WO2022222467A1 - 开口圆环工件外观缺陷检测方法、系统及计算机存储介质 - Google Patents

开口圆环工件外观缺陷检测方法、系统及计算机存储介质 Download PDF

Info

Publication number
WO2022222467A1
WO2022222467A1 PCT/CN2021/132806 CN2021132806W WO2022222467A1 WO 2022222467 A1 WO2022222467 A1 WO 2022222467A1 CN 2021132806 W CN2021132806 W CN 2021132806W WO 2022222467 A1 WO2022222467 A1 WO 2022222467A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
workpiece
open ring
ring
rectangular
Prior art date
Application number
PCT/CN2021/132806
Other languages
English (en)
French (fr)
Inventor
任将
熊星
Original Assignee
苏州华兴源创科技股份有限公司
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 苏州华兴源创科技股份有限公司 filed Critical 苏州华兴源创科技股份有限公司
Publication of WO2022222467A1 publication Critical patent/WO2022222467A1/zh

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • 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
    • G06T7/60—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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the invention relates to the technical field of machine vision, in particular to a method, a system and a computer storage medium for detecting appearance defects of an open ring workpiece.
  • Metal split ring is an indispensable part in the field of automobile manufacturing and industrial equipment manufacturing. During the production and processing of the split ring, there will be many appearance defects such as; unqualified size, burrs, defects, etc. Due to the existence of these defects, the performance of the product will be affected, and even serious equipment failure safety accidents will be caused. At present, in the field of visual inspection, for circular workpieces, it is usually detected after rectangular expansion. However, due to a gap in the appearance of the open ring, there is a certain difference in the outer contour of the conventional circular workpiece. , there is no visual inspection method suitable for open ring workpieces at present.
  • the purpose of the present invention is to provide a method, system and computer storage medium for detecting the appearance defect of an open ring workpiece.
  • the invention provides a method for detecting appearance defects of an open ring workpiece, comprising the steps of:
  • a polar coordinate system is established according to the outline of the outer ring, and in the polar coordinate system, the partial mapping between the two ends of the outline of the outer ring in the image of the open ring workpiece is transformed into a rectangular expanded image;
  • obtaining an image of an open ring workpiece specifically includes:
  • preprocessing the image of the open ring workpiece to obtain the contour image of the workpiece edge specifically includes:
  • the open ring workpiece image is subjected to binarization to obtain a binarized image, and the binarized image includes a workpiece image area and a background image area;
  • the edge contour line of the workpiece image area is detected by the edge detection algorithm, and the edge contour line of the workpiece image area is drawn in the edge contour image, and the edge contour image includes the inner contour line.
  • the gray value of the pixel point in the closed frame is set to zero to obtain a separated contour image, and the separated contour image includes the inner ring contour line and the outer ring contour line which are separated from each other.
  • drawing a closed frame area including two connecting lines specifically includes:
  • the circumscribed circle of the edge contour of the workpiece image area is obtained by fitting, and the coordinates (Mr, Mc) and the radius r of the center of the circumscribed circle are obtained by calculation;
  • a circle with a radius (r-a) is drawn with the coordinate point (Mr, Mc) as the center to obtain an intermediate image, wherein 0 ⁇ a ⁇ w, w is the width value of the standard open ring workpiece;
  • the first difference output image includes a connecting line at the opening area of the opening element
  • the closed frame area is formed by enlarging the first rectangular frame.
  • a polar coordinate system is established according to the outer ring contour line, and the partial mapping between the two ends of the outer ring contour line in the open ring workpiece image in the polar coordinate system is transformed into "Rectangular Expand Image” specifically includes:
  • the method also includes the steps of establishing a standard image:
  • an edge contour of the rectangular expanded image is detected by an edge detection algorithm, and a minimum circumscribed rectangle of the edge contour is drawn to obtain a second rectangular frame;
  • the second difference output image includes the defect area of the opening element
  • the method also includes:
  • the width of the expanded workpiece image area is measured and compared with the width of the standard open ring workpiece to determine whether the open ring workpiece is qualified.
  • the present invention also provides an appearance defect detection system for an open ring workpiece, comprising:
  • a position identification module configured to identify the running position of the open ring workpiece in real time
  • An image acquisition module including a camera and a light source device, is configured to capture and capture an image of the annular workpiece
  • the detection control module includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the steps of the above-mentioned method for detecting an appearance defect of an open ring workpiece are performed;
  • the sorting module is configured to sort the open ring workpieces into categories according to the detection results output by the open ring workpiece appearance defect detection method.
  • the present invention also provides a computer storage medium, in which a computer program is stored, and when the computer program runs, the device where the computer storage medium is located executes the steps of the above-mentioned method for detecting an appearance defect of an open ring workpiece.
  • the present invention proposes a visual technology detection method suitable for an open ring workpiece. It is convenient to perform defect detection by rectangular expansion, so that the defect detection of the open ring workpiece can be automated, save labor costs, and greatly improve the detection accuracy.
  • FIG. 1 is a flow chart showing the steps of a method for detecting an appearance defect of an open ring workpiece according to an embodiment of the present invention.
  • 2a is a schematic diagram of an image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • Fig. 2 b is the schematic diagram of the defective open ring workpiece image obtained by performing one step in the open ring workpiece appearance detection method in one embodiment of the present invention
  • 3a is a schematic diagram of a binarized image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • 3b is a schematic diagram of a binarized image of a defective open ring workpiece obtained by performing one step in a method for detecting the appearance of an open ring workpiece in an embodiment of the present invention
  • FIG. 4 is a schematic diagram of an edge contour image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 5 is a schematic diagram of an intermediate image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 6 is a schematic diagram of a first difference output image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 7 is an enlarged schematic view of a first difference output image including a first rectangular frame of a defect-free open-ring workpiece obtained by performing a step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 8 is a schematic diagram of an edge contour image including a closed frame area of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 9 is a schematic diagram of a separated contour image of a defect-free open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • 10a is a schematic diagram of a rectangular expanded image of a defect-free open ring obtained by performing one step in a method for detecting the appearance of an open ring workpiece in an embodiment of the present invention
  • 10b is a schematic diagram of a rectangular expanded image of a defective open-ring workpiece obtained by performing one step in a method for detecting the appearance of an open-ring workpiece in an embodiment of the present invention
  • FIG. 11 is a schematic diagram of a standard image obtained by performing one step of a method for detecting the appearance of an open ring workpiece in an embodiment of the present invention
  • FIG. 12 is a schematic diagram of a defect image of a defective open ring workpiece obtained by performing one step of the method for detecting the appearance of an open ring workpiece according to an embodiment of the present invention.
  • the term used to describe the relative position in space such as “upper”, “lower”, “rear”, “front”, etc., is used to describe one unit or feature shown in the drawings relative to another A unit or feature relationship.
  • the term spatially relative position may include different orientations of the device in use or operation other than the orientation shown in the figures. For example, if the device in the figures is turned over, elements described as “below” or “above” other elements or features would then be oriented “below” or “above” the other elements or features.
  • the exemplary term “below” can encompass both a spatial orientation of below and above.
  • the present invention provides a method for detecting the appearance defect of an open ring workpiece, comprising the steps of:
  • the open ring workpiece is a circular workpiece with a gap, and the surface shape is roughly "C" shape.
  • step S1 includes the following steps:
  • the camera is an industrial CCD (Charge-Coupled Device, charge-coupled device) camera, which usually takes a grayscale image. If it is a color camera, after taking the image of the open ring workpiece, it also includes the steps of: graying the open ring workpiece image. Scale processing.
  • CCD Charge-Coupled Device, charge-coupled device
  • the image of the defect-free open ring workpiece and the image of the defective open ring workpiece obtained by shooting are respectively, wherein the workpiece is usually white in the figure or has a relatively gray value.
  • the pixels in the defect areas such as burrs and defects are darker than those in the non-defective area.
  • Background parts such as conveyor belts are usually black or gray in the picture. Dark gray with a small degree value.
  • S2 Preprocess the image of the open ring workpiece to obtain the contour image of the workpiece edge.
  • step S2 includes the following steps:
  • S21 Perform binarization processing on the open ring workpiece image to obtain a binarized image, and the binarized image includes a workpiece image area and a background image area.
  • the image of the open ring workpiece obtained by shooting is subjected to binarization processing and converted into a black and white binary image, so as to facilitate the identification of clear edge contour lines.
  • the binarized images are obtained after binarizing FIG. 2 a and FIG. 2 b respectively.
  • S22 Detecting the edge contour line of the workpiece image area in the binarized image through the edge detection algorithm, and drawing the edge contour line of the workpiece image area in the edge contour image, and the edge contour image includes the inner ring contour line and the outer ring contour line. and two connecting lines connecting the endpoints of the inner ring contour line with the outer ring contour line endpoints.
  • the difference between the workpiece image area and the background image area in the binarized image is obvious, and the edge contour of the workpiece image area can be identified by conventional edge detection algorithms, which is equivalent to the actual edge contour of the open ring workpiece.
  • FIG. 4 it is an edge contour image obtained by performing edge detection and identification in FIG. 3 a .
  • step S3 the two connecting lines are removed, so as to separate the outer ring contour line and the inner ring contour line, which specifically includes the steps:
  • S32 Set the gray value of the pixel point in the closed frame to zero to obtain a separated contour image, and the separated contour image includes an inner ring contour line and an outer ring contour line that are separated from each other.
  • step S31 specifically includes steps:
  • S312 Draw a circle with a radius (r-a) in the binarized image with the coordinate point (Mr, Mc) as the center to obtain an intermediate image, where 0 ⁇ a ⁇ w, w is the width value of the standard open ring workpiece.
  • a is set to a value greater than the manufacturing tolerance value to ensure that the position of the circle is between the inner ring contour and the outer ring contour.
  • FIG. 5 it is an intermediate image obtained after drawing the circle in FIG. 3a.
  • S313 Perform a subtraction operation on the corresponding pixel points between the intermediate image and the binarized image to obtain a first difference output image, where the first difference output image includes a connecting line at the opening area of the opening element.
  • the first difference output image is obtained by subtracting the corresponding pixel points in FIG. 5 and FIG. 3 a .
  • S314 Detect the outline of the tie line, fit and draw the minimum circumscribed rectangle of the outline of the tie line, and obtain a first rectangular frame.
  • FIG. 7 it is an enlarged schematic diagram of the first rectangular frame drawn in FIG. 6 .
  • S315 Enlarge the first rectangular frame to form a closed frame area.
  • the enlargement ratio of the length and width of the first rectangular frame is specifically adjusted according to the size of different open ring workpieces.
  • the enlarged first rectangular frame can just include two connecting lines in the premise of considering manufacturing tolerances. Among them, in order to reduce the impact on other areas of the open annular workpiece.
  • FIG. 8 it is the closed frame area drawn in FIG. 4
  • FIG. 9 as shown in FIG. 9 , it is a separated contour image obtained after zeroing the pixels in the closed frame area in FIG. 8 .
  • an entire edge contour line can be conveniently and accurately divided into two parts, the inner ring contour line and the outer ring contour line, so as to facilitate the subsequent image rectangle expansion steps.
  • S4 establish a polar coordinate system according to the outline of the outer ring, and transform the part of the image of the open ring workpiece between the two ends of the outline of the outer ring into a rectangular expanded image in the polar coordinate system.
  • step S4 includes steps:
  • FIG. 10a it is a rectangular expanded image of a non-defective open ring workpiece
  • FIG. 10b it is a rectangular expanded image of a defective open ring workpiece.
  • S5 Establish a standard image, compare the rectangular unfolded image and the standard image, obtain the defect area in the rectangular unfolded image, and judge whether the open ring workpiece is qualified.
  • step S5 "establishing a standard image” includes the steps:
  • the edge contour of the expanded rectangular image is detected by an edge detection algorithm, and a minimum circumscribed rectangle of the edge contour is drawn to obtain a second rectangular frame.
  • S52 Create a standard image with the same size as the expanded rectangular image, draw a second rectangular frame at a corresponding position in the standard image, and fill the second rectangular frame with pixels.
  • FIG. 11 it is a standard image filled with white pixels.
  • step S5 "comparing the expanded rectangular image and the standard image, and obtaining the defect area in the expanded rectangular image” includes the steps:
  • FIG. 12 it is a defect image obtained by subtracting the corresponding pixel points between FIG. 11 and FIG. 10 b .
  • S54 Determine whether the open ring workpiece is qualified according to the image content of the defective area of the open element.
  • the criterion for judging a qualified product can be set as no defective image, or as the number of pixels in the defective image area is less than a preset threshold.
  • Unqualified split ring workpieces are classified into different defective products according to the shape of the defect image.
  • the present invention also provides an appearance defect detection system for an open ring workpiece, comprising:
  • the position recognition module is configured to recognize the running position of the split ring workpiece in real time.
  • An image acquisition module including a camera and a light source device, is configured to capture and capture an image of the annular workpiece
  • the detection control module includes a memory and a processor, the memory stores a computer program that can be run on the processor, and when the processor executes the program, the steps of the above-mentioned method for detecting the appearance defect of an open ring workpiece are realized.
  • the sorting module is configured to sort the open ring workpieces into categories according to the detection results output by the open ring workpiece appearance defect detection method.
  • the open ring workpieces are sorted into qualified products and unqualified products, and further, according to the identification results, the unqualified products can also be sorted into different types of defective products.
  • the present invention also provides a computer storage medium, in which a computer program is stored, and when the computer program runs, the device where the computer storage medium is located executes the steps of the above-mentioned method for detecting an appearance defect of an open ring workpiece.
  • the present invention removes the connection line between the ring contour and the outer ring contour in the inner edge contour image of the open ring workpiece, so that the image is convenient for rectangular expansion and defect detection, and makes the defect detection of the open ring workpiece. It can be automated, save labor costs, and greatly improve the detection accuracy.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

本发明提供一种开口圆环工件外观缺陷检测方法、系统及计算机存储介质，所述方法包括步骤：获取开口圆环工件图像；进行预处理得到工件边缘轮廓图像；清除内环轮廓线端点与外环轮廓线端点之间的连接线，并识别外环轮廓线两端点；根据外环轮廓线建立极坐标系，并将位于外环轮廓线两端点之间的部分映射变换为矩形展开图像；比较矩形展开图像与标准图像，获取缺陷区域，并判断是否合格。检测方法使得瑕疵品检测能够自动化进行，节省人力成本，并大幅提高检测准确率。

Description

开口圆环工件外观缺陷检测方法、系统及计算机存储介质
本申请要求了申请日为2021年04月22日，申请号为202110437890.2，发明名称为“开口圆环工件外观缺陷检测方法、系统及计算机存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及机器视觉技术领域，具体地涉及一种开口圆环工件外观缺陷检测方法、系统及计算机存储介质。
背景技术
金属开口圆环是一种在汽车制造、工业设备制造领域不可或缺的零部件。在开口圆环的生产加工过程中会造成很多外观缺陷如；尺寸不合格、毛刺、缺损等。由于这些缺陷的存在，会影响产品的性能，严重的甚至会造成设备故障安全事故等。目前在视觉检测领域，针对圆环形工件，通常对其进行矩形展开后，再对其进行检测，然而由于开口圆环外观上存在一个缺口，其与常规圆环形工件在外轮廓上存在一定差异，目前尚未有适配于开口圆环工件的视觉检测方法。
发明内容
本发明的目的在于提供一种开口圆环工件外观缺陷检测方法、系统及计算机存储介质。
本发明提供一种开口圆环工件外观缺陷检测方法，包括步骤：
获取开口圆环工件图像；
对所述开口圆环工件图像进行预处理得到工件边缘轮廓图像；
清除所述工件边缘轮廓图像中内环轮廓线端点与外环轮廓线端点之间的连接线，得到分离的所述外环轮廓线和所述内环轮廓线，并识别所述外环轮廓线两端点；
根据所述外环轮廓线建立极坐标系，并在极坐标系内将所述开口圆环工件图像中位于所述外环轮廓线两端点之间的部分映射变换为矩形展开图像；
比较所述矩形展开图像与标准图像，获取所述矩形展开图像内缺陷区域，并判断所述开口圆环工件是否合格。
作为本发明的进一步改进，“获得开口圆环工件图像”具体包括：
控制相机于垂直方向获取所述开口圆环工件表面图像。
作为本发明的进一步改进，“对所述开口圆环工件图像进行预处理得到工件边缘轮廓图像”具体包括：
对所述开口圆环工件图像进行二值化处理得到二值化图像，所述二值化图像内包括 工件图像区域和背景图像区域；
于所述二值化图像内通过边缘检测算法检测得到所述工件图像区域边缘轮廓线，并将所述工件图像区域边缘轮廓线绘制于边缘轮廓图像内，所述边缘轮廓图像内包括所述内环轮廓线、所述外环轮廓线以及连接所述内环轮廓线端点与所述外环轮廓线端点的两条所述连接线。
作为本发明的进一步改进，“清除所述工件边缘轮廓图像中内环轮廓线端点与外环轮廓线端点之间的连接线，得到分离的所述外环轮廓线和所述内环轮廓线”，具体包括：
在所述边缘轮廓图像内绘制囊括两条所述连接线的闭合框区；
将所述闭合框区内像素点灰度值置零，得到分离轮廓图像，所述分离轮廓图像内包括相互分离的所述内环轮廓线和所述外环轮廓线。
作为本发明的进一步改进，“绘制囊括两条所述连接线的闭合框区”具体包括：
在所述边缘轮廓图像内，拟合得到所述工件图像区域边缘轮廓的外接圆，并计算得到所述外接圆的圆心的坐标(Mr，Mc)与半径r；
在所述二值化图像内以坐标点(Mr，Mc)为圆心绘制半径为(r-a)的圆得到中间图像，其中，0≤a≤w，w为标准开口圆环工件的宽度值；
将所述中间图像和所述二值化图像之间对应像素点进行减法运算，得到第一差值输出图像，所述第一差值输出图像内包括所述开口元件开口区域处的联络线；
检测所述联络线轮廓，拟合并绘制所述联络线轮廓的最小外接矩形，得到第一矩形框；
放大所述第一矩形框形成所述闭合框区。
作为本发明的进一步改进，“根据所述外环轮廓线建立极坐标系，并在极坐标系内所述开口圆环工件图像中位于所述外环轮廓线两端点之间的部分映射变换为矩形展开图像”具体包括：
在所述二值化图像和所述分离轮廓图像内以坐标点(Mr，Mc)为坐标中心点建立极坐标系；
在所述分离轮廓图像内，计算所述外环轮廓线两个端点与所述坐标中心点的角度theta1和theta2；
于所述二值化图像内，将极坐标系中位于角度theta1和theta2之间的像素点进行坐标变换，进行矩形展开，得到矩形展开图像，所述矩形展开图像内包括呈矩形的展开后工件图像区域。
作为本发明的进一步改进，所述方法还包括建立标准图像步骤：
在所述矩形展开图像内，通过边缘检测算法检测得到所述矩形展开图像的边缘轮廓，并绘制所述边缘轮廓的最小外接矩形，得到第二矩形框；
创建一张与所述矩形展开图像大小一致的标准图像，在所述标准图像内相应位置绘制所述第二矩形框，并在所述第二矩形框内填充像素点。
作为本发明的进一步改进，“比较所述矩形展开图像与标准图像，获取所述矩形展开图像内缺陷区域，并判断所述开口圆环工件是否合格”具体包括：
将标准图像与所述矩形展开图像之间对应像素点进行减法运算，得到第二差值输出图像，所述第二差值输出图像内包括所述开口元件的缺陷区域；
根据所述开口元件的缺陷区域图像内容判断开口圆环工件是否合格。
作为本发明的进一步改进，所述方法还包括：
在所述矩形展开图像内，测量所述展开后工件图像区域的宽度，并与标准开口圆环工件宽度比较，判断所述开口圆环工件是否合格。
本发明还提供一种开口圆环工件外观缺陷检测系统，包括：
位置识别模块，被配置为用于实时识别所述开口圆环工件运行位置；
图像采集模块，包括相机和光源装置，被配置用于拍摄采集圆环工件图像；
检测控制模块，包括存储器和处理器，所述存储器存储有可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实上述开口圆环工件外观缺陷检测方法的步骤；
分拣模块，被配置用于根据开口圆环工件外观缺陷检测方法输出的检测结果，将开口圆环工件进行类别分拣。
本发明还提供一种计算机存储介质，其中存储有计算机程序，并且所述计算机程序运行时导致所述计算机存储介质的所在设备执行上述开口圆环工件外观缺陷检测方法的步骤。
本发明的有益效果是：本发明提出一种适配于开口圆环工件的视觉技术检测方法，通过清除开口圆环工件内边缘轮廓图像中环轮廓和外环轮廓之间的连线，使得其图像便于进行矩形展开而进行缺陷检测，使得开口圆环工件的瑕疵品检测能够自动化进行，节省人力成本，并大幅提高检测准确率。
附图说明
图1是本发明一实施方式中的开口圆环工件外观缺陷检测方法步骤流程图。
图2a是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件图像的示意图；
图2b是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的有缺陷 开口圆环工件图像的示意图；
图3a是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的二值化图像的示意图；
图3b是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的有缺陷开口圆环工件的二值化图像的示意图；
图4是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的边缘轮廓图像的示意图；
图5是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的中间图像的示意图；
图6是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的第一差值输出图像的示意图；
图7是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的包含第一矩形框的第一差值输出图像的放大示意图；
图8是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的包含闭合框区的边缘轮廓图像的示意图；
图9是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环工件的分离轮廓图像的示意图；
图10a是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的无缺陷开口圆环的矩形展开图像的示意图；
图10b是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的有缺陷开口圆环工件的矩形展开图像的示意图；
图11是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的标准图像的示意图；
图12是本发明一实施方式中开口圆环工件外观检测方法执行一步骤得到的有缺陷开口圆环工件的缺陷图像的示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请具体实施方式及相应的附图对本申请技术方案进行清楚、完整地描述。显然，所描述的实施方式仅是本申请一部分实施方式，而不是全部的实施方式。基于本申请中的实施方式，本领域普通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方式，都属于本申请保护 的范围。
下面详细描述本发明的实施方式，实施方式的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施方式是示例性的，仅用于解释本发明，而不能理解为对本发明的限制。
为方便说明，本文使用表示空间相对位置的术语来进行描述，例如“上”、“下”、“后”、“前”等，用来描述附图中所示的一个单元或者特征相对于另一个单元或特征的关系。空间相对位置的术语可以包括设备在使用或工作中除了图中所示方位以外的不同方位。例如，如果将图中的装置翻转，则被描述为位于其他单元或特征“下方”或“上方”的单元将位于其他单元或特征“下方”或“上方”。因此，示例性术语“下方”可以囊括下方和上方这两种空间方位。
如图1所示，本发明提供一种开口圆环工件外观缺陷检测方法，包括步骤：
S1：获取开口圆环工件图像。
开口圆环工件为存在一个缺口的圆环形工件，表面形状大致呈“C”型。
具体的，步骤S1包括以下步骤：
S11：检测到开口圆环工件位置与相机位置处于同一垂直线，同时，打开位于设置于拍摄位置上方的光源。
S12：控制相机于垂直方向获取开口圆环工件表面图像。
相机为工业CCD(Charge-Coupled Device，电荷耦合元件)相机，通常拍摄得到灰度图像，如果为彩色相机，在拍摄得到开口圆环工件图像后，还包括步骤：将开口圆环工件图像进行灰度化处理。
示例性的，如图2a和图2b所示，分别为拍摄得到的无缺陷开口圆环工件图像和有缺陷的开口圆环工件图像，其中，工件在图中通常呈白色或者呈灰度值较大的亮灰色，当开口圆环工件表面存在缺陷时，其上的毛刺、缺损等缺陷区域像素点相比于无缺陷区域其颜色更深，诸如传送带等背景部分在图中通常呈黑色或者呈灰度值较小的深灰色。
S2：对开口圆环工件图像进行预处理得到工件边缘轮廓图像。
具体的，步骤S2包括以下步骤：
S21：对开口圆环工件图像进行二值化处理得到二值化图像，二值化图像内包括工件图像区域和背景图像区域。
将拍摄得到的开口圆环工件图像进行二值化处理，转换为黑白二值图像，以便于识别得到清晰的边缘轮廓线。
设置一预设像素灰度值为阈值，或通过目前常用算法计算阈值，将开口环形工件图 像内像素点灰度值大于阈值的设为255，小于阈值的设为0，由于在图像中开口圆形工件无缺陷部分、有缺陷部分个背景具有明显颜色差异，从而可将图内像素点灰度划分为工件图像区域和背景图像区域，其中工件图像区域呈白色，当存在缺陷时，工件图像区域上分布有呈黑色的缺陷痕迹，背景图像区域呈黑色。
示例性的，如图3a和图3b所示，为分别将图2a图2b进行二值化处理后得到的二值化图像。
S22：于二值化图像内通过边缘检测算法检测得到工件图像区域边缘轮廓线，并将工件图像区域边缘轮廓线绘制于边缘轮廓图像内，边缘轮廓图像内包括内环轮廓线、外环轮廓线以及连接内环轮廓线端点与外环轮廓线端点的两条连接线。
二值化图像中工件图像区域与背景图像区域差异明显，可以通过常规边缘检测算法识别得到工件图像区域的边缘轮廓线，即相当于开口圆环工件的实际边缘轮廓线。
示例性的，如图4所示，为将图3a进行边缘检测识别后得到的边缘轮廓图像。
S3：清除工件边缘轮廓图像中内环轮廓线端点与外环轮廓线端点之间的连接线，得到分离的外环轮廓线和内环轮廓线，并识别外环轮廓线两端点。
为便于进行识别和定位等目的，需要在后续步骤中需要将呈环形的工件图像区域展开为矩形，其所必需的条件为：找到外环轮廓线的两个端点。但在一个整体的边缘轮廓线中找到外环轮廓线的端点较为困难，故在步骤S3中将两条连线去除，从而使外环轮廓线和内环轮廓线分开，其具体包括步骤：
S31：在边缘轮廓图像内绘制囊括两条连接线的闭合框区。
S32：将闭合框区内像素点灰度值置零，得到分离轮廓图像，分离轮廓图像内包括相互分离的内环轮廓线和外环轮廓线。
具体的，在本实施方式中，步骤S31具体包括步骤：
S311：在边缘轮廓图像内，拟合得到工件图像区域边缘轮廓的外接圆，并计算得到外接圆的圆心的坐标(Mr，Mc)与半径r。
S312：在二值化图像内以坐标点(Mr，Mc)为圆心绘制半径为(r-a)的圆得到中间图像，其中，0≤a≤w，w为标准开口圆环工件的宽度值。
这里，考虑到工件尺寸在实际生产中存在一定制造公差，优选的，将a设置为大于制造公差值的一个数值，以保证所述圆的位置处于内环轮廓和外环轮廓之间。
示例性的，如图5所示，为在图3a中绘制圆后得到的中间图像。
S313：将中间图像和二值化图像之间对应像素点进行减法运算，得到第一差值输出图像，第一差值输出图像内包括开口元件开口区域处的联络线。
示例性的，如图6所示，为将图5和图3a对应像素点进行减法运算后得到的第一差值输出图像。
S314：检测联络线轮廓，拟合并绘制联络线轮廓的最小外接矩形，得到第一矩形框。
示例性的，如图7所示，为在图6中绘制的第一矩形框的放大示意图。
S315：放大第一矩形框形成闭合框区。
这里，根据不同开口圆环工件的尺寸具体调整第一矩形框长和宽的放大比例，优选的，放大后的第一矩形框在考虑制造公差的前提下，能够正好将两条连线囊括于其中，以减小对开口环形工件其他区域的影响。
示例性的，如图8所示，为在图4中绘制的闭合框区，如图9所示，为将图8中闭合框区内像素点置零后得到的分离轮廓图像。
通过上述步骤S3，可以便捷且准确地将一个整体的边缘轮廓线，分割为内环轮廓线和外环轮廓线两部分，从而便于进行后续的图像矩形展开步骤。
S4：根据外环轮廓线建立极坐标系，并在极坐标系内将开口圆环工件图像中位于外环轮廓线两端点之间的部分映射变换为矩形展开图像。
具体的，步骤S4包括步骤：
S41：在二值化图像和分离轮廓图像内以坐标点(Mr，Mc)为坐标中心点建立极坐标系。
S42：在分离轮廓图像内，计算外环轮廓线两个端点与坐标中心点的角度theta1和theta2。
S43：于二值化图像内，将极坐标系中位于角度theta1和theta2之间的像素点进行坐标变换，进行矩形展开，得到矩形展开图像，矩形展开图像内包括呈矩形的展开后工件图像区域。
在二值化图像内，位于工件图像区域内的任一像素点(r，c)坐标转换后，其极坐标为(d，theta)，其中：
theta＝atan2(-(r-Mr)/(c-Mc))；
d＝sqrt((r-Mr)*(r-Mr)+(c-Mc)*(c-Mc))。
示例性的，如图10a所示，为一个无缺陷的开口圆环工件的矩形展开图像，如图10b所示，为一个存在缺陷的开口圆环工件的矩形展开图像。
S5：建立标准图像，比较矩形展开图像与标准图像，获取矩形展开图像内缺陷区域，并判断开口圆环工件是否合格。
具体的，在步骤S5中，“建立标准图像”包括步骤：
S51：在矩形展开图像内，通过边缘检测算法检测得到矩形展开图像的边缘轮廓，并绘制边缘轮廓的最小外接矩形，得到第二矩形框。
S52：创建一张与矩形展开图像大小一致的标准图像，在标准图像内相应位置绘制第二矩形框，并在第二矩形框内填充像素点。
示例性的，如图11所示，为填充白色像素点的标准图像。
进一步的，在步骤S5中，“比较矩形展开图像与标准图像，获取矩形展开图像内缺陷区域”包括步骤：
S53：将标准图像与和矩形展开图像之间对应像素点进行减法运算，得到第二差值输出图像，第二差值输出图像内包括开口元件的缺陷图像。
示例性的，如图12所示，为图11与图10b之间对应像素点进行减法运算后得到的缺陷图像。
S54：根据所述开口元件的缺陷区域图像内容判断开口圆环工件是否合格。
具体的，可根据实际需求，将合格品判断标准设置为不存在缺陷图像，或设置为缺陷图像区域像素点个数小于一预设阈值。
进一步的，在本发明一些实施方式中，还包括步骤：
根据缺陷图像的形状将不合格开口圆环工件分类为不同的缺陷产品。
进一步的，在本发明一些实施方式中，还包括步骤：
在矩形展开图像内，测量展开后工件图像区域的宽度，并与标准开口圆环工件宽度比较，判断开口圆环工件是否合格
本发明还提供一种开口圆环工件外观缺陷检测系统，包括：
位置识别模块，被配置为用于实时识别开口圆环工件运行位置。
图像采集模块，包括相机和光源装置，被配置用于拍摄采集圆环工件图像；
检测控制模块，包括存储器和处理器，存储器存储有可在处理器上运行的计算机程序，处理器执行程序时实现上述开口圆环工件外观缺陷检测方法的步骤。
分拣模块，被配置用于根据开口圆环工件外观缺陷检测方法输出的检测结果，将开口圆环工件进行类别分拣。
根据识别结果将开口圆环工件分拣为合格品和不合格品，进一步的，也可根据识别结果，将不合格品分拣为不同类别的缺陷产品。
本发明还提供一种计算机存储介质，其中存储有计算机程序，并且计算机程序运行时导致计算机存储介质的所在设备执行上述开口圆环工件外观缺陷检测方法的步骤。
综上所述，本发明通过清除开口圆环工件内边缘轮廓图像中环轮廓和外环轮廓之间 的连线，使得其图像便于进行矩形展开而进行缺陷检测，使得开口圆环工件的瑕疵品检测能够自动化进行，节省人力成本，并大幅提高检测准确率。
应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施方式中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。
上文所列出的一系列的详细说明仅仅是针对本发明的可行性实施方式的具体说明，并非用以限制本发明的保护范围，凡未脱离本发明技艺精神所作的等效实施方式或变更均应包含在本发明的保护范围之内。

Claims (11)

  1. 一种开口圆环工件外观缺陷检测方法，其特征在于，包括步骤：
    获取开口圆环工件图像；
    对所述开口圆环工件图像进行预处理得到工件边缘轮廓图像；
    清除所述工件边缘轮廓图像中内环轮廓线端点与外环轮廓线端点之间的连接线，得到分离的所述外环轮廓线和所述内环轮廓线，并识别所述外环轮廓线两端点；
    根据所述外环轮廓线建立极坐标系，并在极坐标系内将所述开口圆环工件图像中位于所述外环轮廓线两端点之间的部分映射变换为矩形展开图像；
    比较所述矩形展开图像与标准图像，获取所述矩形展开图像内缺陷区域，并判断所述开口圆环工件是否合格。
  2. 根据权利要求1所述的开口圆环工件外观缺陷检测方法，其特征在于，“获得开口圆环工件图像”具体包括：
    控制相机于垂直方向获取所述开口圆环工件表面图像。
  3. 根据权利要求2所述的开口圆环工件外观缺陷检测方法，其特征在于，“对所述开口圆环工件图像进行预处理得到工件边缘轮廓图像”具体包括：
    对所述开口圆环工件图像进行二值化处理得到二值化图像，所述二值化图像内包括工件图像区域和背景图像区域；
    于所述二值化图像内通过边缘检测算法检测得到所述工件图像区域边缘轮廓线，并将所述工件图像区域边缘轮廓线绘制于边缘轮廓图像内，所述边缘轮廓图像内包括所述内环轮廓线、所述外环轮廓线以及连接所述内环轮廓线端点与所述外环轮廓线端点的两条所述连接线。
  4. 根据权利要求3所述的开口圆环工件外观缺陷检测方法，其特征在于，“清除所述工件边缘轮廓图像中内环轮廓线端点与外环轮廓线端点之间的连接线，得到分离的所述外环轮廓线和所述内环轮廓线”，具体包括：
    在所述边缘轮廓图像内绘制囊括两条所述连接线的闭合框区；
    将所述闭合框区内像素点灰度值置零，得到分离轮廓图像，所述分离轮廓图像内包括相互分离的所述内环轮廓线和所述外环轮廓线。
  5. 根据权利要求4所述的开口圆环工件外观缺陷检测方法，其特征在于，“绘制囊括两条所述连接线的闭合框区”具体包括：
    在所述边缘轮廓图像内，拟合得到所述工件图像区域边缘轮廓的外接圆，并计算得 到所述外接圆的圆心的坐标(Mr，Mc)与半径r；
    在所述二值化图像内以坐标点(Mr，Mc)为圆心绘制半径为(r-a)的圆得到中间图像，其中，0≤a≤w，w为标准开口圆环工件的宽度值；
    将所述中间图像和所述二值化图像之间对应像素点进行减法运算，得到第一差值输出图像，所述第一差值输出图像内包括所述开口元件开口区域处的联络线；
    检测所述联络线轮廓，拟合并绘制所述联络线轮廓的最小外接矩形，得到第一矩形框；
    放大所述第一矩形框形成所述闭合框区。
  6. 根据权利要求5所述的开口圆环工件外观缺陷检测方法，其特征在于，“根据所述外环轮廓线建立极坐标系，并在极坐标系内所述开口圆环工件图像中位于所述外环轮廓线两端点之间的部分映射变换为矩形展开图像”具体包括：
    在所述二值化图像和所述分离轮廓图像内以坐标点(Mr，Mc)为坐标中心点建立极坐标系；
    在所述分离轮廓图像内，计算所述外环轮廓线两个端点与所述坐标中心点的角度theta1和theta2；
    于所述二值化图像内，将极坐标系中位于角度theta1和theta2之间的像素点进行坐标变换，进行矩形展开，得到矩形展开图像，所述矩形展开图像内包括呈矩形的展开后工件图像区域。
  7. 根据权利要求1所述的开口圆环工件外观缺陷检测方法，其特征在于，所述方法还包括建立标准图像步骤：
    在所述矩形展开图像内，通过边缘检测算法检测得到所述矩形展开图像的边缘轮廓，并绘制所述边缘轮廓的最小外接矩形，得到第二矩形框；
    创建一张与所述矩形展开图像大小一致的标准图像，在所述标准图像内相应位置绘制所述第二矩形框，并在所述第二矩形框内填充像素点。
  8. 根据权利要求1所述的开口圆环工件外观缺陷检测方法，其特征在于，“比较所述矩形展开图像与标准图像，获取所述矩形展开图像内缺陷区域，并判断所述开口圆环工件是否合格”具体包括：
    将标准图像与所述矩形展开图像之间对应像素点进行减法运算，得到第二差值输出图像，所述第二差值输出图像内包括所述开口元件的缺陷区域；
    根据所述开口元件的缺陷区域图像内容判断开口圆环工件是否合格。
  9. 根据权利要求6所述的开口圆环工件外观缺陷检测方法，其特征在于，所述方 法还包括：
    在所述矩形展开图像内，测量所述展开后工件图像区域的宽度，并与标准开口圆环工件宽度比较，判断所述开口圆环工件是否合格。
  10. 一种开口圆环工件外观缺陷检测系统，其特征在于，包括：
    位置识别模块，被配置为用于实时识别所述开口圆环工件运行位置；
    图像采集模块，包括相机和光源装置，被配置用于拍摄采集圆环工件图像；
    检测控制模块，包括存储器和处理器，所述存储器存储有可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现权利要求1-9中任意一项所述开口圆环工件外观缺陷检测方法的步骤；
    分拣模块，被配置用于根据开口圆环工件外观缺陷检测方法输出的检测结果，将开口圆环工件进行类别分拣。
  11. 一种计算机存储介质，其特征在于，其中存储有计算机程序，并且所述计算机程序运行时导致所述计算机存储介质的所在设备执行根据权利要求1-9中任意一项所述开口圆环工件外观缺陷检测方法的步骤。
PCT/CN2021/132806 2021-04-22 2021-11-24 开口圆环工件外观缺陷检测方法、系统及计算机存储介质 WO2022222467A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110437890.2A CN113139943B (zh) 2021-04-22 2021-04-22 开口圆环工件外观缺陷检测方法、系统及计算机存储介质
CN202110437890.2 2021-04-22

Publications (1)

Publication Number Publication Date
WO2022222467A1 true WO2022222467A1 (zh) 2022-10-27

Family

ID=76813608

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132806 WO2022222467A1 (zh) 2021-04-22 2021-11-24 开口圆环工件外观缺陷检测方法、系统及计算机存储介质

Country Status (2)

Country Link
CN (1) CN113139943B (zh)
WO (1) WO2022222467A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113139943B (zh) * 2021-04-22 2022-08-12 苏州华兴源创科技股份有限公司 开口圆环工件外观缺陷检测方法、系统及计算机存储介质
CN115830043B (zh) * 2023-01-09 2023-05-26 北京阿丘机器人科技有限公司 无线充磁铁的边界检测方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020049560A1 (en) * 2000-10-23 2002-04-25 Omron Corporation Contour inspection method and apparatus
CN103499590A (zh) * 2013-10-17 2014-01-08 福州大学 环形零件端面缺损检测及筛选方法及系统
CN108765378A (zh) * 2018-05-07 2018-11-06 上海理工大学 基于g代码引导下工件轮廓飞边凸起的机器视觉检测方法
CN109187581A (zh) * 2018-07-12 2019-01-11 中国科学院自动化研究所 基于视觉的成品轴承端面缺陷检测方法
CN113139943A (zh) * 2021-04-22 2021-07-20 苏州华兴源创科技股份有限公司 开口圆环工件外观缺陷检测方法、系统及计算机存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3689829A (en) * 1971-01-13 1972-09-05 Wean Ind Inc Orbital flaw detector with radially aligned fluid actuators with means to counteract centrifugal forces
JP4399068B2 (ja) * 1999-11-18 2010-01-13 本田技研工業株式会社 筒形状加工物の評価方法および評価装置
US6959108B1 (en) * 2001-12-06 2005-10-25 Interactive Design, Inc. Image based defect detection system
CN102087985B (zh) * 2009-12-03 2013-03-13 无锡华润上华半导体有限公司 晶圆缺陷的检测方法
TWI410880B (zh) * 2010-03-29 2013-10-01 Anmo Electronics Corp 與數位影像分析相關的電腦程式產品
DE102014202176B4 (de) * 2014-02-06 2015-10-22 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Verfahren zum Identifizieren einer Randkontur einer an einem Bearbeitungskopf gebildeten Öffnung und Bearbeitungsmaschine
JP6031697B1 (ja) * 2015-08-24 2016-11-24 レーザーテック株式会社 検査装置、検査方法及び半導体装置の製造方法
CN105279756B (zh) * 2015-10-19 2018-06-12 天津理工大学 基于自适应区域分割的缺口圆弧零件尺寸视觉检测方法
CN106468668B (zh) * 2016-09-28 2019-03-12 北京凯视佳光电设备有限公司 工业相机圆柱检测方法
CN106856003B (zh) * 2016-12-31 2019-06-25 南京理工大学 轴类工件侧表面缺陷检测图像的展开校正方法
CN107192716A (zh) * 2017-04-26 2017-09-22 广东工业大学 一种基于轮廓特征的工件缺陷快速检测方法
US20200064277A1 (en) * 2018-08-24 2020-02-27 GM Global Technology Operations LLC Method of detecting defects in work pieces having curved or cylindrical surfaces
CN110208384A (zh) * 2019-07-01 2019-09-06 河海大学常州校区 一种工件表面开口斜缺陷高度和倾斜角的测量方法
CN112037203A (zh) * 2020-08-31 2020-12-04 济南大学 基于复杂工件外轮廓配准的侧表面缺陷检测方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020049560A1 (en) * 2000-10-23 2002-04-25 Omron Corporation Contour inspection method and apparatus
CN103499590A (zh) * 2013-10-17 2014-01-08 福州大学 环形零件端面缺损检测及筛选方法及系统
CN108765378A (zh) * 2018-05-07 2018-11-06 上海理工大学 基于g代码引导下工件轮廓飞边凸起的机器视觉检测方法
CN109187581A (zh) * 2018-07-12 2019-01-11 中国科学院自动化研究所 基于视觉的成品轴承端面缺陷检测方法
CN113139943A (zh) * 2021-04-22 2021-07-20 苏州华兴源创科技股份有限公司 开口圆环工件外观缺陷检测方法、系统及计算机存储介质

Also Published As

Publication number Publication date
CN113139943B (zh) 2022-08-12
CN113139943A (zh) 2021-07-20

Similar Documents

Publication Publication Date Title
CN112577969B (zh) 一种基于机器视觉的缺陷检测方法以及缺陷检测系统
WO2022222467A1 (zh) 开口圆环工件外观缺陷检测方法、系统及计算机存储介质
CN101995223A (zh) 一种芯片外观检测方法及系统
WO2017067342A1 (zh) 板卡位置检测方法及装置
CN113077437B (zh) 工件质量检测方法及其系统
CN108665458A (zh) 透明体表面缺陷提取及识别方法
CN108257171A (zh) 基于光视觉的汽车雷达装配孔径检测方法
KR102027986B1 (ko) 비전 카메라를 이용한 비드 인식 장치 및 그 방법
WO2017071406A1 (zh) 金针类元件的引脚检测方法和系统
CN106546600A (zh) 一种基于机器视觉的pet瓶多角度检测方法和装置
CN106228541A (zh) 视觉检测中屏幕定位的方法及装置
KR20180115645A (ko) 2d 영상 기반의 용접 비드 인식 장치 및 그것을 이용한 그을음 제거 방법
CN113838043A (zh) 金属箔材制造中基于机器视觉的质量分析方法
CN114897881A (zh) 一种基于边缘特征的晶粒缺陷检测方法
CN112669295A (zh) 一种基于二次阈值分割理论的锂电池极片缺陷检测方法
CN116309532A (zh) 一种目标物品质量检测的方法、装置、设备及介质
KR102242996B1 (ko) 자동차 사출제품의 비정형 불량 검출 방법
CN113269769A (zh) 一种基于图像配准的缺陷检测方法、系统及设备
CN116539641A (zh) 光伏玻璃组件二道铺设后外观检测方法
CN106353340A (zh) 一种棒状高反射率零件表面缺陷检测方法
CN114612423A (zh) 一种芯片封装缺陷检测方法
CN113780235A (zh) 图标瑕疵检测方法及系统
CN111353974B (zh) 一种检测影像边界缺陷的方法及装置
CN117475233A (zh) 压盖异常状态的检测方法、装置、设备和计算机存储介质
KR20190119801A (ko) 차량 헤드라이트 얼라인먼트 보정 및 분류 방법 및 이를 이용한 차량 헤드라이트 불량검사 방법

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: 21937689

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21937689

Country of ref document: EP

Kind code of ref document: A1