WO2019184094A1 - 一种牙孔检测方法及装置 - Google Patents

一种牙孔检测方法及装置 Download PDF

Info

Publication number
WO2019184094A1
WO2019184094A1 PCT/CN2018/090872 CN2018090872W WO2019184094A1 WO 2019184094 A1 WO2019184094 A1 WO 2019184094A1 CN 2018090872 W CN2018090872 W CN 2018090872W WO 2019184094 A1 WO2019184094 A1 WO 2019184094A1
Authority
WO
WIPO (PCT)
Prior art keywords
tapping
image
metal stamping
stamping part
module
Prior art date
Application number
PCT/CN2018/090872
Other languages
English (en)
French (fr)
Inventor
高志坚
王廷
曾庆好
Original Assignee
深圳大学
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 深圳大学 filed Critical 深圳大学
Publication of WO2019184094A1 publication Critical patent/WO2019184094A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • 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
    • G06T7/0012—Biomedical image inspection
    • 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
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30036—Dental; Teeth
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Definitions

  • the invention relates to the field of metal stamping parts production automation, in particular to a method and device for detecting dental holes.
  • the dental prosthesis after metal stamping parts is detected by manual visual inspection.
  • Manual visual inspection requires the detection of metal stamping parts. It requires excellent visual and endurance, and it costs a lot. Human Resources.
  • the existing dental hole detecting device can automatically detect the state of the dental hole, thereby detecting the dental hole defect of the metal stamping part, thereby saving manpower.
  • the existing dental prosthetic detecting device drives the detecting screw on the electric screwdriver to slide linearly and reciprocally to enter or leave the detecting tooth hole, and the position detecting device detects the position of the slider to determine whether the screw is screwed into the inner diameter of the tooth hole. If the tooth hole is damaged, the detection screw can not be screwed into the required position, and the metal stamping part with the tapping defect can be detected.
  • the tooth hole detecting device needs to make the outer thread radius of the detecting screw smaller than the tooth hole radius.
  • the specifications of metal stamping parts are getting smaller and smaller, the precision of detecting screws is getting higher and higher, the specifications of metal stamping parts are too small, and the existing testing devices cannot be used after tapping of metal stamping parts. The dental hole is tested.
  • the main object of the present invention is to provide a method and a device for detecting a dental hole, which are used for solving the technical problem that the dental hole after the tapping of the metal stamping part with too small specification can not be detected in the prior art.
  • a first aspect of the present invention provides a method for detecting a dental hole, the method comprising:
  • a second aspect of the invention provides a dental aperture detecting apparatus, the apparatus comprising:
  • An acquisition module configured to collect a tapping image of the metal stamping part and convert the tapping image into a grayscale image, where the tapping image is an image of the tooth hole of the metal stamping part after the tapping of the camera;
  • a positioning module configured to extract a positioning area of the tooth hole in the tapping image by using a fixed threshold, a contour extraction algorithm, and a minimum circumscribed rectangle algorithm;
  • a calculation module configured to calculate a center position and a radius of the inner circle of the positioning area by using a minimum circumscribed circle algorithm, and calculate a difference between the radius of the inner circle and the inner circle radius of the standard metal stamping part;
  • a determining module configured to determine, according to whether the difference exceeds a preset difference, that the metal stamping part has a tapping defect, and output the metal stamping part as a signal of a defective product.
  • the method uses a fixed threshold, a contour extraction algorithm and a minimum circumscribed rectangle algorithm to extract a positioning area of a tooth hole in a tapping image, and calculates a radius of the inner circle of the positioning area and a standard metal stamping tooth.
  • the difference of the radius of the circle in the hole area is analyzed according to the relationship between the difference and the preset difference value to determine the existence of the tapping defect of the metal stamping part, and the output of the metal stamping part is a bad product signal, thereby the metal stamping part is not Good products are detected.
  • the method is used to detect the tapping defect and improve the accuracy of the tooth hole detection, and the tooth hole detecting method only needs to obtain the tapping image of the metal stamping part, and the specification size of the metal stamping part does not affect the use of the method.
  • FIG. 1 is a schematic flow chart of a method for detecting a dental orifice according to a first embodiment of the present invention
  • FIG. 2 is a schematic flow chart of the step of refining step 102 in the first embodiment
  • step 3 is a schematic flow chart of the refinement step of step 104 in the first embodiment
  • FIG. 4 is a schematic structural view of a dental orifice detecting device according to a second embodiment of the present invention.
  • FIG. 5 is a schematic view showing a refinement structure of a positioning module in the second embodiment
  • Fig. 6 is a schematic view showing the refinement structure of the determination module in the second embodiment.
  • the present invention proposes a method for detecting a tooth hole to accurately detect an operation hole after tapping of a metal stamping member having a small specification.
  • FIG. 1 is a schematic flowchart diagram of a method for detecting a dental hole according to a first embodiment of the present invention.
  • the method for detecting an indentation includes steps 101 to 104:
  • Step 101 Collect a tapping image of the metal stamping part and convert the tapping image into a grayscale image, where the tapping image is an image of the tooth hole of the metal stamping part after the tapping of the camera.
  • the camera captures an image of the tooth hole of the metal stamping part after tapping
  • the control system used by the detecting method obtains an image of the tooth hole of the metal stamping part after tapping, that is, obtaining the metal stamping
  • the tapping image of the piece is converted into a grayscale image after acquiring the tapping image of the metal stamping part, so as to further process the tapping image.
  • Step 102 Extract a positioning area of the tooth hole in the tapping image by using a fixed threshold, a contour extraction algorithm, and a minimum circumscribed rectangle algorithm.
  • the purpose of extracting the positioning area of the tapping image by using a fixed threshold, a contour extraction algorithm and a minimum circumscribed rectangle algorithm is to extract the position of the dental hole of the metal stamping.
  • FIG. 2 is a schematic flowchart of the step of refining step 102 in the first embodiment, and the step of extracting the positioning area of the tooth hole in the tapping image by using a fixed threshold, a contour extraction algorithm, and a minimum circumscribed rectangle algorithm includes the steps. 201 to step 203:
  • Step 201 Perform local enhancement processing and avoidance processing on the grayscale image of the tapping image to obtain a first tapping image.
  • the first tapping image is a tapping image that has been subjected to local enhancement processing and avoidance processing.
  • the specific step of step 201 is: traversing the pixel value of the tapping image, and setting a pixel value greater than a preset specified value as a preset. Specify to set the pixel value less than the preset value to zero.
  • a specified value of the pixel is preset, the pixel value of the image area of the gray image is traversed, the pixel value greater than the specified value is set to a specified value, and the pixel value smaller than the specified value is set to zero.
  • the local enhancement processing is performed on the grayscale image of the tapping image.
  • Step 202 Perform image binarization processing on the first tapping image to obtain a second tapping image.
  • the second tapping image is a tapping image that has been binarized.
  • Step 203 performing image etching on the second tapping image, and then performing contour contour detection on the second tapping image by using a contour extraction algorithm, and using a minimum external quadrilateral fitting process on the contour having the largest area, and obtaining four fixed points of the external quadrilateral. coordinate.
  • the contour extraction algorithm is used to perform image contour detection, and the contour with the largest area is subjected to minimum external quadrilateral fitting processing.
  • Four fixed-point coordinates of the external quadrilateral, the four fixed-point coordinates are the positioning areas obtained in the tapping image, which is the area of the perforations of the metal stamping parts.
  • Step 103 Calculate the inner circle center position and the inner circle radius of the positioning area by using a minimum circumscribed circle algorithm, and calculate a difference between the inner circle radius and the inner circle radius of the standard metal stamping part.
  • the positioning area refers to a hole area after tapping of the metal stamping part
  • the inner circle center position and the inner circle radius of the tooth punch area of the metal stamping part can be obtained by using a minimum circumscribed circle algorithm, the inner circle radius and the standard metal stamping
  • Step 104 Analyze and determine that there is a tapping defect in the metal stamping part according to the relationship between the difference value and the preset difference value, and output the signal that the metal stamping part is a defective product.
  • the magnitude relationship between the difference and the preset difference value is compared, and the metal stamping component is re-analyzed according to the magnitude relationship to determine that the tapping defect is a defective product.
  • FIG. 3 is a schematic flow chart of the refinement step of step 104 in the first embodiment, and analyzing and determining the presence of a tapping defect in the metal stamping part according to the relationship between the difference value and the preset difference value.
  • the signal for outputting the metal stamping part as a defective product specifically includes steps 301 to 306:
  • Step 301 Determine whether the difference exceeds a preset difference value
  • Step 302 If the difference exceeds the preset difference, determining that the metal stamping part has a tapping defect, and outputting the metal stamping part as a signal of the defective product;
  • Step 303 If the difference does not exceed the preset difference, expand an inner circle radius of the positioning area to obtain a detection circle.
  • Step 304 Set the pixel values of the inner circle inner portion of the positioning area and the outer portion of the detection circle to zero, and calculate the number of pixel points of the annular portion between the inner circle of the positioning area and the detection circle;
  • Step 305 Determine whether the number of pixel points is within a preset range
  • Step 306 If it is not in the preset range, determine that the metal stamping part has a tapping defect, and output the metal stamping part as a signal of the defective product.
  • the difference is first determined whether the difference exceeds the preset difference. If it is determined that the difference is greater than the preset difference, it is determined that the metal stamping part has a tapping defect, and the metal stamping part is output as a signal of the defective product. If it is determined that the difference is less than or equal to the preset difference, the next operation is performed to expand the inner circle radius of the positioning area to obtain a detection circle, and the inner circle of the positioning area and the pixel value of the outer part of the detection circle are obtained.
  • the detecting method further includes:
  • the contour extraction algorithm and the minimum circumscribed rectangle algorithm cannot extract the positioning area of the tooth hole in the tapping image, it is determined that the metal stamping part has a tapping defect, and the metal stamping part is output as a signal of the defective product.
  • the positioning area that cannot obtain the tooth hole of the tapping image refers to the coordinate that the tooth hole area of the metal stamping part cannot be obtained.
  • the method uses a fixed threshold, a contour extraction algorithm and a minimum circumscribed rectangle algorithm to extract the positioning area of the tooth hole in the tapping image, and calculates the radius of the inner circle of the positioning area and the standard metal stamping teeth.
  • the difference of the radius of the circle in the hole area is analyzed according to the relationship between the difference and the preset difference value to determine the existence of the tapping defect of the metal stamping part, and the output of the metal stamping part is a bad product signal, thereby the metal stamping part is not Good products are detected.
  • the method is used to detect the tapping defect and improve the accuracy of the tooth hole detection, and the tooth hole detecting method only needs to obtain the tapping image of the metal stamping part, and the specification size of the metal stamping part does not affect the use of the method.
  • FIG. 4 is a schematic structural diagram of a dental aperture detecting apparatus according to a second embodiment of the present invention.
  • the dental aperture detecting apparatus includes an acquiring module 401, a positioning module 402, a calculating module 403, and a determining module 404:
  • the collecting module 401 is configured to collect a tapping image of the metal stamping part and convert the tapping image into a grayscale image, where the tapping image is an image of the tooth hole of the metal stamping part after the tapping of the camera.
  • the camera captures an image of the tooth hole of the metal stamping part after tapping
  • the collecting module 401 obtains an image of the tooth hole of the metal stamping part after tapping, that is, obtaining a tapping image of the metal stamping part.
  • the tapping image is converted into a grayscale image to further process the tapping image.
  • the positioning module 402 is configured to extract a positioning area of the tooth hole in the tapping image by using a fixed threshold, a contour extraction algorithm, and a minimum circumscribed rectangle algorithm.
  • the purpose of extracting the positioning area of the tapping image by using a fixed threshold, a contour extraction algorithm and a minimum circumscribed rectangle algorithm is to extract the position of the dental hole of the metal stamping.
  • FIG. 5 is a schematic diagram of a refinement structure of a positioning module in a second embodiment.
  • the positioning module 402 specifically includes a first processing module 501, a second processing module 502, and an extraction module 503:
  • the first processing module 501 is configured to perform local enhancement processing and avoidance processing on the grayscale image of the tapping image to obtain a first tapping image.
  • the first tapping image is a tapping image that has been subjected to local enhancement processing and avoidance processing.
  • the first processing module 501 traverses the pixel value of the tapping image, and sets a pixel value greater than a preset specified value as a preset designation. Set, the pixel value less than the preset specified value is set to zero.
  • the first processing module 501 presets a specified value of the pixel, traverses the pixel value of the image region of the grayscale image, sets a pixel value greater than the specified value to a specified value, and sets a pixel value smaller than the specified value. Both are set to zero to complete the local enhancement processing of the grayscale image of the tapping image.
  • the second processing module 502 is configured to perform image binarization processing on the first tapping image to obtain a second tapping image.
  • the second tapping image is a tapping image that has been binarized.
  • the extracting module 503 is configured to perform image etching on the second tapping image, and then perform contour contour detection on the second tapping image by using a contour extraction algorithm, and adopt a minimum external quadrilateral fitting processing on the contour with the largest area to obtain an external quadrilateral Four fixed point coordinates.
  • the first processing module 501 after acquiring the grayscale image of the tapping image, the first processing module 501 performs local enhancement processing and avoidance processing on the grayscale image to obtain the first tapping image.
  • the second processing module 502 performs binarization processing on the first tapping image to obtain a second tapping image, and then the extracting module 503 performs image etching on the second tapping image, and then uses a contour extraction algorithm to perform image contour detection.
  • the minimum external quadrilateral fitting process is applied to the contour with the largest area, and four fixed-point coordinates of the external quadrilateral are obtained.
  • the four fixed-point coordinates are the positioning areas obtained in the tapping image, which is the dental hole area of the metal stamping part.
  • the calculation module 403 is configured to calculate the inner circle center position and the inner circle radius of the positioning area by using a minimum circumscribed circle algorithm, and calculate a difference between the inner circle radius and the inner circle radius of the standard metal stamping part.
  • the positioning area refers to a hole area after tapping of the metal stamping part
  • the inner circle center position and the inner circle radius of the tooth punch area of the metal stamping part can be obtained by using a minimum circumscribed circle algorithm, the inner circle radius and the standard metal stamping
  • the determining module 404 is configured to analyze and determine that the metal stamping part has a tapping defect according to the magnitude relationship between the difference value and the preset difference value, and output the metal stamping part as a defective product.
  • the magnitude relationship between the difference and the preset difference value is compared, and the metal stamping component is re-analyzed according to the magnitude relationship to determine that the tapping defect is a defective product.
  • FIG. 6 is a schematic diagram of a refinement structure of the determining module in the second embodiment.
  • the determining module 404 specifically includes a first judging module 601, a first output module 602, an expansion module 603, and a setting computing module. 604.
  • the second determining module 605 and the second output module 606 are:
  • the first determining module 601 is configured to determine whether the difference exceeds a preset difference value
  • the first output module 602 is configured to: when the difference exceeds the preset difference, determine that the metal stamping part has a tapping defect, and output the metal stamping part as a signal of the defective product;
  • the expansion module 603 is configured to expand an inner circle radius of the positioning area when the difference does not exceed the preset difference, to obtain a detection circle;
  • the setting calculation module 604 is configured to set the pixel values of the inner circle inner portion of the positioning area and the outer portion of the detection circle to zero, and calculate the pixel points of the inner circle between the inner circle of the positioning area and the detection circle. quantity;
  • the second determining module 605 is configured to determine whether the number of pixel points is within a preset range
  • the second output module 606 is configured to determine that the metal stamping part has a tapping defect when the preset part is not in the preset range, and output the metal stamping part as a signal of the defective product.
  • the first determining module 601 first determines whether the difference exceeds the preset difference. If the difference is greater than the preset difference, the first output module 602 determines that the metal stamping part has a tapping defect, and outputs the Metal stamping parts are signals of defective products. If the first determining module 601 determines that the difference is less than or equal to the preset difference, proceeding to the next step, the expansion module 603 expands the inner circle radius of the positioning area to obtain a detection circle, and the setting calculation module 604 sets the inner circle of the positioning area.
  • the pixel values of the inner portion of the circle and the outer portion of the detection circle are both set to zero, and the number of pixel points of the inner circle between the inner circle and the detection circle of the positioning area is calculated, and the second determining module 605 determines the number of pixel points. Whether it is within the preset range, if not in the preset range, the second output module 606 determines that the metal stamping part has a tapping defect, and the output metal stamping part is a signal of a defective product, and the operation improves the defective metal stamping part. Screening rate.
  • the dental hole detecting device further includes:
  • the confirmation module is configured to determine that the metal stamping part has a tapping defect when the fixed threshold, the contour extraction algorithm, and the minimum circumscribed rectangle algorithm cannot extract the positioning area of the tooth hole in the tapping image, and output the metal stamping part as not Good signal.
  • the positioning area that cannot obtain the tooth hole of the tapping image refers to the coordinate that the tooth hole area of the metal stamping part cannot be obtained.
  • the positioning module of the device extracts the positioning region of the tooth hole in the tapping image by using a fixed threshold, a contour extraction algorithm and a minimum circumscribed rectangle algorithm, and the calculation module calculates the radius of the inner circle of the positioning region by The difference between the inner circle radius of the standard metal stamping part, the determination module determines and determines the existence of the tapping defect of the metal stamping part according to the relationship between the difference and the preset difference value, and outputs the metal stamping part as the signal of the defective product, This detects the defective products of the metal stamping parts.
  • the device is used to detect the tapping defect and improve the accuracy of the tooth hole detection, and the tooth hole detecting device only needs to obtain the tapping image of the metal stamping part, and the specification size of the metal stamping part does not affect the use of the method.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules is only a logical function division.
  • there may be another division manner for example, multiple modules or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the modules described as separate components may or may not be physically separated.
  • the components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Abstract

一种牙孔检测方法，包括：采集五金冲压件的攻牙图像并将该攻牙图像转换成灰度图（101），采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像中牙孔的定位区域（102），再采用最小外接圆算法计算该定位区域的内圆圆心位置和内圆半径大小，计算该内圆半径与标准五金冲压件牙孔区域内圆半径的差值（103），最后根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号（104），从而将五金冲压件中的不良品检测出来。采用该方法检测攻牙缺陷，提高牙孔检测的精度，且只需获取五金冲压件的攻牙图像，五金冲压件的规格大小不影响该方法的使用。

Description

一种牙孔检测方法及装置
本发明涉及五金冲压件生产自动化领域，尤其涉及一种牙孔检测方法及装置。
目前五金冲压件攻牙后的牙孔检测采用人工目视检测的方法，人工目视检测需对五金冲压件的攻牙一一检测，需要检测人员有极好的视力和耐力，花费很大的人力资源。现有的牙孔检测装置，能自动检测牙孔的状态，从而将五金冲压件的牙孔缺陷检测出来，节省人力。
现有的牙孔检测装置是通过滑块带动电动螺丝起子上的检测螺丝直线往复滑动来进入或脱离检测牙孔，通过位置检测装置检测滑块的位置来判断螺丝是否旋入牙孔内定深度。若牙孔存在损坏，检测螺丝无法旋入到要求位置，即可将存在攻牙缺陷的五金冲压件检测出来，此牙孔检测装置，需使检测螺丝的外螺纹半径小于牙孔半径。然而，随着技术发展，五金冲压件的规格越来越小，检测螺丝的精细度要求也越来越高，五金冲压件的规格过小时，现有检测装置无法对五金冲压件攻牙后的牙孔进行检测。
发明内容
本发明的主要目的在于提供一种牙孔检测方法及装置，用于解决现有技术中无法对规格过小的五金冲压件攻牙后的牙孔进行检测的技术问题。
为实现上述目的，本发明第一方面提供一种牙孔检测方法，所述方法包括：
采集五金冲压件的攻牙图像并将所述攻牙图像转换成灰度图，所述攻牙图像为相机拍摄的所述五金冲压件攻牙后牙孔的图像；
采用固定阈值、轮廓提取算法和最小外接矩形算法提取所述攻牙图像中所述牙孔的定位区域；
采用最小外接圆算法计算所述定位区域的内圆圆心位置和内圆半径大小，计算所述内圆半径与标准五金冲压件牙孔区域内圆半径的差值；
根据所述差值与预置差值大小关系来分析确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
本发明第二方面提供一种牙孔检测装置，所述装置包括：
采集模块，用于采集五金冲压件的攻牙图像并将所述攻牙图像转换成灰度图，所述攻牙图像为相机拍摄的所述五金冲压件攻牙后牙孔的图像；
定位模块，用于采用固定阈值、轮廓提取算法和最小外接矩形算法提取所述攻牙图像中所述牙孔的定位区域；
计算模块，用于采用最小外接圆算法计算所述定位区域的内圆圆心位置和半径大小，计算所述内圆半径与标准五金冲压件牙孔区域内圆半径的差值；
确定模块，用于根据所述差值是否超过预置差值确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
从上述发明提供的技术方案可知，该方法利用固定阈值、轮廓提取算法和最小外接矩形算法提取攻牙图像中牙孔的定位区域，通过计算该定位区域内圆半径的大小与标准五金冲压件牙孔区域内圆半径的差值，根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号，由此将五金冲压件的不良品检测出来。采用该方法检测攻牙缺陷，提高牙孔检测的精度，且采用该牙孔检测方法只需获取五金冲压件的攻牙图像，五金冲压件的规格大小不影响该方法的使用。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明第一实施例提供的牙孔检测方法的流程示意图；
图2为第一实施例中步骤102细化步骤的流程示意图；
图3为第一实施例中步骤104的细化步骤的流程示意图；
图4为本发明第二实施例提供的牙孔检测装置的结构示意图；
图5为第二实施例中定位模块的细化结构的示意图；
图6为第二实施例中确定模块的细化结构的示意图。
具体实施方式
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而非全部实施例。基于本发明中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
由于现有技术中无法对规格过小的五金冲压件攻牙后的牙孔进行检测。为了解决上述技术问题，本发明提出一种牙孔检测方法，以对规格过小的五金冲压件攻牙后的牙孔进行精确地检测。
请参阅图1，图1为本发明第一实施例提供的牙孔检测方法的流程示意图，该牙孔检测方法包括步骤101至步骤104：
步骤101、采集五金冲压件的攻牙图像并将该攻牙图像转换成灰度图，该攻牙图像为相机拍摄的五金冲压件攻牙后牙孔的图像。
具体地，在本发明实施例中，相机拍摄五金冲压件攻牙后牙孔的图像，该检测方法所运用的控制系统获取该五金冲压件攻牙后牙孔的图像，即为获取该五金冲压件的攻牙图像，在获取该五金冲压件的攻牙图像后将该攻牙图像转换成灰度图，以便进一步地对该攻牙图像进行处理。
步骤102、采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像中牙孔的定位区域。
其中，采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像的定位区域的目的是提取到该五金冲压件的牙孔位置。
如图2所示，图2为第一实施例中步骤102细化步骤的流程示意图，采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像中牙孔的定位区域具体步骤包括步骤201至步骤203：
步骤201、对攻牙图像的灰度图进行局部增强处理和避位处理，得到第一攻牙图像。
其中，第一攻牙图像为已进行局部增强处理和避位处理的攻牙图像，步骤201具体步骤为：遍历该攻牙图像的像素值，将大于预置指定值的像素值设置为预置指定置，将小于该预置指定值的像素值均设置为零。
具体地，预先设置像素的一个指定值，遍历该灰度图像的图像区域的像素值，将大于该指定值的像素值均设置为指定值，将小于该指定值的像素值均设置为零，以完成对攻牙图像的灰度图进行局部增强处理。
步骤202、对该第一攻牙图像进行图像二值化处理，得到第二攻牙图像。
其中，第二攻牙图像为己进行二值化处理的攻牙图像。
步骤203、对该第二攻牙图像进行图像腐蚀，然后采用轮廓提取算法对第二攻牙图像进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点坐标。
具体地，在本发明实施例中，在获取到攻牙图像的灰度图后，对该灰度图进行局部增强处理和避位处理得到第一攻牙图像，再对该第一攻牙图像进行二值化处理得到第二攻牙图像，再然后对该第二攻牙图像进行图像腐蚀，接着采用轮廓提取算法进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点坐标，该四个定点坐标为攻牙图像中获取的定位区域，即为五金冲压件的牙孔区域。
步骤103、采用最小外接圆算法计算该定位区域的内圆圆心位置和内圆半径大小，计算该内圆半径与标准五金冲压件牙孔区域内圆半径的差值。
其中，该定位区域指五金冲压件攻牙后的牙孔区域，采用最小外接圆算法可获取该五金冲压件牙孔区域的内圆圆心位置和内圆半径大小，该内圆半径与标准五金冲压件牙孔区域内圆半径存在差值，计算可获取该差值。
步骤104、根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。
具体地，比较该差值与预置差值的大小关系，根据该大小关系再分析确定该五金冲压件存在攻牙缺陷为不良品。
进一步地，如图3所示，图3为第一实施例中步骤104的细化步骤的流程示意图，根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号具体包括步骤301至步骤306：
步骤301、判断该差值是否超过预置差值；
步骤302、若该差值超过预置差值，则确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号；
步骤303、若该差值未超过该预置差值，则扩展该定位区域的内圆半径，得到检测圆；
步骤304、将定位区域的内圆圆内部分和检测圆圆外部分的像素值均设置为零，计算该定位区域的内圆与该检测圆之间的圆环部分的像素点的数量；
步骤305、判断像素点的数量是否在预置范围内；
步骤306、若不在预置范围内，则确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号。
具体地，先判断该差值是否超过该预置差值，若判断该差值大于预置差值，则确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。若判断该差值小于或等于预置差值，则进行下一步操作，扩展该定位区域的内圆半径，得到检测圆，将定位区域的内圆圆内部分和检测圆圆外部分的像素值均设置为零，计算该定位区域的内圆与该检测圆之间的圆环部分的像素点的数量，判断像素点的数量是否在预置范围内，若不在预置范围内，则确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号，此操作提高了五金冲压件不良品的筛选率。
进一步地，该检测方法还包括：
若采用固定阈值、轮廓提取算法和最小外接矩形算法不能提取到该攻牙图像中牙孔的定位区域，则确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。
其中，不能获取到该攻牙图像牙孔的定位区域是指不能获取到该五金冲压件牙孔区域的坐标。
从图1提供的检测方法可知，该方法利用固定阈值、轮廓提取算法和最小外接矩形算法提取攻牙图像中牙孔的定位区域，通过计算该定位区域内圆半径的大小与标准五金冲压件牙孔区域内圆半径的差值，根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号，由此将五金冲压件的不良品检测出来。采用该方法检测攻牙缺陷，提高牙孔检测的精度，且采用该牙孔检测方法只需获取五金冲压件的攻牙图像，五金冲压件的规格大小不影响该方法的使用。
请参阅图4，为本发明第二实施例提供的牙孔检测装置的结构示意图，该牙孔检测装置包括采集模块401、定位模块402、计算模块403和确定模块404：
采集模块401、用于采集五金冲压件的攻牙图像并将该攻牙图像转换成灰度图，该攻牙图像为相机拍摄的五金冲压件攻牙后牙孔的图像。
具体地，在本发明实施例中，相机拍摄五金冲压件攻牙后牙孔的图像，采集模块401获取该五金冲压件攻牙后牙孔的图像，即为获取该五金冲压件的攻牙图像，在获取该五金冲压件的攻牙图像后将该攻牙图像转换成灰度图，以便进一步地对该攻牙图像进行处理。
定位模块402、用于采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像中牙孔的定位区域。
其中，采用固定阈值、轮廓提取算法和最小外接矩形算法提取该攻牙图像的定位区域的目的是提取到该五金冲压件的牙孔位置。
如图5所示，图5为第二实施例中定位模块的细化结构的示意图，定位模块402具体包括第一处理模块501、第二处理模块502和提取模块503：
第一处理模块501、用于对攻牙图像的灰度图进行局部增强处理和避位处理，得到第一攻牙图像。
其中，第一攻牙图像为已进行局部增强处理和避位处理的攻牙图像，第一处理模块501遍历该攻牙图像的像素值，将大于预置指定值的像素值设置为预置指定置，将小于该预置指定值的像素值均设置为零。
具体地，第一处理模块501预先设置像素的一个指定值，遍历该灰度图像的图像区域的像素值，将大于该指定值的像素值均设置为指定值，将小于该指定值的像素值均设置为零，以完成对攻牙图像的灰度图进行局部增强处理。
第二处理模块502、用于对该第一攻牙图像进行图像二值化处理，得到第二攻牙图像。
其中，第二攻牙图像为己进行二值化处理的攻牙图像。
提取模块503、用于对该第二攻牙图像进行图像腐蚀，然后采用轮廓提取算法对第二攻牙图像进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点坐标。
具体地，在本发明实施例中，该装置在获取到攻牙图像的灰度图后，第一处理模块501对该灰度图进行局部增强处理和避位处理得到第一攻牙图像，第二处理模块502再对该第一攻牙图像进行二值化处理得到第二攻牙图像，再然后提取模块503对该第二攻牙图像进行图像腐蚀，接着采用轮廓提取算法进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点坐标，该四个定点坐标为攻牙图像中获取的定位区域，即为五金冲压件的牙孔区域。
计算模块403、用于采用最小外接圆算法计算该定位区域的内圆圆心位置和内圆半径大小，计算该内圆半径与标准五金冲压件牙孔区域内圆半径的差值。
其中，该定位区域指五金冲压件攻牙后的牙孔区域，采用最小外接圆算法可获取该五金冲压件牙孔区域的内圆圆心位置和内圆半径大小，该内圆半径与标准五金冲压件牙孔区域内圆半径存在差值，计算可获取该差值。
确定模块404、用于根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。
具体地，比较该差值与预置差值的大小关系，根据该大小关系再分析确定该五金冲压件存在攻牙缺陷为不良品。
进一步地，如图6所示，图6为第二实施例中确定模块的细化结构的示意图，确定模块404具体包括第一判断模块601、第一输出模块602、扩展模块603、设置计算模块604、第二判断模块605和第二输出模块606：
第一判断模块601、用于判断该差值是否超过预置差值；
第一输出模块602、用于在该差值超过预置差值时，确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号；
扩展模块603、用于在该差值未超过该预置差值时，扩展该定位区域的内圆半径，得到检测圆；
设置计算模块604、用于将定位区域的内圆圆内部分和检测圆圆外部分的像素值均设置为零，计算该定位区域的内圆与该检测圆之间的圆环部分的像素点的数量；
第二判断模块605、用于判断像素点的数量是否在预置范围内；
第二输出模块606、用于不在预置范围内时，确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号。
具体地，第一判断模块601先判断该差值是否超过该预置差值，若判断该差值大于预置差值，则第一输出模块602确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。若第一判断模块601判断该差值小于或等于预置差值，则进行下一步操作，扩展模块603扩展该定位区域的内圆半径，得到检测圆，设置计算模块604将定位区域的内圆圆内部分和检测圆圆外部分的像素值均设置为零，计算该定位区域的内圆与该检测圆之间的圆环部分的像素点的数量，第二判断模块605判断像素点的数量是否在预置范围内，若不在预置范围内时，第二输出模块606确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号，此操作提高了五金冲压件不良品的筛选率。
进一步地，该牙孔检测装置还包括：
确认模块，用于在采用固定阈值、轮廓提取算法和最小外接矩形算法不能提取到该攻牙图像中牙孔的定位区域时，确定该五金冲压件存在攻牙缺陷，输出该五金冲压件为不良品的信号。
其中，不能获取到该攻牙图像牙孔的定位区域是指不能获取到该五金冲压件牙孔区域的坐标。
从图4提供的检测装置可知，该装置的定位模块利用固定阈值、轮廓提取算法和最小外接矩形算法提取攻牙图像中牙孔的定位区域，计算模块通过计算该定位区域内圆半径的大小与标准五金冲压件牙孔区域内圆半径的差值，确定模块根据该差值与预置差值大小关系来分析确定该五金冲压件存在攻牙缺陷，输出五金冲压件为不良品的信号，由此将五金冲压件的不良品检测出来。采用该装置检测攻牙缺陷，提高牙孔检测的精度，且采用该牙孔检测装置只需获取五金冲压件的攻牙图像，五金冲压件的规格大小不影响该方法的使用。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备（可以是个人计算机，服务器，或者网络设备等）执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、磁碟或者光盘等各种可以存储程序代码的介质。
需要说明的是，对于前述的各方法实施例，为了简便描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其它顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定都是本发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其它实施例的相关描述。
以上为对本发明所提供的一种牙孔检测方法及装置的描述，对于本领域的技术人员，依据本发明实施例的思想，在具体实施方式及应用范围上均会有改变之处，综上，本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种牙孔检测方法，其特征在于，所述方法包括：
    采集五金冲压件的攻牙图像并将所述攻牙图像转换成灰度图，所述攻牙图像为相机拍摄的所述五金冲压件攻牙后牙孔的图像；
    采用固定阈值、轮廓提取算法和最小外接矩形算法提取所述攻牙图像中所述牙孔的定位区域；
    采用最小外接圆算法计算所述定位区域的内圆圆心位置和内圆半径大小，计算所述内圆半径与标准五金冲压件牙孔区域内圆半径的差值；
    根据所述差值与预置差值大小关系来分析确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述差值与预置差值大小关系来分析确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号的步骤包括：判断所述差值是否超过预置差值；
    若所述差值超过所述预置差值，则确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号；
    若所述差值未超过所述预置差值，则扩展所述定位区域的内圆半径，得到检测圆；将所述定位区域的内圆圆内部分和所述检测圆圆外部分的像素值均设置为零，计算所述定位区域的内圆与所述检测圆之间的圆环部分的像素点的数量；判断所述像素点的数量是否在预置范围内；若不在预置范围内，则确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
  3. 根据权利要求1所述的方法，其特征在于，所述采用固定阈值、轮廓提取算法和最小外接矩形算法提取所述攻牙图像中所述牙孔的定位区域的步骤具体包括:
    对所述攻牙图像的灰度图进行图像局部增强处理和避位处理，得到第一攻牙图像；
    对所述第一攻牙图像进行图像二值化处理，得到第二攻牙图像；
    对所述第二攻牙图像进行图像腐蚀，然后采用轮廓提取算法对所述第二攻牙图像进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点的坐标。
  4. 根据权利要求3所述的方法，其特征在于，所述对所述攻牙图像的灰度图进行图像局部增强处理和避位处理，得到第一攻牙图像的步骤具体包括：
    遍历所述攻牙图像的牙孔区域的像素值，将大于预置指定值的像素值设置为所述预置指定值，将小于所述预置指定值的像素值均设置为零。
  5. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    若采用固定阈值、轮廓提取算法和最小外接矩形算法不能获取到所述攻牙图像中所述牙孔的定位区域，则确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
  6. 一种牙孔检测装置，其特征在于，所述装置包括：
    采集模块，用于采集五金冲压件的攻牙图像并将所述攻牙图像转换成灰度图，所述攻牙图像为相机拍摄的所述五金冲压件攻牙后牙孔的图像；
    定位模块，用于采用固定阈值、轮廓提取算法和最小外接矩形算法提取所述攻牙图像中所述牙孔的定位区域；
    计算模块，用于采用最小外接圆算法计算所述定位区域的内圆圆心位置和半径大小，计算所述内圆半径与标准五金冲压件牙孔区域内圆半径的差值；
    确定模块，用于根据所述差值是否超过预置差值确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
  7. 根据权利要求6所述的装置，其特征在于，所述确定模块还包括：
    第一判断模块，用于判断所述差值是否超过预置差值；
    第一输出模块，用于在所述差值超过所述预置差值时，确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号；
    扩展模块，用于在所述差值未超过所述预置差值时，扩展所述定位区域的内圆半径，得到检测圆；
    设置计算模块，用于将所述定位区域的内圆圆内部分和所述检测圆圆外部分的像素值均设置为零，计算所述定位区域的内圆与所述检测圆之间的圆环部分的像素点的数量；
    第二判断模块，用于判断所述像素点的数量是否在预置范围内；
    第二输出模块，用于若不在预置范围内，则确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
  8. 根据权利要求6所述的装置，其特征在于，所述定位模块具体包括：
    第一处理模块，用于对所述攻牙图像的灰度图进行图像局部增强处理和避位处理，得到第一攻牙图像；
    第二处理模块，用于对所述第一攻牙图像进行图像二值化处理，得到第二攻牙图像；
    提取模块，用于对所述第二攻牙图像进行图像腐蚀，然后采用轮廓提取算法对所述第二攻牙图像进行图像轮廓检测，并对面积最大的轮廓采用最小外接四边形拟合处理，得到外接四边形四个定点的坐标。
  9. 根据权利要求8所述的装置，其特征在于，所述第一处理模块具体包括：
    设置模块，用于遍历所述攻牙图像的牙孔区域的像素值，将大于所述预置指定值的像素值设置为预置指定值，将小于所述预置指定值的像素值均设置为零。
  10. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    确认模块，用于在采用固定阈值、轮廓提取算法和最小外接矩形算法不能获取到所述攻牙图像中所述牙孔的定位区域时，确定所述五金冲压件存在攻牙缺陷，输出所述五金冲压件为不良品的信号。
PCT/CN2018/090872 2018-03-30 2018-06-12 一种牙孔检测方法及装置 WO2019184094A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810295602.2A CN108550142A (zh) 2018-03-30 2018-03-30 一种牙孔检测方法及装置
CN201810295602.2 2018-03-30

Publications (1)

Publication Number Publication Date
WO2019184094A1 true WO2019184094A1 (zh) 2019-10-03

Family

ID=63514176

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/090872 WO2019184094A1 (zh) 2018-03-30 2018-06-12 一种牙孔检测方法及装置

Country Status (2)

Country Link
CN (1) CN108550142A (zh)
WO (1) WO2019184094A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI825924B (zh) * 2022-08-16 2023-12-11 榮昌科技股份有限公司 偵測螺絲孔位的裝置及偵測方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112184639B (zh) * 2020-09-15 2024-03-29 佛山(华南)新材料研究院 圆孔检测方法、装置、电子设备及存储介质
CN112719805A (zh) * 2020-12-21 2021-04-30 四川科思精密模具有限公司 一种锥度螺纹加工方法

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5214712A (en) * 1990-09-11 1993-05-25 Matsushita Electric Industrial Co., Ltd. Pattern inspection system for inspecting defect of land pattern for through-hole on printed board
JP2000180374A (ja) * 1998-12-15 2000-06-30 Matsushita Electric Ind Co Ltd 欠陥検出方法
CN101532926A (zh) * 2008-12-12 2009-09-16 齐齐哈尔华工机床制造有限公司 冲击试样自动加工装置在线检测视觉系统及其图像处理方法
CN102128589A (zh) * 2010-01-20 2011-07-20 中国科学院自动化研究所 一种在轴孔装配中零件内孔方位误差的校正方法
CN103093222A (zh) * 2011-11-07 2013-05-08 鸿富锦精密工业（深圳）有限公司 主板圆孔定位方法及系统
CN104897062A (zh) * 2015-06-26 2015-09-09 北方工业大学 一种零件异面平行孔形位偏差的视觉测量方法及装置
CN105787939A (zh) * 2016-02-26 2016-07-20 南京理工大学 一种用于pcb板圆孔的快速定位检测方法
CN106327496A (zh) * 2016-08-26 2017-01-11 西安电子科技大学 基于aoi的pcb裸板盲孔缺陷的检测系统及方法
CN106778541A (zh) * 2016-11-28 2017-05-31 华中科技大学 一种基于视觉的多层梁中外梁孔的识别与定位方法
CN107301636A (zh) * 2017-05-17 2017-10-27 华南理工大学 一种基于高斯拟合的高密度电路板圆孔亚像素检测方法
CN107705297A (zh) * 2017-09-18 2018-02-16 华南理工大学 一种柔性电路板圆孔的阈值分割检测方法

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5214712A (en) * 1990-09-11 1993-05-25 Matsushita Electric Industrial Co., Ltd. Pattern inspection system for inspecting defect of land pattern for through-hole on printed board
JP2000180374A (ja) * 1998-12-15 2000-06-30 Matsushita Electric Ind Co Ltd 欠陥検出方法
CN101532926A (zh) * 2008-12-12 2009-09-16 齐齐哈尔华工机床制造有限公司 冲击试样自动加工装置在线检测视觉系统及其图像处理方法
CN102128589A (zh) * 2010-01-20 2011-07-20 中国科学院自动化研究所 一种在轴孔装配中零件内孔方位误差的校正方法
CN103093222A (zh) * 2011-11-07 2013-05-08 鸿富锦精密工业（深圳）有限公司 主板圆孔定位方法及系统
CN104897062A (zh) * 2015-06-26 2015-09-09 北方工业大学 一种零件异面平行孔形位偏差的视觉测量方法及装置
CN105787939A (zh) * 2016-02-26 2016-07-20 南京理工大学 一种用于pcb板圆孔的快速定位检测方法
CN106327496A (zh) * 2016-08-26 2017-01-11 西安电子科技大学 基于aoi的pcb裸板盲孔缺陷的检测系统及方法
CN106778541A (zh) * 2016-11-28 2017-05-31 华中科技大学 一种基于视觉的多层梁中外梁孔的识别与定位方法
CN107301636A (zh) * 2017-05-17 2017-10-27 华南理工大学 一种基于高斯拟合的高密度电路板圆孔亚像素检测方法
CN107705297A (zh) * 2017-09-18 2018-02-16 华南理工大学 一种柔性电路板圆孔的阈值分割检测方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI825924B (zh) * 2022-08-16 2023-12-11 榮昌科技股份有限公司 偵測螺絲孔位的裝置及偵測方法

Also Published As

Publication number Publication date
CN108550142A (zh) 2018-09-18

Similar Documents

Publication Publication Date Title
WO2019184094A1 (zh) 一种牙孔检测方法及装置
CN109544533B (zh) 一种基于深度学习的金属板缺陷检测和度量方法
US10740912B2 (en) Detection of humans in images using depth information
WO2016127736A1 (zh) 指纹重叠区域面积的计算方法及电子装置
US7978904B2 (en) Pattern inspection apparatus and semiconductor inspection system
JP7034840B2 (ja) 外観検査装置および方法
CN106441804A (zh) 解像力测试方法
CN109118476B (zh) 一种零部件边缘轮廓完整性检测方法及装置
TWI765442B (zh) 瑕疵等級判定的方法及存儲介質
CN108288274B (zh) 模具检测方法、装置以及电子设备
JP2980789B2 (ja) パターン寸法測定装置及びその方法
CN116559177A (zh) 一种缺陷检测方法、装置、设备以及存储介质
WO2018176261A1 (zh) 一种检测参数确定方法和检测装置
CN110544243A (zh) 一种ct图像小缺陷自动检出、定量及可靠性评价方法
CN109102486B (zh) 基于机器学习的表面缺陷检测方法及装置
CN107561106B (zh) 一种条痕状形貌表征参数的测量方法及装置
JP2011058926A (ja) 画像検査方法及び画像検査装置
JP2014126445A (ja) 位置合せ装置、欠陥検査装置、位置合せ方法、及び制御プログラム
CN117351017A (zh) 一种光伏钢结构组件缺陷视觉检测方法
CN115170476B (zh) 基于图像处理的印制线路板缺陷检测方法
CN109272480B (zh) 一种不相溶溶液分界线的检测方法
JP5022981B2 (ja) 荷電粒子線装置
TW201621856A (zh) 檢測顯示模組間隙寬度的方法
CN111524097B (zh) 一种两器喇叭口的检测方法、装置、存储介质及设备
CN112712791B (zh) 静音语音检测方法、装置、终端设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18912490

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27.01.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18912490

Country of ref document: EP

Kind code of ref document: A1