fin stack-up compliance of claim 1, wherein the step of locating a datum line above the set of cooling fins includes:
s2.4, coarse positioning, manually selecting a top positioning detection area of the cooling fin group, and carrying out binarization processing on the top positioning detection area;
s2.5, the top positioning detection area is divided into different communication areas, the largest communication area is selected for opening operation, then an external rectangle of the communication area is selected, and the edge of the lowest position of the external rectangle is used as an upper datum line of the cooling fin group.
5. The method for detecting the lamination compliance of cooling fins according to claim 1, wherein step S4 further comprises: and when the matching of the first characteristic template fails, shifting the preset pixel position again to obtain a second small detection area, and if the white area of the area is judged to be a connected domain larger than the preset pixel value, confirming that the matching is successful.
CN202010423895.5A 2020-05-19 2020-05-19 Method for detecting lamination compliance of cooling fins Active CN111652091B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010423895.5A CN111652091B (en) 2020-05-19 2020-05-19 Method for detecting lamination compliance of cooling fins

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010423895.5A CN111652091B (en) 2020-05-19 2020-05-19 Method for detecting lamination compliance of cooling fins

Publications (2)

Publication Number Publication Date
CN111652091A CN111652091A (en) 2020-09-11
CN111652091B true CN111652091B (en) 2023-03-24

Family

ID=72346729

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010423895.5A Active CN111652091B (en) 2020-05-19 2020-05-19 Method for detecting lamination compliance of cooling fins

Country Status (1)

Country Link
CN (1) CN111652091B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009109722A (en) * 2007-10-30 2009-05-21 Canon Inc Image forming apparatus
CN102226907A (en) * 2011-05-24 2011-10-26 武汉嘉业恒科技有限公司 License plate positioning method and apparatus based on multiple characteristics
CN104102100A (en) * 2013-04-01 2014-10-15 株式会社理光 Image forming apparatus and instruction output control method
WO2016127736A1 (en) * 2015-02-13 2016-08-18 比亚迪股份有限公司 Computing method for area of fingerprint overlapping area and electronic apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009109722A (en) * 2007-10-30 2009-05-21 Canon Inc Image forming apparatus
CN102226907A (en) * 2011-05-24 2011-10-26 武汉嘉业恒科技有限公司 License plate positioning method and apparatus based on multiple characteristics
CN104102100A (en) * 2013-04-01 2014-10-15 株式会社理光 Image forming apparatus and instruction output control method
WO2016127736A1 (en) * 2015-02-13 2016-08-18 比亚迪股份有限公司 Computing method for area of fingerprint overlapping area and electronic apparatus

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机器视觉的零件产品检测***设计;顾桂鹏等;《工业控制计算机》;20170125(第01期);全文 *

Also Published As

Publication number Publication date
CN111652091A (en) 2020-09-11

Similar Documents

Publication Publication Date Title
US7197414B2 (en) System and method for identifying a manufacturing tool causing a fault
CN110097542B (en) Method and device for detecting chip bubbles and storage medium
US9020237B2 (en) Method for optimizing observed image classification criterion and image classification apparatus
EP1734456A1 (en) Learning type classification device and learning type classification method
CN109767445B (en) High-precision PCB defect intelligent detection method
CN105184225B (en) A kind of multinational banknote image recognition methods and device
US6336086B1 (en) Method and system for analyzing wafer processing order
CN111048435B (en) Defect monitoring method
CN111461068A (en) Chromosome metaphase map identification and segmentation method
CN110223269A (en) A kind of FPC defect inspection method and device
CN110473174B (en) Method for calculating accurate number of pencils based on image
JP5123244B2 (en) Shape defect inspection device, shape modeling device, and shape defect inspection program
CN110930350A (en) Machine learning method and automatic optical detection equipment applying same
CN111652091B (en) Method for detecting lamination compliance of cooling fins
CN109919154A (en) A kind of character intelligent identification Method and identification device
CN116209957A (en) Defect detection for semiconductor structures on a wafer
CN110135416A (en) A kind of licence plate recognition method and device
CN1936585A (en) Classification system
CN109034166B (en) Confusable character recognition model training method and device
CN113269743A (en) Chip quantity detection method based on iterative translation verification
CN116030274A (en) Green pricklyash fruit sequence detection method based on self-adaptive density clustering
KR102129459B1 (en) Method And Apparatus for Classifying Defective Electronic Component
US11094052B2 (en) Method of counting sheet materials
CN111368928A (en) Wafer pattern matching method and device, electronic equipment and storage medium
US8143076B2 (en) Manufacture of defect cards for semiconductor dies

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