CN116542998B - Contour detection method, device, equipment and medium for photoetching film inductance - Google Patents

Contour detection method, device, equipment and medium for photoetching film inductance Download PDF

Info

Publication number
CN116542998B
CN116542998B CN202310255362.4A CN202310255362A CN116542998B CN 116542998 B CN116542998 B CN 116542998B CN 202310255362 A CN202310255362 A CN 202310255362A CN 116542998 B CN116542998 B CN 116542998B
Authority
CN
China
Prior art keywords
contour
template
point
target
image
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
CN202310255362.4A
Other languages
Chinese (zh)
Other versions
CN116542998A (en
Inventor
何良雨
张文刚
刘彤
梅能华
吴志烨
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.)
Fengrui Lingchuang Zhuhai Technology Co ltd
Original Assignee
Fengrui Lingchuang Zhuhai 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 Fengrui Lingchuang Zhuhai Technology Co ltd filed Critical Fengrui Lingchuang Zhuhai Technology Co ltd
Priority to CN202310255362.4A priority Critical patent/CN116542998B/en
Publication of CN116542998A publication Critical patent/CN116542998A/en
Application granted granted Critical
Publication of CN116542998B publication Critical patent/CN116542998B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
    • Y02P70/50—Manufacturing or production processes characterised by the final manufactured product

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a medium for detecting a contour of a photolithographic thin film inductor. According to the method, template point difference information and target point difference information corresponding to template contour points and target contour points extracted from a template image and a target image are determined according to the target point difference image and the template point difference image, the target contour points corresponding to the target point difference information which are the same as the template point difference information are used as candidate contour points according to the positions of the template contour points corresponding to the target point difference image and the vertical direction of a template contour line segment in the target point difference image, all the template contour points are compared with all the candidate contour points, the contour detection result of the target image is determined according to the comparison result, the candidate contour points corresponding to each template contour point can be quickly and accurately searched by adopting a searching mode and combining the point difference information, the specific situation of the contour defect can be accurately detected, and the accuracy and the efficiency of contour detection are improved.

Description

Contour detection method, device, equipment and medium for photoetching film inductance
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a medium for detecting a contour of a photolithographic thin film inductor.
Background
For mass production of photoetching film inductance products, a manual mode is adopted to detect the outline defects of the products, a large amount of human resources are often consumed, the detection accuracy is low due to the influence of subjective factors of detection staff, and currently, the outline detection of the photoetching film inductance products usually adopts a deep learning detection or outline matching detection mode.
However, the deep learning detection method needs to provide a large amount of labeling data for the deep learning model, the training, use and maintenance costs are high, the detection efficiency is low, and the effective landing is difficult, while the contour matching detection method generally adopts the comparison of the features of the whole contour and the standard template features, such as the moment, the histogram or the contour tree of the contour image, but such a method consumes a large amount of computing resources, the contour detection efficiency is low, and the abnormal position in the contour image is difficult to accurately locate, so how to improve the accuracy and the efficiency of the contour detection is a problem to be solved.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method, an apparatus, a device, and a medium for detecting a profile of a photolithographic thin film inductor, so as to solve the problem of low accuracy of profile detection.
In a first aspect, an embodiment of the present invention provides a contour detection method for a lithographic thin film inductor, where the contour detection method includes:
acquiring a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
acquiring a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
extracting the contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in the target image to obtain at least one target contour point, and determining target point difference information of each target contour point in the target point difference image;
Determining the corresponding position of the template contour point in the target point difference image aiming at any template contour point, searching in the target point difference image along the vertical direction of the template contour line segment by taking the position as a starting point to obtain a target contour point corresponding to target point difference information identical to the template point difference information of the template contour point, and taking the target contour point meeting the preset condition as a candidate contour point of the template contour point;
and traversing all the template contour points to obtain candidate contour points corresponding to the template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
In a second aspect, an embodiment of the present invention provides a profile detection apparatus for a lithographic thin film inductor, the profile detection apparatus comprising:
the image acquisition module is used for acquiring a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
The contour extraction module is used for extracting the contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in the target image to obtain at least one target contour point, and determining target point difference information of each target contour point in the target point difference image;
an image searching module, configured to determine, for any one of the template contour points, a position of the template contour point corresponding to the target point difference image, and search in the target point difference image along a vertical direction of the template contour line segment with the position as a starting point, to obtain a target contour point corresponding to target point difference information identical to template point difference information of the template contour point, where the target contour point satisfying a preset condition is used as a candidate contour point of the template contour point;
and the contour comparison module is used for traversing all the template contour points to obtain candidate contour points of the corresponding template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implementing the contour detection method according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the contour detection method according to the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
obtaining a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image, extracting a contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting a contour in the target image to obtain at least one target contour point, determining target point difference information of each target contour point in the target point difference image, determining a position corresponding to the template contour point in the target point difference image aiming at any template contour point, taking the position as a starting point, searching in the target point difference image along the vertical direction of the template contour line segment to obtain a target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point, traversing all the template contour points to obtain candidate contour points corresponding to the template contour point by taking the target contour point meeting the preset condition as the candidate contour point of the template contour point, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, determining the contour detection result of the target image according to the comparison result, acquiring the candidate contour point according to the point difference information in combination with the searching mode, rapidly determining the candidate contour point and the template contour point with the corresponding relation, performing refined comparison by all the template contour points and all the candidate contour points in the template contour line segment, thereby rapidly determining the contour defect type and the defect position, the accuracy and efficiency of contour detection are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of an application environment of a contour detecting method for a photolithographic thin film inductor according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of a contour detection method for a lithographic thin film inductor according to an embodiment of the present invention;
fig. 3 is a flowchart of a contour detecting method for a lithographic thin film inductor according to a first embodiment of the present invention;
FIG. 4 is a schematic diagram of a binary image of a contour detection method for a lithographic thin film inductor according to a first embodiment of the present invention;
FIG. 5 is a schematic diagram of a profile identification image of a profile detection method for a lithographic thin film inductor according to a first embodiment of the present invention;
FIG. 6 is a schematic diagram of a sequence identification image of a contour detection method for a lithographic thin film inductor according to a first embodiment of the present invention;
Fig. 7 is a schematic diagram of a first template outline of a contour detection method for a photolithographic thin film inductor according to a first embodiment of the present invention;
fig. 8 is a schematic diagram of a first outline defect corresponding to a schematic diagram of a first template of a contour detection method for a photolithographic thin film inductor according to a first embodiment of the present invention;
fig. 9 is a schematic diagram of a second template outline of a contour detection method for a photolithographic thin film inductor according to a first embodiment of the present invention;
fig. 10 is a schematic diagram of a second outline defect corresponding to a schematic diagram of a second template of a contour detection method for a photolithographic thin film inductor according to a first embodiment of the present invention;
fig. 11 is a schematic structural diagram of a profile detection apparatus for lithography thin film inductors according to a second embodiment of the present invention;
fig. 12 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the invention. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
It should be understood that the sequence numbers of the steps in the following embodiments do not mean the order of execution, and the execution order of the processes should be determined by the functions and the internal logic, and should not be construed as limiting the implementation process of the embodiments of the present invention.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
The contour detection method for the photoetching film inductor provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, wherein a client side and a server side are communicated. The client includes, but is not limited to, a palm top computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud terminal device, a personal digital assistant (personal digital assistant, PDA), and other computer devices. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 2, a schematic diagram of an implementation scenario of a contour detection method for a lithographic thin film inductor according to an embodiment of the present invention is provided, where an image capturing device communicates with an image processing device. The image acquisition device includes, but is not limited to, a camera, a video recorder, a mobile terminal, etc., the image processing device may perform binarization processing on the acquired image, and send the acquired image and the binarization processing result to the server in fig. 1 for storage, the lithography film inductance may be a product to be detected, the inductance image is a surface pattern of the product to be detected, and the image acquisition environment may be polished by an annular light source and a bottom parallel backlight source, where in this embodiment, the annular light source adopts a 60 ° annular light source. It should be noted that, the image acquisition device may be moved so that the acquisition area covers the entire photolithographic film inductance, and accordingly, the annular light source should also move along with the image acquisition device, the image acquired by the image acquisition device may include more than one inductance pattern, and the image acquisition on the surface of the photolithographic film inductance is realized by using techniques such as image stitching through pose resolving of the image acquisition device.
Referring to fig. 3, a flow chart of a contour detection method for a lithography thin film inductor according to an embodiment of the present invention is provided, where the contour detection method may be applied to a client in fig. 1, and a computer device corresponding to the client is connected to a server to obtain a target image of a product to be detected and a target binary image corresponding to the target image, and a template image of a template corresponding to the product to be detected and a template binary image corresponding to the template image. As shown in fig. 3, the contour detection method may include the steps of:
step S301, a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image are obtained, and point difference calculation is carried out on the target binary image and the template binary image according to a preset direction, so as to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image.
The product to be detected may be a product to be subjected to contour detection, the target image may be a product actual image acquired by the image acquisition device, and the target binary image may be a binary image obtained by performing binarization processing on the target image.
The template image may refer to a product standard image acquired by the image acquisition device of a standard product corresponding to the product to be detected, and the template binary image may refer to a binary image obtained after binarization processing is performed on the template image.
The preset direction may be a calculation direction of a pointing difference, the point difference may refer to a difference between pixel values corresponding to pixel points, the target point difference image may refer to an image obtained by performing point difference calculation on a target binary image according to the preset direction, and the template point difference image may refer to an image obtained by performing point difference calculation on a template binary image according to the preset direction.
Specifically, in one embodiment, the template binary image may be generated by manually designing the product area by an operator, for example, the pixel value of the pixel point in the product area is set to 255, and the pixel values of the other pixel points are set to 0, so that the template image is not required to be acquired, and the generated binary image is directly used as the template binary image.
Referring to fig. 4, a binary image schematic diagram of a contour detecting method for a lithographic thin film inductor according to an embodiment of the present invention is shown, wherein a black area is an area formed by pixel points with a pixel value of 0, and a white area is an area formed by pixel points with a pixel value of 255.
Before the binarization processing, the image needs to be subjected to the grey level processing, the binarization processing can adopt a threshold method, a pixel value threshold value is preset, the pixel value corresponding to the pixel point which is larger than the pixel value threshold value in the image is set to 255, the pixel value corresponding to other pixel points is set to 0, and the pixel value threshold value can be manually set by an implementer, for example, the pixel value threshold value is set to 127.
In one embodiment, the pixel value threshold may also be an adaptive threshold, such as an average value, a median value, or the like of all pixel values in the image, or an oxford threshold method based on gray histogram statistics.
Since the object of the point difference calculation is a binary image, the calculation result of each pixel point after the point difference calculation only includes three values, namely 0, 255 and-255.
It should be noted that, the template image is aligned with the target image by default, that is, for any coordinate point, the corresponding pixel points in the template image and the target image of the coordinate point represent the same real position, if the template image is not aligned with the target image, the optimal reference position of the target image can be obtained by means of template matching, adding a marker and the like, and the target image is adjusted.
Optionally, the preset direction includes at least one reference direction;
respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image, wherein the method comprises the following steps:
respectively carrying out point difference calculation on the target binary image according to each reference direction to obtain a target point difference image corresponding to the reference direction;
and respectively carrying out point difference calculation on the template binary images according to each reference direction to obtain template point difference images corresponding to the reference directions.
The reference direction may be a direction of pointing difference calculation, and in general, the reference direction may include an X direction and a Y direction, wherein the X direction may refer to a horizontal axis positive direction of an image coordinate system and the Y direction may refer to a vertical axis positive direction of the image coordinate system.
Specifically, the preset direction may include more than one reference direction, for example, in this embodiment, the X direction and the Y direction may be adopted as the reference directions, and the obtained point difference images are also two corresponding points. For any pixel in the binary image, a reference direction adopted according to the current point difference calculation can be determined, for example, for a pixel (i, j), where i may refer to an abscissa of the pixel, j may refer to an ordinate of the pixel, if the reference direction is an X direction, the adjacent pixel is (i+1, j), if the reference direction is a Y direction, the adjacent pixel is (i, j+1), and if the pixel is located in the last row or the last column of the binary image, the point difference is p (i, j+1) -p (i, j), and it is noted that if the pixel is located in the last row or the last column of the binary image, the point difference is a preset value, the preset value may be 0, and traversing all the pixels in the binary image, so as to obtain the point difference image corresponding to the reference direction.
In this embodiment, a plurality of reference directions are set as preset directions, and point difference calculation is performed on the target binary image and the template binary image respectively, so that any binary image corresponds to a plurality of point difference images, so that the point difference information extracted based on the point difference images is richer, and further, the accuracy of determining the candidate contour points based on the point difference information is improved, that is, the accuracy of contour detection is improved.
The step of obtaining the target binary image corresponding to the target image of the product to be detected and the template binary image corresponding to the template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to the preset direction to obtain the target point difference image corresponding to the target binary image and the template point difference image corresponding to the template binary image can provide point difference information for subsequent contour point searching, so that the corresponding relation between the template contour point and the target contour point can be determined conveniently, the situation of false correspondence of the contour point can be effectively avoided, and the accuracy of contour detection is improved.
Step S302, extracting the contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in the target image to obtain at least one target contour point, and determining target point difference information of each target contour point in the target point difference image.
The outline may represent outer edge information of a product in the image, the template outline line segment may refer to an outer edge approximation line segment of a standard product in the template image, and the template point difference information may refer to point difference information corresponding to a template outline point in the template point difference image.
The target contour point may refer to a contour point of a product to be detected in the target image, and the target point difference information may refer to point difference information corresponding to the target contour point in the target point difference image.
Specifically, the contour extraction of the template contour line segment may be implemented in a polygonal approximation manner, for example, using an appxpolydp () function in an OpenCV library, to obtain a polygonal contour similar to the real contour, where the polygonal contour may include a plurality of contour line segments, and correspondingly, at least one template contour line segment is obtained after the contour is extracted from the template image.
After extracting the template contour information, a template contour identifier may be allocated to each pixel according to a template contour segment to which each pixel belongs, where the template contour identifier may be expressed as (m 1 ,n 1 ) Wherein m is 1 It may mean that the pixel point belongs to the mth 1 A plurality of template contour line segments, n 1 Can mean that the pixel point is the mth 1 Nth of the template contour segments 1 And a pixel point.
Similarly, after the target contour information is extracted, a target contour identifier may be allocated to each pixel according to the target contour to which the corresponding pixel belongs, where the target contour identifier may be expressed as (m 2 ,n 2 ) Wherein m is 2 It may mean that the pixel point belongs to the mth 2 Target profile, n 2 Can mean that the pixel point is the mth 2 Nth of the target contours 2 And a pixel point.
Further, a template contour identification image and a template sequence identification image can be constructed according to the template contour identification, and the pixel values of all pixel points in the template contour identification image are m corresponding to the pixel points 1 Value determination, wherein the pixel values of all pixel points in the template sequence identification image are determined by n corresponding to the pixel points 1 And (5) value determination.
Similarly, a target contour identification image and a target sequence identification image can be constructed according to the target contour identification, and the pixel values of all pixel points in the target contour identification image are m corresponding to the pixel points 2 Value determination, wherein the pixel values of all pixel points in the target sequence identification image are determined by n corresponding to the pixel points 2 And determining the value, namely constructing a contour identification image and a sequence identification image so as to quickly record contour information of the pixel points and improve reading and inquiring efficiency.
Referring to fig. 5, a schematic diagram of a contour identification image is provided in this embodiment, in which a pixel with a pixel value of 0 is a pixel included in a first contour, a pixel with a pixel value of 1 is a pixel included in a second contour, and a pixel with a pixel value of 2 is a pixel included in a third contour.
Referring to fig. 6, a sequence identification image schematic diagram provided in this embodiment corresponds to the same product image as the contour identification image schematic diagram, in this sequence identification image schematic diagram, for a pixel point in a first contour, a pixel value corresponding to the starting point is 0 with an upper left corner point, and pixel values are given clockwise, where the pixel values represent serial numbers of the corresponding pixel points in the contour, and when the pixel values are given, 1 is added sequentially, for example, the pixel values corresponding to the pixel points in the first contour are 0 to 13, the pixel values corresponding to the pixel points in the second contour are 0 to 7, and the pixel values corresponding to the pixel points in the third contour are 0 to 11.
In one embodiment, when the default template image and the target image are aligned, the template contour area may be determined according to the template contour line segment, for example, a minimum circumscribed rectangle is adopted to determine the range of the target image for contour extraction according to the template contour area, in this embodiment, the template contour area is directly taken as the range of the target image for contour extraction, in one embodiment, the template contour area may be scaled, the scaled area is taken as the range of the target image for contour extraction, and the target image only carries out contour extraction processing within the range, thereby achieving the effect of isolating irrelevant working conditions and reducing the occurrence of contour noise.
In the product contour detection process, the same template image can be adopted for a plurality of products to be detected which are produced in batches according to the same specification, and the template image is only required to be processed at the moment, and the corresponding template binary image, the template point difference image, the template contour identification image and the template sequence identification image are stored and directly read when in use, so that the contour detection efficiency is further improved.
In this embodiment, taking a single template contour line segment as an example, a subsequent processing procedure is described, and according to coordinate information corresponding to each template contour point in the template contour line segment, pixel values of all coordinate information in a template point difference image, that is, template point difference information, respectively, are extracted, and similarly, target point difference information of each target contour point in a target point difference image can be determined.
The method comprises the steps of extracting the contour in a template image, obtaining a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in a target image, obtaining at least one target contour point, determining target point difference information of each target contour point in the target point difference image, extracting point difference information of the template contour point and the target contour point, facilitating selection of candidate contour line segments according to the subsequent point difference information, improving accuracy of candidate contour line segment determination, and recording the contour information through a contour identification image and a sequence identification image, facilitating improvement of reading and searching efficiency, thereby improving efficiency and accuracy of contour detection.
Step S303, for any template contour point, determining the corresponding position of the template contour point in the target point difference image, searching in the target point difference image along the vertical direction of the template contour line segment by taking the position as a starting point, obtaining a target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point, and taking the target contour point meeting the preset condition as a candidate contour point of the template contour point.
The position may refer to a coordinate corresponding to any template contour point in the template contour line segment, the vertical direction may refer to a vertical direction of a line where the template contour line segment is located, and the candidate contour point may refer to a target contour point having a corresponding relationship with the template contour point.
Optionally, searching in the target point difference image along the vertical direction of the template contour line segment with the position as a starting point to obtain a target contour point corresponding to the same target point difference information as the template point difference information of the template contour point, including:
determining a searching straight line according to the starting point and the vertical direction, and acquiring a target contour point closest to the template contour point on the searching straight line;
and comparing the target point difference information corresponding to the target contour point with the template point difference information of the template contour point, and if the comparison result is consistent, obtaining the target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point.
The search straight line may refer to a straight line for searching for the target contour point.
Specifically, the vertical direction of the template contour line segment may include a positive direction and a negative direction, and when searching in one direction, a ray may be determined according to the starting point and the direction, and when searching in both the positive direction and the negative direction, a search line is formed to perform the search.
And if the comparison results are consistent, obtaining a target contour point corresponding to the target point difference information which is the same as the template point difference information of the template contour point, and stopping the searching process.
If the comparison result is inconsistent, searching is continued until a target contour point corresponding to the target point difference information which is the same as the template point difference information of the template contour point is obtained, and at the moment, the distance between the target contour point and the template contour point is the smallest in the distances between the target contour points corresponding to the target point difference information which is the same as the template point difference information of the template contour point and the template contour point.
Since there may be a plurality of template point difference images and target point difference images, the target point difference information and the template point difference information comparison method are determined according to the number of the target point difference images, for example, if the template point difference image and the target point difference image are one, each target point difference information is compared with the template point difference information respectively, and at least one target point difference information identical to the template point difference information is obtained.
If two template point difference images and two target point difference images exist, respectively, two template point difference information exists in a single template contour point, two template point difference values are regarded as a template point difference pair, each target contour point corresponds to one target point difference pair, each target point difference pair is compared with the template point difference pair, when one target point difference value is the same as the corresponding template point difference value in the comparison result, the other target point difference value is not opposite to the corresponding template point difference value, the target contour point to which the corresponding target contour point belongs is determined to be a candidate contour point, for example, the template point difference pair is (255 ), and the target point difference pair meeting the conditions should be (0, 255), (255 ) and (255, 0).
In the embodiment, the target contour points with the corresponding relation with the template contour points are obtained in a searching mode, the searching range is limited to a searching straight line, the searching range is smaller, only the target contour points with the nearest distance are searched, and the searching efficiency and the searching accuracy can be effectively ensured.
Optionally, taking the target contour point meeting the preset condition as a candidate contour point of the template contour point includes:
aiming at a target contour point corresponding to the same target point difference information as the template point difference information of the template contour point, acquiring the corresponding position of the target contour point in the target point difference image, and calculating the distance between the position of the target contour point and the position of the template contour point to obtain the point position distance;
If the point distance is smaller than a preset searching threshold value, determining that the target contour point meets a preset condition, and taking the target contour point as the candidate contour point.
The point location distance may refer to a distance between a target contour point and a template contour point, and a preset search threshold may be used to measure whether the searched target contour point is an out-of-limit contour point.
Specifically, since the target contour point and the template contour point are both determined according to the template point difference image, the euclidean distance between the position coordinates can be directly used for calculating the point position distance, the search threshold can be set to 3, and the implementer can adjust the search threshold according to the actual situation.
In the embodiment, the searched target contour points are screened through the search threshold, so that the target contour points which are obviously not in corresponding relation with the template contour points can be removed, the calculated amount of the subsequent contour detection is reduced, and the accuracy and the efficiency of the contour detection are improved.
And determining the corresponding position of the template contour point in the target point difference image according to any template contour point, searching in the target point difference image along the vertical direction of the template contour line segment by taking the position as a starting point to obtain a target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point, taking the target contour point meeting the preset condition as a candidate contour point of the template contour point, acquiring the target contour point in a searching mode, selecting the candidate contour point according to the point difference information, and rapidly determining the candidate contour point and the template contour point with the corresponding relation, thereby facilitating the follow-up fine comparison of the candidate contour point and the template contour point and improving the contour detection efficiency and accuracy.
Step S304, traversing all the template contour points to obtain candidate contour points corresponding to the template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
The comparison mode may be to perform point-to-point comparison on each template contour point in the template contour line segment and the corresponding candidate contour point, and the contour detection result may include results of contour splitting, contour missing or pollution, contour adhesion, contour protrusion, contour depression, and the like.
Specifically, each candidate contour point has a candidate contour line to which it belongs, according to the template contour point and the candidate contour point having a corresponding relationship, the template contour line and the candidate contour line having a corresponding relationship can be determined, if there is an un-corresponding template contour point or candidate contour point in the template contour line and the candidate contour line having a corresponding relationship, interpolation can be adopted to perform correspondence so that each template contour point or each candidate contour point has a corresponding relationship, for example, the template contour line a and the template contour point a in the candidate contour line B, a having a corresponding relationship 1 Corresponding to candidate contour point B in B 3 Template contour point a in A 3 Corresponding to candidate contour point B in B 2 If the template contour point a 1 And template contour point a 3 There are also template contour points a between 2 According to the template contour point a 2 Respectively with the outline point a of the template 1 And template contour point a 3 Is the distance between (2)Candidate contour points corresponding to template contour points with smaller determined distance are also corresponding to template contour point a 2 And the corresponding relation exists, and the corresponding relation is built for the candidate contour points in the same way. After the corresponding relation is established, if the corresponding relation exists between a plurality of template contour points and a single candidate contour point, the situation of contour adhesion exists, if the corresponding relation exists between the single template contour point and the plurality of candidate contour points, the situation of contour splitting exists, and if the candidate contour point which does not correspond to the template contour point in the template contour line segment still exists, the situation of contour missing or pollution exists is indicated.
Referring to fig. 7, a schematic diagram of a first template contour is provided in this embodiment, where white pixels may represent template contour information, and is denoted as a first template contour.
Referring to fig. 8, a first outline defect schematic corresponding to a first template outline schematic provided in an embodiment of the present invention is shown, where white pixel points may represent normal outline information, that is, product outline points with normal comparison result with the first template outline, and black pixel points may represent abnormal outline information, that is, product outline points with abnormal comparison result with the first template outline, and when there is a black pixel point, the product outline may be considered to have a defect.
Referring to fig. 9, a schematic diagram of a second template contour is provided in this embodiment, where white pixels may also represent template contour information, denoted as a second template contour.
Referring to fig. 10, a second outline defect schematic diagram corresponding to a second template outline schematic diagram provided by the embodiment of the present invention, in which white pixel points also represent normal outline information, that is, product outline points with normal comparison results with the second template outline, and black pixel points also represent abnormal outline information, that is, product outline points with abnormal comparison results with the second template outline, and when there are black pixel points, the product outline can be considered to have defects.
Optionally, comparing all template contour points in the template contour line segment with all candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result includes:
calculating the average value of the distances between all the template contour points and the corresponding candidate contour points to obtain a first distance value;
and forming candidate contour lines by all the candidate contour points, and determining the candidate contour lines as abnormal lines if the first distance value is larger than a preset distance threshold value.
The first distance value may be a mean value of distances between the template contour points of the groups having the correspondence relationship and the candidate contour points, and the candidate contour line may be a line obtained by fitting the candidate contour points. The preset distance threshold may be used to determine whether the candidate contour line is an abnormal line.
Specifically, when the first distance value is greater than a preset distance threshold value, it is indicated that the template contour line segment cannot correspond to the candidate contour line, and at this time, the candidate contour line of the product to be detected belongs to an abnormal deviation condition, and the candidate contour line is determined to be an abnormal line.
In the embodiment, the comparison is performed between the preset distance threshold value and the first distance value, the initial judgment is performed on the abnormal condition, the candidate contour lines with obvious abnormality are obtained, and the subsequent refined comparison is not needed, so that the contour detection efficiency and accuracy are improved.
Optionally, after obtaining the first distance value, the method further includes:
if the first distance value is smaller than or equal to a preset distance threshold value, calculating the distance calculation between each template contour point in the template contour line segment and the corresponding candidate contour point to obtain a second distance value of the corresponding template contour point;
When any one of the second distance values is larger than the first distance value, determining that the contour detection result is a contour protrusion result;
and when any one of the second distance values is smaller than the first distance value, determining that the contour detection result is a contour concave result.
Wherein the second distance value may represent a distance between the template contour point and its corresponding candidate contour point.
Specifically, if no abnormal condition exists, the candidate contour line should coincide with the template contour line segment, and under the condition that translational error is allowed to occur, the candidate contour line segment obtained by performing straight line fitting based on the candidate contour line should be in parallel relation with the template contour line segment, and the distance between parallel lines to which the candidate contour line segment and the template contour line segment respectively belong is the first distance value.
In this embodiment, when any one of the second distance values is greater than the first distance value, it is indicated that the distance between the corresponding template contour point and the candidate contour point does not satisfy the parallel relationship, and the protrusion condition exists at the candidate contour point, and when any one of the second distance values is smaller than the first distance value, it is indicated that the distance between the corresponding template contour point and the candidate contour point does not satisfy the parallel relationship, and the recess condition exists at the candidate contour point.
In an embodiment, since a certain deviation may exist between a template contour line segment obtained by a polygon approximation mode and a real contour, and a certain error tolerance range exists in product manufacturing, an operator may set a corresponding protrusion threshold and a corresponding recess threshold, in this embodiment, the protrusion threshold and the recess threshold are set to 4, and the operator may adjust the protrusion threshold and the recess threshold according to an actual situation, if any one of the second distance values is greater than the first distance value, and the absolute value of the difference between the second distance value and the second distance value is greater than the protrusion threshold, the contour detection result is determined to be a contour protrusion result, and if any one of the second distance values is less than the first distance value, and the absolute value of the difference between the second distance value and the second distance value is greater than the recess threshold, the contour detection result is determined to be a contour recess result.
In the embodiment, by means of distance comparison, the outline abnormality of the outline bulge and the outline recess can be accurately identified and accurately positioned to the pixel point, so that the size and the position of the defect are accurately and rapidly detected, and the efficiency and the accuracy of outline detection are improved.
Optionally, after the comparison result is obtained, the method further includes:
Determining all template contour points in two template contour line segments with intersection points to form a template point set, and determining candidate contour points corresponding to all template contour points in the two template contour line segments to form a candidate point set;
comparing the template point set with the candidate point set to obtain a reference comparison result;
correspondingly, determining the contour detection result of the target image according to the comparison result comprises the following steps:
and determining a contour detection result of the target image according to the comparison result and the reference comparison result.
The intersection point of the two template contour segments is usually an inflection point, the template point set may include all template contour points in the two template contour segments with the intersection point, the candidate point set may include candidate contour points corresponding to all template contour points in the two template contour segments, and the reference comparison result may be used for rechecking the comparison result.
Specifically, for two template contour line segments with inflection points, taking a single vertex area of a positive rectangle as an example, the single vertex area includes two mutually perpendicular line segments, vertex coordinates are (1, 1), if the vertex area has an oblique offset condition, that is, the vertex coordinates are changed to (0, 0) in the corresponding target contour, when distance calculation is performed on the corresponding candidate contour points respectively, the distance between the corresponding points may be calculated to be 1, however, in the actual correspondence, the template contour points at the inflection points correspond to the candidate contour points, at this time, the actual distance should be ∈2, therefore, all the template contour points in the two template contour line segments with the intersection points form a template point set, and the reference comparison result is obtained by comparing in an integral mode.
In one embodiment, the specific comparison mode may be to determine a translation direction according to the intersection point and the corresponding point thereof, translate the template point set according to the translation direction, and then compare after translation to obtain the reference comparison result.
If the reference comparison result is consistent with the comparison result, determining the contour detection result of the target image according to the comparison result, and if the reference comparison result is inconsistent with the comparison result, determining the contour detection result of the target image according to the reference comparison result.
In this embodiment, all template contour points in the template contour line segment with inflection points are combined and then locally compared, so as to achieve the effect of rechecking, avoid erroneous judgment in the contour comparison process due to existence of the inflection points, and improve the accuracy of contour detection.
And traversing all the template contour points to obtain candidate contour points corresponding to the template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining the contour detection result of the target image according to the comparison result, so that the type and the position of the contour defect can be rapidly and accurately determined, and the efficiency and the accuracy of contour detection are improved.
In this embodiment, candidate contour points are obtained according to the point difference information in combination with the search mode, so that the candidate contour points and the template contour points with corresponding relations can be rapidly determined, and then all the template contour points and all the candidate contour points in the template contour line segment are subjected to fine comparison, so that the contour defect type and the defect position are rapidly determined, and the accuracy and the efficiency of contour detection are improved.
Fig. 11 shows a block diagram of a profile detection apparatus for a lithographic thin film inductor according to a second embodiment of the present invention, where the profile detection apparatus is applied to a client, and a computer device corresponding to the client is connected to a server to obtain a target image of a product to be detected and a target binary image corresponding to the target image, and a template image of a template corresponding to the product to be detected and a template binary image corresponding to the template to be detected, where the target image and the target binary image are required to be subjected to profile detection. For convenience of explanation, only portions relevant to the embodiments of the present invention are shown.
Referring to fig. 11, the contour detecting apparatus includes:
the image acquisition module 111 is configured to acquire a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and perform point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
The contour extraction module 112 is configured to extract a contour in the template image to obtain a template contour line segment, determine template point difference information of each template contour point in the template point difference image in the template contour line segment, extract a contour in the target image to obtain at least one target contour point, and determine target point difference information of each target contour point in the target point difference image;
an image searching module 113, configured to determine, for any one of the template contour points, a position of the template contour point corresponding to the target point difference image, search in the target point difference image along a vertical direction of a template contour line segment with the position as a starting point, obtain a target contour point corresponding to target point difference information identical to template point difference information of the template contour point, and use the target contour point satisfying a preset condition as a candidate contour point of the template contour point;
and the contour comparison module 114 is used for traversing all the template contour points to obtain candidate contour points corresponding to the template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
Optionally, the preset direction includes at least one reference direction;
The image acquisition module 111 includes:
the first point difference calculation unit is used for respectively carrying out point difference calculation on the target binary image according to each reference direction to obtain a target point difference image corresponding to the reference direction;
and the second point difference calculation unit is used for respectively carrying out point difference calculation on the template binary image according to each reference direction to obtain a template point difference image corresponding to the reference direction.
Optionally, the image searching module 113 includes:
a straight line determining unit for determining a search straight line according to the starting point and the vertical direction, and acquiring a target contour point closest to the template contour point on the search straight line;
and the information comparison unit is used for comparing the target point difference information corresponding to the target contour point with the template point difference information of the template contour point to obtain the target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point.
Optionally, the image searching module 113 further includes:
the point position distance calculation unit is used for obtaining the corresponding position of the target contour point in the target point difference image according to the target contour point corresponding to the target point difference information which is the same as the template point difference information of the template contour point, and calculating the distance between the position of the target contour point and the position of the template contour point to obtain the point position distance;
And the condition screening unit is used for determining that the target contour point meets the preset condition and taking the target contour point as the candidate contour point if the point position distance is smaller than the preset searching threshold value.
Optionally, the profile comparison module 114 includes:
the first distance calculation unit is used for calculating the average value of the distances between all the template contour points and the corresponding candidate contour points to obtain a first distance value;
and the line segment abnormality judging unit is used for forming candidate contour lines by all the candidate contour points, and determining the candidate contour lines as abnormal lines if the first distance value is larger than a preset distance threshold value.
Optionally, the profile comparison module 114 further includes:
the second distance calculation unit is used for calculating the distance calculation between each template contour point in the template contour line segment and the corresponding candidate contour point if the first distance value is smaller than or equal to the preset distance threshold value, so as to obtain a second distance value of the corresponding template contour point;
the first abnormality judgment unit is used for determining that the contour detection result is a contour protrusion result when any one of the second distance values is larger than the first distance value;
and the second abnormality judgment unit is used for determining that the contour detection result is a contour concave result when any one of the second distance values is smaller than the first distance value.
Optionally, the contour detection device further includes:
the set determining module is used for determining that all template contour points in the two template contour line segments with the intersection points form a template point set and determining candidate contour points corresponding to all the template contour points in the two template contour line segments form a candidate point set;
the set comparison module is used for comparing the template point set with the candidate point set to obtain a reference comparison result;
correspondingly, the contour comparison module 114 further includes:
and the result determining unit is used for determining the contour detection result of the target image according to the comparison result and the reference comparison result.
It should be noted that, because the content of information interaction, execution process and the like between the modules, units and sub-units is based on the same concept as the method embodiment of the present invention, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.
Fig. 12 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. As shown in fig. 12, the computer device of this embodiment includes: at least one processor (only one shown in fig. 12), a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program to perform the steps of any of the various contour detection method embodiments described above.
The computer device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that fig. 12 is merely an example of a computer device and is not intended to be limiting, and that a computer device may include more or fewer components than shown, or may combine certain components, or different components, such as may also include a network interface, a display screen, an input device, and the like.
The processor may be a CPU, but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory includes a readable storage medium, an internal memory, etc., where the internal memory may be the memory of the computer device, the internal memory providing an environment for the execution of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments may be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. that are provided on the computer device. Further, the memory may also include both internal storage units and external storage devices of the computer device. The memory is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs such as program codes of computer programs, and the like. The memory may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working process of the units and modules in the above device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again. The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above-described embodiment, and may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The present invention may also be implemented as a computer program product for implementing all or part of the steps of the method embodiments described above, when the computer program product is run on a computer device, causing the computer device to execute the steps of the method embodiments described above.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/computer device and method may be implemented in other manners. For example, the apparatus/computer device embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (10)

1. A profile detection method for a photolithographic thin film inductor, the profile detection method comprising:
acquiring a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
Extracting the contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in the target image to obtain at least one target contour point, and determining target point difference information of each target contour point in the target point difference image;
determining the corresponding position of the template contour point in the target point difference image aiming at any template contour point, searching in the target point difference image along the vertical direction of the template contour line segment by taking the position as a starting point to obtain a target contour point corresponding to target point difference information identical to the template point difference information of the template contour point, and taking the target contour point meeting the preset condition as a candidate contour point of the template contour point;
and traversing all the template contour points to obtain candidate contour points corresponding to the template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
2. The contour detection method as defined in claim 1, wherein said preset direction comprises at least one reference direction;
The calculating of the point difference is performed on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image, including:
respectively carrying out point difference calculation on the target binary image according to each reference direction to obtain a target point difference image corresponding to the reference direction;
and respectively carrying out point difference calculation on the template binary images according to each reference direction to obtain template point difference images corresponding to the reference directions.
3. The contour detection method as defined in claim 1, wherein searching in the target point difference image along a vertical direction of the template contour line segment with the position as a starting point to obtain a target contour point corresponding to the same target point difference information as the template point difference information of the template contour point comprises:
determining a searching straight line according to the starting point and the vertical direction, and acquiring a target contour point closest to the template contour point on the searching straight line;
and comparing the target point difference information corresponding to the target contour point with the template point difference information of the template contour point, and if the comparison result is consistent, obtaining the target contour point corresponding to the target point difference information identical to the template point difference information of the template contour point.
4. A contour detection method as defined in claim 3, wherein said taking a target contour point satisfying a preset condition as a candidate contour point of said template contour point comprises:
aiming at a target contour point corresponding to target point difference information which is the same as the template point difference information of the template contour point, acquiring a position corresponding to the target contour point in the target point difference image, and calculating a distance between the position of the target contour point and the position of the template contour point to obtain a point position distance;
and if the point position distance is smaller than a preset searching threshold value, determining that the target contour point meets a preset condition, and taking the target contour point as the candidate contour point.
5. The contour detection method as defined in claim 1, wherein comparing all template contour points in the template contour line segment with all candidate contour points to obtain a comparison result, and determining the contour detection result of the target image according to the comparison result comprises:
calculating the average value of the distances between all the template contour points and the corresponding candidate contour points to obtain a first distance value;
and forming candidate contour lines by all the candidate contour points, and determining the candidate contour lines as abnormal lines if the first distance value is larger than a preset distance threshold value.
6. The contour detection method as defined in claim 5, further comprising, after said obtaining a first distance value:
if the first distance value is smaller than or equal to a preset distance threshold value, calculating the distance calculation between each template contour point in the template contour line segment and the corresponding candidate contour point to obtain a second distance value of the corresponding template contour point;
when any one of the second distance values is larger than the first distance value, determining that the contour detection result is a contour protrusion result;
and when any one of the second distance values is smaller than the first distance value, determining that the contour detection result is a contour concave result.
7. The contour detection method as defined in any one of claims 1-6, further comprising, after said obtaining a comparison result:
determining that all template contour points in two template contour line segments with intersection points form a template point set, and determining candidate contour points corresponding to all template contour points in the two template contour line segments form a candidate point set;
comparing the template point set with the candidate point set to obtain a reference comparison result;
correspondingly, the determining the contour detection result of the target image according to the comparison result comprises the following steps:
And determining a contour detection result of the target image according to the comparison result and the reference comparison result.
8. A profile inspection apparatus for a lithographic thin film inductor, the profile inspection apparatus comprising:
the image acquisition module is used for acquiring a target binary image corresponding to a target image of a product to be detected and a template binary image corresponding to a template image, and respectively carrying out point difference calculation on the target binary image and the template binary image according to a preset direction to obtain a target point difference image corresponding to the target binary image and a template point difference image corresponding to the template binary image;
the contour extraction module is used for extracting the contour in the template image to obtain a template contour line segment, determining template point difference information of each template contour point in the template point difference image in the template contour line segment, extracting the contour in the target image to obtain at least one target contour point, and determining target point difference information of each target contour point in the target point difference image;
an image searching module, configured to determine, for any one of the template contour points, a position of the template contour point corresponding to the target point difference image, and search in the target point difference image along a vertical direction of the template contour line segment with the position as a starting point, to obtain a target contour point corresponding to target point difference information identical to template point difference information of the template contour point, where the target contour point satisfying a preset condition is used as a candidate contour point of the template contour point;
And the contour comparison module is used for traversing all the template contour points to obtain candidate contour points of the corresponding template contour points, comparing all the template contour points in the template contour line segment with all the candidate contour points to obtain a comparison result, and determining a contour detection result of the target image according to the comparison result.
9. A computer device, characterized in that it comprises a processor, a memory and a computer program stored in the memory and executable on the processor, which processor implements the contour detection method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the contour detection method according to any one of claims 1 to 7.
CN202310255362.4A 2023-03-15 2023-03-15 Contour detection method, device, equipment and medium for photoetching film inductance Active CN116542998B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310255362.4A CN116542998B (en) 2023-03-15 2023-03-15 Contour detection method, device, equipment and medium for photoetching film inductance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310255362.4A CN116542998B (en) 2023-03-15 2023-03-15 Contour detection method, device, equipment and medium for photoetching film inductance

Publications (2)

Publication Number Publication Date
CN116542998A CN116542998A (en) 2023-08-04
CN116542998B true CN116542998B (en) 2023-11-17

Family

ID=87447853

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310255362.4A Active CN116542998B (en) 2023-03-15 2023-03-15 Contour detection method, device, equipment and medium for photoetching film inductance

Country Status (1)

Country Link
CN (1) CN116542998B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6621924B1 (en) * 1999-02-26 2003-09-16 Sony Corporation Contour extraction apparatus, a method thereof, and a program recording medium
CN103364410A (en) * 2013-07-23 2013-10-23 三峡大学 Crack detection method of hydraulic concrete structure underwater surface based on template search
CN108037133A (en) * 2017-12-27 2018-05-15 武汉市智勤创亿信息技术股份有限公司 A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image
CN108037132A (en) * 2017-12-25 2018-05-15 华南理工大学 A kind of visual sensor system and method for the detection of dry cell pulp layer paper winding defect
CN112085755A (en) * 2020-09-14 2020-12-15 贝壳技术有限公司 Object contour detection method, device and equipment and storage medium
CN112348797A (en) * 2020-11-09 2021-02-09 东方晶源微电子科技（北京）有限公司深圳分公司 Bridging defect detection method for double-pattern mask optimization result and electronic equipment
CN112598657A (en) * 2020-12-28 2021-04-02 锋睿领创(珠海)科技有限公司 Defect detection method and device, model construction method and computer equipment
CN112734761A (en) * 2021-04-06 2021-04-30 中科慧远视觉技术(北京)有限公司 Industrial product image boundary contour extraction method
CN114199895A (en) * 2021-12-15 2022-03-18 珠海高纳智能科技有限公司 Inductance defect visual detection method
CN114943704A (en) * 2022-05-24 2022-08-26 蜂巢能源科技股份有限公司 Method, device and equipment for detecting defects of battery electrode die-cut piece

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6621924B1 (en) * 1999-02-26 2003-09-16 Sony Corporation Contour extraction apparatus, a method thereof, and a program recording medium
CN103364410A (en) * 2013-07-23 2013-10-23 三峡大学 Crack detection method of hydraulic concrete structure underwater surface based on template search
CN108037132A (en) * 2017-12-25 2018-05-15 华南理工大学 A kind of visual sensor system and method for the detection of dry cell pulp layer paper winding defect
CN108037133A (en) * 2017-12-27 2018-05-15 武汉市智勤创亿信息技术股份有限公司 A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image
CN112085755A (en) * 2020-09-14 2020-12-15 贝壳技术有限公司 Object contour detection method, device and equipment and storage medium
CN112348797A (en) * 2020-11-09 2021-02-09 东方晶源微电子科技（北京）有限公司深圳分公司 Bridging defect detection method for double-pattern mask optimization result and electronic equipment
CN112598657A (en) * 2020-12-28 2021-04-02 锋睿领创(珠海)科技有限公司 Defect detection method and device, model construction method and computer equipment
CN112734761A (en) * 2021-04-06 2021-04-30 中科慧远视觉技术(北京)有限公司 Industrial product image boundary contour extraction method
CN114199895A (en) * 2021-12-15 2022-03-18 珠海高纳智能科技有限公司 Inductance defect visual detection method
CN114943704A (en) * 2022-05-24 2022-08-26 蜂巢能源科技股份有限公司 Method, device and equipment for detecting defects of battery electrode die-cut piece

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
A Novel Pixel Orientation Estimation Based Line Segment Detection Framework, and Its Applications to SAR Images;Chenguang Liu等;《IEEE Transactions on Geoscience and Remote Sensing》;第60卷;1-18 *
Investigation on Multisets Mixture Learning Based Object Detection;Zhiyong Liu等;《International Journal of Pattern Recognition and Artificial Intelligence》;第21卷(第08期);1339-1351 *
基于机器视觉的刹车片尺寸综合检测系统研究;胡琳丽;《中国优秀硕士学位论文全文数据库_工程科技Ⅱ辑》;C035-279 *
基于机器视觉的触摸屏玻璃缺陷检测方法研究;陈晓红;《中国优秀硕士学位论文全文数据库_信息科技辑》;I140-662 *
空间目标快速轮廓特征提取与跟踪技术;曹姝清;刘宗明;牟金震;张翰墨;张宇;;飞控与探测(第02期);38-43 *

Also Published As

Publication number Publication date
CN116542998A (en) 2023-08-04

Similar Documents

Publication Publication Date Title
CN110060237B (en) Fault detection method, device, equipment and system
CN106960208B (en) Method and system for automatically segmenting and identifying instrument liquid crystal number
CN108564579B (en) Concrete crack detection method and detection device based on time-space correlation
CN109738450B (en) Method and device for detecting notebook keyboard
CN109740417B (en) Invoice type identification method, invoice type identification device, storage medium and computer equipment
CN109509200A (en) Checkerboard angle point detection process, device and computer readable storage medium based on contours extract
CN115205223B (en) Visual inspection method and device for transparent object, computer equipment and medium
CN111898610B (en) Card unfilled corner detection method, device, computer equipment and storage medium
CN111695410A (en) Violation reporting method and device, computer equipment and storage medium
CN114387591A (en) License plate recognition method, system, equipment and storage medium
CN112651953A (en) Image similarity calculation method and device, computer equipment and storage medium
CN112419207A (en) Image correction method, device and system
CN117094975A (en) Method and device for detecting surface defects of steel and electronic equipment
CN116542998B (en) Contour detection method, device, equipment and medium for photoetching film inductance
CN115345895B (en) Image segmentation method and device for visual detection, computer equipment and medium
CN111695374B (en) Segmentation method, system, medium and device for zebra stripes in monitoring view angles
CN116188826A (en) Template matching method and device under complex illumination condition
CN116228861A (en) Probe station marker positioning method, probe station marker positioning device, electronic equipment and storage medium
CN113378847B (en) Character segmentation method, system, computer device and storage medium
CN115423765A (en) Grain defect quantitative segmentation method based on template image
CN115619725A (en) Electronic component detection method and device, electronic equipment and automatic quality inspection equipment
CN112052859B (en) License plate accurate positioning method and device in free scene
CN112085683A (en) Depth map reliability detection method in significance detection
CN111062984A (en) Method, device and equipment for measuring area of video image region and storage medium
CN114581890B (en) Method and device for determining lane line, electronic equipment and storage medium

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