Back-drilled hole 2D / 3D feature measurement system, method and device

Abstract

The present invention relates to a back-drilled hole two-dimensional / three-dimensional feature measurement system, comprising: an image acquisition device acquires a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes by moving a moving platform at equal intervals; a position acquisition device performs fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes to obtain the position information of each back-drilled hole on the two-dimensional real-time image; a back-drilled hole center extraction device acquires an image of a region of interest at the location of each back-drilled hole according to the location of each back-drilled hole in the two-dimensional real-time image; a back-drilled hole inner and outer boundary processing device performs double threshold segmentation according to the center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, and obtains the positional relationship between the inner and outer boundary center and the inner and outer boundary; a feature parameter generation device calculates the feature parameters of the back-drilled hole on the three-dimensional actual height image. The present invention also discloses a back-drilled hole two-dimensional / three-dimensional feature measurement method and a back-drilled hole two-dimensional / three-dimensional feature measurement device.

Description

Technical Field

[0001] The present invention relates to the field of optical measurement technology, and in particular to a back-drilled hole two-dimensional / three-dimensional feature measurement system, a back-drilled hole two-dimensional / three-dimensional feature measurement method and a back-drilled hole two-dimensional / three-dimensional feature measurement device. Background Art

[0002] As a substrate for carrying electronic components, circuit boards are widely used in the electronics field. Due to the wiring requirements of different electronic products, the main structural classification of circuit boards can be divided into two major parts. One is based on the number of layers, which can be divided into single-sided boards, double-sided boards, multi-layer boards, and flexible boards; the other is based on the production process, which can be divided into copper boards, tin-sprayed boards, halogen-free boards, gold-immersion boards, nickel-plated boards, aluminum substrates, etc. Among them, circuit boards have attracted much attention as carriers for electrical connections of electronic components. Circuit boards are circuit boards that form point-to-point connections and printed components on a universal substrate according to a predetermined design. Their main function is to enable various electronic components to form connections in predetermined circuits. As an important electronic component, circuit boards are widely used in different fields, including consumer electronics, automotive electronics, semiconductor packaging, network communications, aerospace, and other fields. In particular, with the rapid development of new energy vehicles, the demand for automotive electronics has increased significantly. In addition, the demand for circuit boards in consumer electronics and semiconductor packaging is also huge.

[0003] However, the existing production process of circuit boards is not mature, especially there are many problems in the process detection of parameters related to back drilling in circuit boards, which also restricts the working efficiency of the circuit board production line. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a back-drilled hole two-dimensional / three-dimensional feature measurement system, aiming to solve the problems of low detection efficiency and poor accuracy of the roundness and back-drilling height of back-drilled holes in circuit boards in the existing detection system.

[0005] A back-drilled hole 2D / 3D feature measurement system, comprising: an image acquisition device, used to acquire a 2D real-time image and a 3D actual height image of a circuit board with back-drilled holes by moving a motion platform at equal intervals; a position acquisition device, electrically connected to the image acquisition device, the position acquisition device is used to perform fixed threshold segmentation on the 2D real-time image of the circuit board with back-drilled holes to obtain the position information of each back-drilled hole on the 2D real-time image, and to construct a corresponding position conversion model with the position information of each back-drilled hole on the 2D real-time image and preset standard data of the circuit board back-drilled hole manufacturing to obtain the position of each back-drilled hole in the 2D real-time image; a back-drilled hole center extraction device, electrically connected to the position acquisition device, the back-drilled hole center extraction device is used to extract the position of each back-drilled hole in the 2D real-time image according to the position of each back-drilled hole in the 2D real-time image. A region of interest image of each back-drilled hole is obtained at the position of each back-drilled hole, and the center of each back-drilled hole is obtained; a back-drilled hole inner and outer boundary processing device is electrically connected to the back-drilled hole center extraction device, and the back-drilled hole inner and outer boundary processing device is used to perform double threshold segmentation according to the center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculate the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and convert the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in a first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries; a feature parameter generating device is electrically connected to the back-drilled hole inner and outer boundary processing device, and the feature parameter generating device is used to calculate the feature parameters of the back-drilled hole on the three-dimensional actual height image transmitted by the image acquisition device according to the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

[0006] Optionally, the image acquisition device includes a camera and a line laser, wherein the line laser emits a laser line, and an angle between the line laser and the camera is a preset angle.

[0007] Optionally, the position acquisition device includes a contour point calculation circuit, a feature hole acquisition circuit, a matching result acquisition circuit, a secondary center position calculation circuit and a conversion model calculation circuit, wherein the contour point calculation circuit is used to perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes and extract contours, calculate the centroid set of each contour point in the circuit board with back-drilled holes, and transmit the centroid set of each contour point to the feature hole acquisition circuit; the feature hole acquisition circuit is electrically connected to the contour point calculation circuit, and the feature hole acquisition circuit is used to screen the centroid set of each contour point to obtain a preset number of global feature hole sets; the matching result acquisition circuit is connected to the The feature hole acquisition circuit is electrically connected, and the matching result acquisition circuit is used to obtain the corresponding matching result according to the preset number of global feature hole sets; the secondary center position calculation circuit is electrically connected to the matching result acquisition circuit, and the secondary center position calculation circuit is used to calculate the corresponding secondary center position of the back-drilled hole in the circuit board according to the matching result; the conversion model calculation circuit is electrically connected to the secondary center position calculation circuit, and the conversion model calculation circuit is used to calculate the position conversion model according to the center position of the two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the back-drilled hole making board of the circuit board to obtain the position of each back-drilled hole in the two-dimensional real-time image.

[0008] Optionally, the back-drilled hole center extraction device includes an area of ​​interest image acquisition circuit, a threshold segmentation processing circuit and a three-dimensional center position calculation circuit, wherein the area of ​​interest image acquisition circuit is used to acquire the area of ​​interest image of the center position on the two-dimensional real-time image according to the position transformation model; the threshold segmentation processing circuit is electrically connected to the area of ​​interest image acquisition circuit, and the threshold segmentation processing circuit is used to perform adaptive threshold segmentation processing based on the area of ​​interest image of each back-drilled hole on the two-dimensional real-time image; the three-dimensional center position calculation circuit is electrically connected to the threshold segmentation processing circuit, and the three-dimensional center position calculation circuit is used to calculate the corresponding three-dimensional center positions of the back-drilled holes in the circuit board according to the segmentation threshold.

[0009] Optionally, the back-drilled hole inner and outer boundary processing device includes a segmentation threshold calculation circuit, a first fitting circuit, an eccentricity calculation circuit, a process parameter acquisition circuit and a first parameter conversion circuit, wherein the segmentation threshold calculation circuit is used to calculate the first segmentation threshold and the second segmentation threshold according to the center of the back-drilled hole; the first fitting circuit is electrically connected to the segmentation threshold calculation circuit, and the first fitting circuit is used to segment the target back-drilled hole area by the first segmentation threshold and the second segmentation threshold, and fit the center and radius of the inner and outer boundaries; the eccentricity calculation circuit is electrically connected to the first fitting circuit, and the eccentricity calculation circuit is used to calculate the eccentricity according to the center and radius of the inner and outer boundaries; the process parameter acquisition circuit is electrically connected to the eccentricity calculation circuit, and the process parameter acquisition circuit is used to acquire the two-dimensional process parameters of the inner and outer boundaries according to the eccentricity; the first parameter conversion circuit is electrically connected to the process parameter acquisition circuit, and the first parameter conversion circuit is used to convert the two-dimensional process parameters into actual numerical parameters in the first coordinate system to obtain the positional relationship between the center of the inner and outer boundaries and the inner and outer boundaries.

[0010] Optionally, the characteristic parameter generating device includes a boundary data acquisition circuit, a second fitting circuit and a second parameter conversion circuit, wherein the boundary data acquisition circuit is used to obtain the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the center positions of the inner and outer boundaries and the positions of the inner and outer boundaries; the second fitting circuit is electrically connected to the boundary data acquisition circuit, and the second fitting circuit is used to calculate and fit the first height plane and the second height plane according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image; the second parameter conversion circuit is electrically connected to the second fitting circuit, and the second parameter conversion circuit is used to calculate the first distance between the first height planes and the second distance from the first height plane to the second height plane, and convert the obtained first distance and second distance into the characteristic parameters of the back-drilled hole in the first coordinate system.

[0011] In summary, the back-drilled hole two-dimensional / three-dimensional feature measurement system described in the present application obtains a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes through the image acquisition device, the back-drilled hole center extraction device, the back-drilled hole inner and outer boundary processing device, and the feature parameter generation device, and calculates the feature parameters of the back-drilled holes, thereby solving the problems of low detection efficiency and poor accuracy of the roundness and back-drilling height of the back-drilled holes of the circuit board, and effectively improving the production efficiency of the circuit board.

[0012] Based on the same inventive concept, the present application also provides a back-drilled hole two-dimensional / three-dimensional feature measurement method, which is performed by the above-mentioned back-drilled hole two-dimensional / three-dimensional feature measurement system, and the back-drilled hole two-dimensional / three-dimensional feature measurement method includes: acquiring a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes by moving the motion platform at equal intervals; performing fixed threshold segmentation on the acquired two-dimensional real-time image of the circuit board with back-drilled holes to obtain the position information of each back-drilled hole on the two-dimensional real-time image, and constructing the position information of each back-drilled hole and the preset standard data of the circuit board back-drilled hole manufacturing into a corresponding position conversion model to obtain the position information of each back-drilled hole in the two-dimensional real-time image. The position of each back-drilled hole; obtaining an image of a region of interest at the position of each back-drilled hole according to the position of each back-drilled hole in the acquired two-dimensional real-time image, and obtaining the center of each back-drilled hole by calculation; performing double threshold segmentation according to the acquired center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculating the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in a first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries; and calculating the characteristic parameters of the back-drilled hole on the three-dimensional actual height image according to the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

[0013] Optionally, the acquiring of a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes by moving the motion platform at equal intervals includes: acquiring a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes in a current column by moving the motion platform at equal intervals along a first direction; acquiring a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes in a next column by moving the motion platform at equal intervals along a second direction, wherein the second direction is perpendicular to the first direction; and sequentially scanning the circuit board with back-drilled holes by the motion platform along the second direction to acquire a two-dimensional real-time image and a three-dimensional actual height image of the entire circuit board with back-drilled holes.

[0014] Optionally, the obtained two-dimensional real-time image of the circuit board with back-drilled holes is segmented with a fixed threshold value to obtain the position information of each back-drilled hole on the two-dimensional real-time image, and the position information of each back-drilled hole is constructed into a corresponding position conversion model with preset standard data of the circuit board back-drilled hole making to obtain the position of each back-drilled hole in the two-dimensional real-time image, including: performing fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes and extracting contours, calculating the centroid set of each contour point in the circuit board with back-drilled holes; screening the centroid set of each contour point to obtain a preset number of global feature hole sets; obtaining corresponding matching results based on the preset number of global feature hole sets; calculating the corresponding secondary center position of the back-drilled hole in the circuit board based on the obtained matching results; calculating the position conversion model based on the center position of the obtained two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled hole making to obtain the position of each back-drilled hole in the two-dimensional real-time image.

[0015] Optionally, the step of obtaining an image of a region of interest at the location of each back-drilled hole according to the location of each back-drilled hole in the acquired two-dimensional real-time image, and obtaining the center of each back-drilled hole by calculation, comprises: obtaining an image of a region of interest at the center position on the two-dimensional real-time image according to the position conversion model; performing adaptive threshold segmentation processing according to the image of the region of interest of each back-drilled hole in the two-dimensional real-time image; and calculating three corresponding center positions of the back-drilled holes in the circuit board according to the obtained segmentation threshold.

[0016] Optionally, performing double threshold segmentation according to the obtained center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculating the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in a first coordinate system to obtain the positional relationship between the inner and outer boundary center points and the inner and outer boundaries, including: calculating a first segmentation threshold and a second segmentation threshold according to the center of the back-drilled hole; segmenting the target back-drilled hole area by the obtained first segmentation threshold and second segmentation threshold, and fitting to obtain the center and radius of the inner circle boundary; calculating the eccentricity according to the obtained center and radius of the inner and outer boundaries; obtaining the two-dimensional process parameters of the inner and outer boundaries according to the obtained eccentricity; converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary center points and the inner and outer boundaries.

[0017] Optionally, the characteristic parameters of the back-drilled hole are calculated on the three-dimensional actual height image according to the positional relationship between the center points of the inner and outer boundaries and the inner and outer boundaries, including: obtaining the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the acquired positions of the center points of the inner and outer boundaries and the inner and outer boundaries of the back-drilled hole; calculating and fitting a first height plane and a second height plane according to the acquired positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image; calculating a first distance from the center height of the back-drilled hole to the first height plane and a second distance from the first height plane to the second height plane, and converting the obtained first distance and second distance into the characteristic parameters of the back-drilled hole in a first coordinate system.

[0018] In summary, the back-drilled hole 2D / 3D feature measurement method described in the present application obtains a 2D real-time image and a 3D actual height image of a circuit board with a back-drilled hole, and calculates the characteristic parameters of the back-drilled hole, thereby solving the problems of low detection efficiency and poor accuracy of the roundness and back-drilling height of the back-drilled holes of the circuit board, and effectively improves the production efficiency of the circuit board.

[0019] Based on the same inventive concept, the present application also provides a back-drilled hole two-dimensional / three-dimensional feature measurement device, which includes: at least one processor and a memory, at least one of the processors executes computer execution instructions stored in the memory, and at least one of the processors executes the above-mentioned back-drilled hole two-dimensional / three-dimensional feature measurement method.

[0020] In summary, the back-drilled hole 2D / 3D feature measurement device provided in the present application can realize the detection of circuit boards, thereby effectively improving the working efficiency of the circuit board production line and improving the market competitiveness of the products. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of the structure of a back-drilled hole two-dimensional / three-dimensional feature measurement system disclosed in an embodiment of the present application;

[0023] Figure 2 for Figure 1 The optical path diagram of the transparent material screen thickness measurement system shown;

[0024] Figure 3 for Figure 1A schematic structural diagram of a position acquisition device of a back-drilled hole 2D / 3D feature measurement system;

[0025] Figure 4 for Figure 1 A schematic structural diagram of a back-drilled hole center extraction device of a back-drilled hole 2D / 3D feature measurement system shown;

[0026] Figure 5 for Figure 1 A schematic structural diagram of a back-drilled hole inner and outer boundary processing device of the back-drilled hole 2D / 3D feature measurement system shown;

[0027] Figure 6 for Figure 1 A structural schematic diagram of a feature parameter generating device of a back-drilled hole 2D / 3D feature measurement system shown;

[0028] Figure 7 A schematic flow chart of a back-drilled hole two-dimensional / three-dimensional feature measurement method disclosed in an embodiment of the present application;

[0029] Figure 8 for Figure 7 A schematic flow chart of step S10 in the back-drilled hole 2D / 3D feature measurement method shown;

[0030] Fig. 9 for Figure 7 A schematic flow chart of step S20 in the back-drilled hole 2D / 3D feature measurement method shown;

[0031] Fig.10 for Figure 7 A schematic flow chart of step S30 in the back-drilled hole 2D / 3D feature measurement method shown;

[0032] Fig.11 for Figure 7 A schematic flow chart of step S40 in the back-drilled hole 2D / 3D feature measurement method is shown;

[0033] Fig.12 for Figure 7 The flowchart of step S50 in the back-drilled hole 2D / 3D feature measurement method is shown;

[0034] Fig.13 A schematic diagram of the hardware structure of a back-drilled hole two-dimensional / three-dimensional feature measurement device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present application are given in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thoroughly and comprehensively understood.

[0036] The following descriptions of the various embodiments are with reference to the attached diagrams to illustrate specific embodiments that the present application can be used to implement. The serial numbers for the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in the present application, unless otherwise specified, include direct and indirect connections (couplings). The directional terms mentioned in the present application, such as "upper", "lower", "front", "back", "left", "right", "inside", "outside", "side", etc., are only with reference to the directions of the attached diagrams. Therefore, the directional terms used are for better and clearer explanation and understanding of the present application, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present application.

[0037] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be fixedly connected, detachably connected, or integrally connected; it can be mechanically connected; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including", "may include", "include", or "may include" used in this application indicate the existence of the corresponding functions, operations, elements, etc. disclosed, and do not limit one or more other functions, operations, elements, etc. In addition, the terms "including" or "include" indicate the existence of the corresponding features, numbers, steps, operations, elements, components, or combinations thereof disclosed in the specification, and do not exclude the existence or addition of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, and are intended to cover non-exclusive inclusions.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0039] As a substrate for carrying electronic components, circuit boards are widely used in the electronic field. Due to the wiring requirements of different electronic products, the main structural classification of circuit boards can be divided into two major parts. One is to be divided according to the number of layers, which can be divided into single-sided boards, double-sided boards, multi-layer boards, and flexible boards; the other is to be divided according to the production process, which can be divided into copper boards, tin-sprayed boards, halogen-free boards, gold-immersion boards, nickel-plated boards, aluminum substrates, etc. Among them, circuit boards as carriers of electrical connections of electronic components have attracted much attention. Circuit boards are circuit boards that form point-to-point connections and printed components on a general substrate according to a predetermined design. The main function is to enable various electronic components to form connections in predetermined circuits. As an important electronic component, circuit boards are widely used in different fields, including consumer electronics, automotive electronics, semiconductor packaging, network communications, aerospace and other fields. In particular, with the rapid development of new energy vehicles, the demand for automotive electronics has increased significantly. In addition, the demand for circuit boards in consumer electronics and semiconductor packaging is also huge. However, the existing production process of circuit boards is not mature, especially for the process detection of back drilling related parameters in circuit boards. There are many problems, which also restricts the working efficiency of circuit board production lines.

[0040] Based on this, the present application hopes to provide a solution that can solve the above-mentioned technical problems, which can solve the problems of low detection efficiency and poor accuracy of the roundness and back-drilling height of the back-drilled holes of the circuit board, thereby effectively improving the production efficiency of the circuit board. The details will be explained in subsequent embodiments.

[0041] The back-drilled hole 2D / 3D feature measurement system, method and device provided in the embodiments of the present application are mainly designed based on structured light, which can simultaneously obtain 2D / 3D data of back-drilled holes in circuit boards under structured light. It should be noted that structured light is a system structure composed of a projector and a camera. Specifically, after a projector projects specific light information onto the surface of an object and the background, the camera collects the information, calculates the position and depth of the object and other information based on the changes in the light signal caused by the object, and then restores the entire three-dimensional space.

[0042] See also Figure 1 , which is a schematic diagram of the structure of a back-drilled hole 2D / 3D feature measurement system disclosed in an embodiment of the present application. Figure 1As shown, in an embodiment of the present application, the present application provides a back-drilled hole 2D / 3D feature measurement system 100, which may at least include an image acquisition device 110, a position acquisition device 120, a back-drilled hole center extraction device 130, a back-drilled hole inner and outer boundary processing device 140, and a feature parameter generation device 150. The image acquisition device 110 is electrically connected to the position acquisition device 120, the position acquisition device 120 is electrically connected to the back-drilled hole center extraction device 130, the back-drilled hole center extraction device 130 is electrically connected to the back-drilled hole inner and outer boundary processing device 140, and the back-drilled hole inner and outer boundary processing device 140 is electrically connected to the feature parameter generation device 150, that is, the position acquisition device 120, the back-drilled hole center extraction device 130, the back-drilled hole inner and outer boundary processing device 140, and the feature parameter generation device 150 are electrically connected in sequence.

[0043] The image acquisition device 110 is used to acquire a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes by moving the motion platform at equal intervals, and transmit the two-dimensional real-time image and the three-dimensional actual height image of the circuit board with back-drilled holes to the position acquisition device 120. In an exemplary embodiment, Figure 2 As shown, the image acquisition device 110 may include a camera and a line laser, wherein the line laser emits a laser line, and the angle between the line laser and the camera is a preset angle, and the preset angle may be 50 degrees. Optionally, the angle between the camera and the vertical direction may be 20 degrees, and correspondingly, the angle between the line laser and the vertical direction may be 30 degrees. The motion platform is a two-dimensional motion platform.

[0044] The position acquisition device 120 is used to perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes acquired by the image acquisition device 110 to obtain the position information of each back-drilled hole on the two-dimensional real-time image, and to construct a corresponding position conversion model with the position information of each back-drilled hole on the two-dimensional real-time image and preset standard data of the circuit board back-drilling board manufacturing to acquire the position of each back-drilled hole in the two-dimensional real-time image, and transmit the position of each back-drilled hole in the two-dimensional real-time image to the back-drilled hole center extraction device 130.

[0045] In the embodiment of the present application, specifically, the position acquisition device 120 can perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes acquired by the image acquisition device 110 using the two-dimensional imaging features of the back-drilled holes to obtain the position information of each back-drilled hole on the two-dimensional real-time image of the circuit board with back-drilled holes, and construct a one-to-one corresponding position conversion model based on the position information of each back-drilled hole on the two-dimensional real-time image of the circuit board with back-drilled holes and the preset standard data obtained by back-drilling the circuit board to obtain the position of each back-drilled hole in the two-dimensional real-time image, and transmit the position of each back-drilled hole in the two-dimensional real-time image to the back-drilled hole center extraction device 130.

[0046] The back-drilled hole center extraction device 130 is used to obtain a region of interest (ROI) image of the location of each back-drilled hole according to the location of each back-drilled hole in the two-dimensional real-time image obtained by the position acquisition device 120, obtain the center of each back-drilled hole by calculation, and transmit the center of the back-drilled hole to the back-drilled hole inner and outer boundary processing device 140.

[0047] In the embodiment of the present application, specifically, the back-drilling hole center extraction device 130 can obtain the ROI image of each back-drilling hole according to the position of each back-drilling hole in the two-dimensional real-time image obtained by the position acquisition device 120, segment the current back-drilling hole and the background area of ​​the ROI image according to the maximum inter-class variance principle, and extract the center of the back-drilling hole through the centroid formula to achieve accurate positioning of the back-drilling hole. It should be noted that in machine vision and image processing, the area to be processed is outlined from the processed image in the form of a box, circle, ellipse, irregular polygon, etc., which is called a region of interest (ROI).

[0048] The back-drilled hole inner and outer boundary processing device 140 is used to perform double threshold segmentation based on the center of the back-drilled hole obtained by the back-drilled hole center extraction device 130 to obtain the inner and outer boundaries of the back-drilled hole, calculate the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, convert the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries, and transmit the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries of the back-drilled hole to the feature parameter generation device 150.

[0049] In the embodiment of the present application, specifically, the back-drilled hole inner and outer boundary processing device 140 can perform double threshold segmentation based on the center of the back-drilled hole obtained by the back-drilled hole center extraction device 130 with its inner and outer radii as the range, obtain the inner and outer boundaries of the back-drilled hole, fit the sub-pixel center positions of the inner and outer holes corresponding to the inner and outer boundaries, and calculate the two-dimensional process parameters of the back-drilled hole through the hole roundness calculation method, and then convert the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system according to the camera field of view resolution to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries, and transmit the positional relationship between the inner and outer boundary centers and the inner and outer boundaries of the back-drilled hole to the feature parameter generation device 150. In the exemplary embodiment of the present application, the two-dimensional process parameters of the back-drilled hole include two-dimensional process parameters such as the center distance of the inner and outer circle centers and the inner and outer roundness. The first coordinate system is a physical coordinate system.

[0050] The characteristic parameter generating device 150 is used to calculate the characteristic parameters of the back-drilled hole on the three-dimensional actual height image transmitted by the image acquisition device 110 according to the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries transmitted by the back-drilled hole inner and outer boundary processing device 140. In an exemplary embodiment of the present application, the characteristic parameters of the back-drilled hole include but are not limited to: the height value between the circuit board surface and the outer boundary of the back-drilled hole, the height value between the outer boundary of the back-drilled hole and the bottom of the center of the circle, etc.

[0051] In summary, the back-drilled hole two-dimensional / three-dimensional feature measurement system described in the present application obtains a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes through an image acquisition device 110, a position acquisition device 120, a back-drilled hole center extraction device 130, a back-drilled hole inner and outer boundary processing device 140, and a feature parameter generation device 150, and calculates the feature parameters of the back-drilled holes, thereby solving the problems of low detection efficiency and poor accuracy of the roundness and back-drilling height of the back-drilled holes of the circuit board, and effectively improving the production efficiency of the circuit board.

[0052] Please also read Figure 1 and Figure 2 As shown, in this embodiment, the image acquisition device 110 is specifically used to acquire a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes in the current column by moving the motion platform at equal intervals along the first direction. The first direction may be the Y-axis direction of the motion platform, and the three-dimensional actual height image may be obtained by the height data of the laser triangulation principle. Figure 2 As shown, when the measured point O of the measured object (i.e., the circuit board with back-drilled holes) moves or the surface height changes, the coordinate of the reference point P of the imaging point can be observed to change by x on the imaging surface of the camera. The principle of the laser triangulation method is:

[0053] According to the properties of similar triangles, we have:

[0054]

[0055] Among them, h is the surface height or displacement change of the object to be measured, l is the distance from the intersection of the laser optical axis and the camera optical axis to the center of the lens, that is, the object distance; d is the distance from the center of the lens to the camera image plane, that is, the image distance; α is the angle between the laser optical axis and the camera optical axis, that is, the angle between the laser plane and the camera optical axis; x is the distance from point P to point P1 on the camera image plane.

[0056] In order to ensure that the measured point O forms a clear real image on the camera image plane, the following formula must be satisfied:

[0057]

[0058] Where f is the focal length of the lens.

[0059] In the formula, combining formula (1) and formula (2), we can get:

[0060]

[0061] The image acquisition device 110 is also specifically used to acquire a two-dimensional real-time image and a three-dimensional actual height image of the next row of the circuit board with back-drilled holes by moving the motion platform at equal intervals along a second direction. The second direction is perpendicular to the first direction. In this embodiment, the second direction can be the X-axis direction.

[0062] The image acquisition device 110 is also specifically used to sequentially scan the circuit board with back-drilled holes along the second direction through the motion platform to obtain a two-dimensional real-time image and a three-dimensional actual height image of the entire circuit board with back-drilled holes.

[0063] See also Figure 3 , which is Figure 1 The schematic diagram of the structure of the position acquisition device 120 of the back-drilling two-dimensional / three-dimensional feature measurement system is shown in FIG. Figure 3 As shown, the position acquisition device 120 includes a contour point calculation circuit 121, a feature hole acquisition circuit 122, a matching result acquisition circuit 123, a secondary center position calculation circuit 124, and a conversion model calculation circuit 125. The contour point calculation circuit 121 is electrically connected to the feature hole acquisition circuit 122, the feature hole acquisition circuit 122 is electrically connected to the matching result acquisition circuit 123, the matching result acquisition circuit 123 is electrically connected to the secondary center position calculation circuit 124, and the secondary center position calculation circuit 124 is electrically connected to the conversion model calculation circuit 125.

[0064] In the embodiment of the present application, the contour point calculation circuit 121 is used to perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes transmitted by the image acquisition device 110 and extract the contour, calculate the centroid set of each contour point in the circuit board with back-drilled holes, and transmit the centroid set of each contour point to the feature hole acquisition circuit 122. Specifically, the contour point calculation circuit 121 can perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes transmitted by the image acquisition device 110 through the threshold function of the opencv library, extract the contour of the circuit board with back-drilled holes using cvFindContours, and calculate the centroid set {C1, C2, ..., Cn} of each contour point in the circuit board with back-drilled holes.

[0065] The feature hole acquisition circuit 122 is used to filter the centroid sets of each of the contour points transmitted by the contour point calculation circuit 121 to obtain a preset number of global feature hole sets. Specifically, the centroid sets of each of the contour points need to be filtered to meet the requirement that the aspect ratio of the circumscribed rectangle of the contour is less than a set threshold value 1, and the global feature hole set is {C1', C2', ..., Cn'}.

[0066] The matching result acquisition circuit 123 is used to obtain the corresponding matching result according to the preset number of global feature hole sets obtained by the feature hole acquisition circuit 122. In the embodiment of the present application, the matching result acquisition circuit 123 reads the standard hole data of the back drilling of the circuit board, and uses translation search to calculate the multiplication correlation coefficient of the global feature hole set {C1', C2', ..., Cn'} and the standard hole data with a set step size to obtain the corresponding matching result. The multiplication correlation coefficient calculation formula is:

[0067] G=STD_Template*REAL_Template formula (4)

[0068] Among them, REAL_Template is the real-time image ROI area corresponding to each moving step position.

[0069] The secondary center position calculation circuit 124 is used to calculate the corresponding secondary center position of the back-drilled hole in the circuit board according to the matching result obtained by the matching result acquisition circuit 123. In the embodiment of the present application, the secondary center position calculation circuit 124 corresponds the standard hole data of the back-drilled hole of the circuit board to the two-dimensional real-time image of the circuit board with the back-drilled hole according to the matching result obtained by the matching result acquisition circuit 123, and obtains the approximate center position and radius of the back-drilled hole corresponding to the two-dimensional real-time image of the circuit board with the back-drilled hole, and calculates the corresponding secondary center position of the back-drilled hole in the circuit board by the grayscale center of gravity calculation formula in a circular area with a preset radius as the center. Among them, the preset radius can be 1.5 cm, and the grayscale center of gravity formula is:

[0070]

[0071] The conversion model calculation circuit 125 is used to calculate a position conversion model based on the center position of the two-dimensional real-time image of the circuit board with back-drilled holes obtained by the secondary center position calculation circuit 124 and the center position of the corresponding standard hole of the circuit board back-drilled board, so as to obtain the position of each back-drilled hole in the two-dimensional real-time image. Specifically, the conversion model calculation circuit 125 calculates the affine transformation matrix of the center position of the two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled board, based on the center position of the two-dimensional real-time image of the circuit board with back-drilled holes obtained by the secondary center position calculation circuit 124, and obtains the position conversion model to obtain the position of each back-drilled hole in the two-dimensional real-time image. The parameters of the affine transformation matrix can be estimated by the least squares method, and the calculation process is as follows:

[0072] Suppose the original image is f(x,y) and the transformed image is F(X',Y'). To restore F(X',Y') to f(x,y), we need to find the conversion relationship between (X',Y') coordinates and (x,y) coordinates. This conversion relationship is called coordinate transformation, expressed as (x,y)=T(X',Y').

[0073] The expression of affine transformation is: R(x)=Px+Q, x=(x,y) is the plane position of the pixel, P is the 2*2 rotation matrix, Q is the 2*1 translation vector, P and Q are the affine transformation parameters, that is:

[0074] x=AX'+BY'+C Formula (6)

[0075] y=DX'+EY'+F formula (7)

[0076] Therefore, it can be summarized as the solution of coordinate transformation coefficients A, B, C, D, E, and F. In order to prevent the occurrence of empty pixels, reverse mapping is generally used, and the least squares method is used to obtain:

[0077] vec1=inv([XYI]'*[XYI])*[XYI]'*U Formula (8)

[0078] vec2=inv([XYI]'*[XYI])*[XYI]'*V; Formula (9)

[0079] Among them, vec1 = [ABC]'; vec2 = [DEF]'; XYUVI are vectors composed of x, y, X', Y', 1 respectively.

[0080] See also Figure 4 , which is Figure 1 The structural diagram of the back-drilled hole center extraction device 130 of the back-drilled hole 2D / 3D feature measurement system is shown in FIG. Figure 4 As shown, the back-drilling hole center extraction device 130 includes a ROI image acquisition circuit 131, a threshold segmentation processing circuit 132, and a three-dimensional center position calculation circuit 133. The ROI image acquisition circuit 131 is electrically connected to the threshold segmentation processing circuit 132, and the threshold segmentation processing circuit 132 is electrically connected to the three-dimensional center position calculation circuit 133.

[0081] In the embodiment of the present application, the ROI image acquisition circuit 131 is used to acquire the ROI image of the center position on the two-dimensional real-time image according to the position conversion model transmitted by the position acquisition device 120. Specifically, the ROI image acquisition circuit 131 corresponds all the holes in the standard image to the two-dimensional real-time image according to the position conversion model transmitted by the position acquisition device 120, obtains the approximate center position and radius of all the back-drilled holes in the two-dimensional real-time image, and acquires the ROI image corresponding to the ROI area of ​​the back-drilled hole on the two-dimensional real-time image. Among them, the ROI area can be twice the radius of the center position of the back-drilled hole.

[0082] The threshold segmentation processing circuit 132 is used to perform adaptive threshold segmentation processing according to the ROI image of each back-drilled hole on the two-dimensional real-time image acquired by the ROI image acquisition circuit 131. Specifically, the threshold segmentation processing circuit 132 performs adaptive threshold segmentation according to the maximum variance principle within the inner and outer radius ranges of the back-drilled hole according to the ROI image of each back-drilled hole acquired by the ROI image acquisition circuit 131. The maximum variance principle is as follows:

[0083] Calculate the cumulative mean M of the gray level K and the global mean MG of the image:

[0084] Among them, P i is the probability value of the current gray level appearing, and the final inter-class variance formula of this embodiment is:

[0085]

[0086] Among them, the gray level K that maximizes the formula is the calculated segmentation threshold.

[0087] The tertiary center position calculation circuit 133 is used to calculate the corresponding tertiary center position of the back-drilled hole in the circuit board according to the segmentation threshold value obtained by the threshold segmentation processing circuit 132. Specifically, the tertiary center position calculation circuit 133 can separate the target back-drilled hole from the background plane according to the segmentation threshold value obtained by the threshold segmentation processing circuit 132, and then calculate the tertiary center position of the back-drilled hole in the circuit board through the grayscale centroid formula.

[0088] See also Figure 5 , which is Figure 1 The schematic diagram of the structure of the back-drilled hole inner and outer boundary processing device 140 of the back-drilled hole 2D / 3D feature measurement system is shown in FIG. Figure 5 As shown, the back-drilling hole inner and outer boundary processing device 140 includes a segmentation threshold calculation circuit 141, a first fitting circuit 142, an eccentricity calculation circuit 143, a process parameter acquisition circuit 144 and a first parameter conversion circuit 145. The segmentation threshold calculation circuit 141 is electrically connected to the first fitting circuit 142, the first fitting circuit 142 is electrically connected to the eccentricity calculation circuit 143, the eccentricity calculation circuit 143 is electrically connected to the process parameter acquisition circuit 144, and the process parameter acquisition circuit 144 is electrically connected to the first parameter conversion circuit 145.

[0089] The segmentation threshold calculation circuit 141 is used to calculate the first segmentation threshold and the second segmentation threshold according to the center of the back-drilled hole transmitted by the back-drilled hole center extraction device 130. Specifically, the segmentation threshold calculation circuit 141 performs circular ROI area interception in the inner and outer radius areas of the back-drilled hole according to the center of the back-drilled hole transmitted by the back-drilled hole center extraction device 130, and performs adaptive segmentation using the maximum variance principle to obtain the first segmentation threshold and the second segmentation threshold.

[0090] The first fitting circuit 142 is used to segment the target back-drilling area by the first segmentation threshold and the second segmentation threshold obtained by the segmentation threshold calculation circuit 141, and to fit the center and radius of the inner and outer boundaries. Specifically, the first fitting circuit 142 segments the target back-drilling area by the first segmentation threshold and the second segmentation threshold obtained by the segmentation threshold calculation circuit 141, extracts the inner and outer boundary contour information of the target back-drilling, obtains the boundary position, and fits the center and radius of the inner circle boundary by the least squares method. Among them, the optimization objective function of the square error of the circle fitting by the least squares method is:

[0091]

[0092] Where: (x i ,y i )i=1,2,...,n are the coordinates of the feature points on the arc; n is the number of feature points involved in fitting. On the premise of maintaining the characteristics of the optimization objective function, in order to avoid the square root calculation, the error function is optimized. The meaning of formula (11) is that the minimum distance difference from all moving points to the fixed point becomes the minimum difference between the square of the distance from all moving points to the fixed point and the square of the radius, which is defined as follows:

[0093]

[0094] Then formula (12) is expanded to:

[0095]

[0096] At the same time, let B = -2y 0 , A=-2x 0 , That is, formula (13) can be expressed as:

[0097]

[0098] According to the principle of least squares method, parameters A, B, and C should make E obtain the minimum value. According to the method of finding the minimum value, A, B, and C should satisfy the following formula:

[0099]

[0100] Solve the system of equations and write it in matrix form to obtain formula (16):

[0101]

[0102] The parameters in formula (16) are calculated as follows:

[0103]

[0104]

[0105]

[0106]

[0107] So as to obtain the best fitting circle center coordinates (x 0 ,y 0 ), the fitted value of radius r:

[0108]

[0109] In this embodiment, when performing the least squares circle fitting, the number of fitting points has been determined, that is, the number of n is a known quantity, so x can be directly calculated using the above formula as a priori formula. 0 ,y 0 ,r three parameters.

[0110] The eccentricity calculation circuit 143 is used to calculate the eccentricity according to the center and radius of the inner and outer boundaries obtained by the first fitting circuit 142. Specifically, the center of the inner circle is (X 0 , Y 0 , R 0 ), the center of the outer circle is (X 1 , Y 1 , R 1 ), the corresponding eccentricity can be calculated according to the eccentricity formula. Wherein, the eccentricity formula is:

[0111]

[0112] The process parameter acquisition circuit 144 is used to acquire the two-dimensional process parameters of the inner and outer boundaries according to the eccentricity obtained by the eccentricity calculation circuit 143. For example, the calculation of the roundness process parameter in the two-dimensional process parameter is described as follows, the distance from all contour points on the circuit board with back-drilled holes to the center of the fitting circle is calculated, and then the roundness residual En is obtained by calculating the difference (i.e., absolute value) between the distance from each contour point on the circuit board with back-drilled holes to the center of the fitting circle and the radius R, and the mean of the roundness residual En is calculated, and finally (Rn-ave(En)) / Rn is used as the roundness process parameter.

[0113] The first parameter conversion circuit 145 is used to convert the two-dimensional process parameters of the back drilling hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries. Specifically, in the embodiment of the present application, all the parameters calculated above are the results in the image coordinate system, that is, the pixel unit, and the horizontal and vertical resolutions of the image are both 16um / pixel. The values ​​of each process parameter obtained by the above calculation are multiplied by the corresponding resolution to obtain the actual numerical parameters in the first coordinate system.

[0114] See also Figure 6 , which is Figure 1 The structural diagram of the feature parameter generating device 150 of the back-drilling two-dimensional / three-dimensional feature measurement system is shown in FIG. Figure 6 As shown, the characteristic parameter generating device 150 includes a boundary data acquisition circuit 151, a second fitting circuit 152 and a second parameter conversion circuit 153. The boundary data acquisition circuit 151 is electrically connected to the second fitting circuit 152, and the second fitting circuit 152 is electrically connected to the second parameter conversion circuit 153.

[0115] In the embodiment of the present application, the boundary data acquisition circuit 151 is used to obtain the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the center positions of the inner and outer boundaries of the back-drilled hole and the positions of the inner and outer boundaries obtained by the back-drilled hole inner and outer boundary processing device 140. Specifically, the two-dimensional real-time image and the three-dimensional actual height image of the circuit board with the back-drilled hole are obtained simultaneously during the scanning process, and the two-dimensional real-time image and the three-dimensional actual height image have a one-to-one correspondence. Therefore, the boundary data acquisition circuit 151 can obtain the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the positional relationship between the center positions of the inner and outer boundaries of the back-drilled hole and the inner and outer boundaries obtained by the back-drilled hole inner and outer boundary processing device 140.

[0116] The second fitting circuit 152 is used to calculate and fit the first height plane and the second height plane according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image acquired by the boundary data acquisition circuit 151. Specifically, the second fitting circuit 152 obtains the height value of the annular area of ​​the back-drilled hole according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image acquired by the boundary data acquisition circuit 151, obtains the first height plane by fitting through the least square method, recorded as Z1, and obtains the second height plane by fitting inside the area 1.5 times the radius of the back-drilled hole and outside the outer contour boundary of the back-drilled hole, recorded as Z2.

[0117] The second parameter conversion circuit 153 is used to calculate the first distance between the center height of the back-drilled hole and the first height plane and the second distance between the first height plane and the second height plane, and convert the obtained first distance and second distance into the characteristic parameters of the back-drilled hole in the first coordinate system. Specifically, the first distance between the center height of the back-drilled hole and the first height plane is the height between the outer boundary of the back-drilled hole and the bottom of the center of the circle, and the second distance between the first height plane and the second height plane is the height value between the back-drilled hole of the circuit board and the outer boundary of the back-drilled hole. In the embodiment of the present application, the height resolution is about 12um / pixel, and the characteristic parameters of the back-drilled hole in the physical coordinate system are obtained by multiplying each height value calculated above by the corresponding resolution. In the exemplary embodiment of the present application, the characteristic parameters of the back-drilled hole include but are not limited to: the height value between the circuit board surface and the outer boundary of the back-drilled hole, the height value between the outer boundary of the back-drilled hole and the bottom of the center of the circle, etc.

[0118] See also Figure 7 , which is a flow chart of a back-drilled hole two-dimensional / three-dimensional feature measurement method disclosed in an embodiment of the present application, the above Figure 1-Figure 6 The back-drilled hole 2D / 3D feature measurement system in the illustrated embodiment uses the following back-drilled hole 2D / 3D feature measurement method to measure the 2D / 3D features of the back-drilled holes in the circuit board, thereby effectively improving the work efficiency of the circuit board production line. Figure 7 As shown, the back-drilled hole 2D / 3D feature measurement method includes at least the following steps.

[0119] S10, acquiring a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes by moving the motion platform at equal intervals.

[0120] In this embodiment, the image acquisition device 110 moves at equal intervals through a motion platform to simultaneously acquire a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes, and transmits the two-dimensional real-time image and the three-dimensional actual height image of the circuit board with back-drilled holes to the position acquisition device 120.

[0121] In the embodiments of this application, please refer to Figure 8 , the step S10 at least includes the following steps.

[0122] S11, acquiring a two-dimensional real-time image and a three-dimensional actual height image of the circuit boards with back-drilled holes in the current column by moving the motion platform at equal intervals along the first direction.

[0123] Specifically, the first direction may be the Y-axis direction of the motion platform, and the three-dimensional actual height image may be height data obtained by the laser triangulation principle. Figure 2As shown, when the measured point O of the measured object (i.e., the circuit board with back-drilled holes) moves or the surface height changes, the coordinate of the reference point P of the imaging point can be observed to change by x on the imaging surface of the camera. The principle of the laser triangulation method is:

[0124] According to the properties of similar triangles, we have:

[0125]

[0126] Among them, h is the surface height or displacement change of the object to be measured, l is the distance from the intersection of the laser optical axis and the camera optical axis to the center of the lens, that is, the object distance; d is the distance from the center of the lens to the camera image plane, that is, the image distance; α is the angle between the laser optical axis and the camera optical axis, that is, the angle between the laser plane and the camera optical axis; x is the distance from point P to point P1 on the camera image plane.

[0127] In order to ensure that the measured point O forms a clear real image on the camera image plane, the following formula must be satisfied:

[0128]

[0129] Where f is the focal length of the lens.

[0130] In the formula, combining formula (1) and formula (2), we can get:

[0131]

[0132] S12, acquiring a two-dimensional real-time image and a three-dimensional actual height image of the next row of circuit boards with back-drilled holes by moving the motion platform at equal intervals along the second direction.

[0133] The second direction is perpendicular to the first direction. In this embodiment, the second direction may be the X-axis direction.

[0134] S13, sequentially scanning the circuit board with the back-drilled holes along the second direction by the motion platform to obtain a two-dimensional real-time image and a three-dimensional actual height image of the entire circuit board with the back-drilled holes.

[0135] S20, performing fixed threshold segmentation on the acquired two-dimensional real-time image of the circuit board with back-drilled holes to obtain the position information of each back-drilled hole on the two-dimensional real-time image, and constructing the position information of each back-drilled hole and the preset standard data of the circuit board back-drilling board into a corresponding position conversion model to obtain the position of each back-drilled hole in the two-dimensional real-time image.

[0136] In this embodiment, the two-dimensional real-time image of the circuit board with back-drilled holes acquired by the image acquisition device 110 is segmented by a fixed threshold value through the position acquisition device 120 to obtain the position information of each back-drilled hole on the two-dimensional real-time image, and the position information of each back-drilled hole on the two-dimensional real-time image is constructed into a corresponding position conversion model with preset standard data of circuit board back-drilling board making to acquire the position of each back-drilled hole in the two-dimensional real-time image, and the position of each back-drilled hole in the two-dimensional real-time image is transmitted to the back-drilled hole center extraction device 130.

[0137] In the embodiments of this application, please refer to Fig. 9 , the step S20 at least includes the following steps.

[0138] S21, performing fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes and extracting contours, and calculating a centroid set of each contour point in the circuit board with back-drilled holes.

[0139] Specifically, the two-dimensional real-time image of the circuit board with back-drilled holes transmitted by the image acquisition device 110 is segmented by a fixed threshold value and the contour is extracted through the contour point calculation circuit 121, the centroid set of each contour point in the circuit board with back-drilled holes is calculated, and the centroid set of each contour point is transmitted to the feature hole acquisition circuit 122. Specifically, the contour point calculation circuit 121 can perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes transmitted by the image acquisition device 110 through the threshold function of the opencv library, and use cvFindContours to extract the contour of the circuit board with back-drilled holes, and calculate the centroid set {C1, C2, ..., Cn} of each contour point in the circuit board with back-drilled holes.

[0140] S22, screening the centroid sets of each of the contour points to obtain a preset number of global feature hole sets.

[0141] Specifically, the centroid sets of the contour points transmitted by the contour point calculation circuit 121 are screened by the feature hole acquisition circuit 122 to obtain a preset number of global feature hole sets. Specifically, the centroid sets of the contour points are screened so that the aspect ratio of the circumscribed rectangle of the contour is less than a set threshold value 1, and the global feature hole set is {C1', C2', ..., Cn'}.

[0142] S23. Obtain corresponding matching results according to the preset number of global feature hole sets.

[0143] In this embodiment, the matching result acquisition circuit 123 obtains the corresponding matching result according to the preset number of global feature hole sets obtained by the feature hole acquisition circuit 122. Specifically, in the embodiment of the present application, the matching result acquisition circuit 123 reads the standard hole data of the back drilling of the circuit board, and uses translation search to calculate the multiplication correlation coefficient of the global feature hole set {C1', C2', ..., Cn'} and the standard hole data with a set step size to obtain the corresponding matching result.

[0144] Wherein, the multiplication correlation coefficient calculation formula is:

[0145] G=STD_Template*REAL_Template formula (4)

[0146] Among them, REAL_Template is the real-time image ROI area corresponding to each moving step position.

[0147] S24. Calculate the secondary center position of the back-drilled hole in the corresponding circuit board according to the obtained matching result.

[0148] In this embodiment, the secondary center position calculation circuit 124 calculates the secondary center position of the back-drilled hole in the corresponding circuit board according to the matching result obtained by the matching result acquisition circuit 123. Specifically, in the embodiment of the present application, the secondary center position calculation circuit 124 corresponds the standard hole data of the back-drilled hole of the circuit board to the two-dimensional real-time image of the circuit board with the back-drilled hole according to the matching result obtained by the matching result acquisition circuit 123, and obtains the approximate center position and radius of the back-drilled hole corresponding to the two-dimensional real-time image of the circuit board with the back-drilled hole, and calculates the secondary center position of the back-drilled hole in the corresponding circuit board by the grayscale center of gravity calculation formula in a circular area with a preset radius as the center. Among them, the preset radius can be 1.5 cm, and the grayscale center of gravity formula is:

[0149]

[0150] S25. Calculate a position conversion model based on the center position of the obtained two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled hole making board to obtain the position of each back-drilled hole in the two-dimensional real-time image.

[0151] In this embodiment, the conversion model calculation circuit 125 calculates the position conversion model based on the center position of the two-dimensional real-time image of the circuit board with back-drilled holes obtained by the secondary center position calculation circuit 124 and the center position of the corresponding standard hole of the circuit board back-drilled board to obtain the position of each back-drilled hole in the two-dimensional real-time image. Specifically, the conversion model calculation circuit 125 calculates the affine transformation matrix of the center position of the two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled board to obtain the position conversion model to obtain the position of each back-drilled hole in the two-dimensional real-time image. The parameters of the affine transformation matrix can be estimated by the least squares method, and the calculation process is as follows:

[0152] Suppose the original image is f(x,y) and the transformed image is F(X',Y'). To restore F(X',Y') to f(x,y), we need to find the conversion relationship between (X',Y') coordinates and (x,y) coordinates. This conversion relationship is called coordinate transformation, expressed as (x,y)=T(X',Y').

[0153] The expression of affine transformation is: R(x)=Px+Q, x=(x,y) is the plane position of the pixel, P is the 2*2 rotation matrix, Q is the 2*1 translation vector, P and Q are the affine transformation parameters, that is:

[0154] x=AX'+BY'+C Formula (6)

[0155] y=DX'+EY'+F formula (7)

[0156] Therefore, it can be summarized as the solution of coordinate transformation coefficients A, B, C, D, E, and F. In order to prevent the occurrence of empty pixels, reverse mapping is generally used, and the least squares method is used to obtain:

[0157] vec1=inv([XYI]'*[XYI])*[XYI]'*U Formula (8)

[0158] vec2=inv([XYI]'*[XYI])*[XYI]'*V; Formula (9)

[0159] Among them, vec1 = [ABC]'; vec2 = [DEF]'; XYUVI are vectors composed of x, y, X', Y', 1 respectively.

[0160] S30, acquiring a ROI image of the location of each back-drilled hole according to the location of each back-drilled hole in the acquired two-dimensional real-time image, and acquiring the center of each back-drilled hole by calculation.

[0161] In this embodiment, the back-drilled hole center extraction device 130 is used to obtain an ROI image of the location of each back-drilled hole according to the location of each back-drilled hole in the two-dimensional real-time image obtained by the position acquisition device 120, obtain the center of each back-drilled hole by calculation, and transmit the center of the back-drilled hole to the back-drilled hole inner and outer boundary processing device 140.

[0162] In the embodiments of this application, please refer to Fig.10 , the step S30 at least includes the following steps.

[0163] S31. Acquire a ROI image at the center position of the two-dimensional real-time image according to the position conversion model.

[0164] Specifically, the ROI image acquisition circuit 131 acquires the ROI image of the center position on the two-dimensional real-time image according to the position conversion model transmitted by the position acquisition device 120. Specifically, the ROI image acquisition circuit 131 corresponds all the holes in the standard image to the two-dimensional real-time image according to the position conversion model transmitted by the position acquisition device 120, obtains the approximate center position and radius of all the back-drilled holes in the two-dimensional real-time image, and acquires the ROI image corresponding to the ROI area of ​​the back-drilled hole on the two-dimensional real-time image. The ROI area may be twice the radius of the center position of the back-drilled hole.

[0165] S32, performing adaptive threshold segmentation processing according to the ROI image of each back-drilled hole on the two-dimensional real-time image.

[0166] Specifically, the threshold segmentation processing circuit 132 performs adaptive threshold segmentation processing according to the ROI image of each back-drilled hole on the two-dimensional real-time image acquired by the ROI image acquisition circuit 131. Specifically, the threshold segmentation processing circuit 132 performs adaptive threshold segmentation according to the maximum variance principle within the inner and outer radius ranges of the back-drilled hole according to the ROI image of each back-drilled hole acquired by the region acquisition 131. The maximum variance principle is as follows:

[0167] Calculate the cumulative mean M of the gray level K and the global mean MG of the image:

[0168] Among them, P i is the probability value of the current gray level appearing, and the final inter-class variance formula of this embodiment is:

[0169]

[0170] Among them, the gray level K that maximizes the formula is the calculated segmentation threshold.

[0171] S33, calculating the corresponding three-time center positions of the back-drilled holes in the circuit board according to the obtained segmentation threshold.

[0172] Specifically, the tertiary center position calculation circuit 133 calculates the corresponding tertiary center position of the back-drilled hole in the circuit board according to the segmentation threshold obtained by the threshold segmentation processing circuit 132. Specifically, the tertiary center position calculation circuit 133 separates the target back-drilled hole from the background plane according to the segmentation threshold obtained by the threshold segmentation processing circuit 132, and then calculates the tertiary center position of the back-drilled hole in the circuit board through the grayscale centroid formula.

[0173] S40, performing double threshold segmentation according to the obtained center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculating the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

[0174] In this embodiment, the back-drilled hole inner and outer boundary processing device 140 performs double threshold segmentation according to the center of the back-drilled hole obtained by the back-drilled hole center extraction device 130 to obtain the inner and outer boundaries of the back-drilled hole, calculates the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, converts the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries, and transmits the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries of the back-drilled hole to the feature parameter generation device 150.

[0175] In the embodiments of this application, please refer to Fig.11 , the step S40 at least includes the following steps.

[0176] S41 . Calculate a first segmentation threshold and a second segmentation threshold according to the center of the back-drilled hole.

[0177] Specifically, the segmentation threshold calculation circuit 141 calculates the first segmentation threshold and the second segmentation threshold according to the center of the back-drilled hole transmitted by the back-drilled hole center extraction device 130. Specifically, the segmentation threshold calculation circuit 141 performs circular ROI area interception in the inner and outer radius areas of the back-drilled hole according to the center of the back-drilled hole transmitted by the back-drilled hole center extraction device 130, and performs adaptive segmentation using the maximum variance principle to obtain the first segmentation threshold and the second segmentation threshold.

[0178] S42, segmenting the target back-drilling area by using the acquired first segmentation threshold and second segmentation threshold, and fitting to obtain the center and radius of the inner circle boundary.

[0179] Specifically, the first fitting circuit 142 segments the target back-drilling area through the first segmentation threshold and the second segmentation threshold obtained by the segmentation threshold calculation circuit 141, and fits the center and radius of the inner circle boundary. Specifically, the first fitting circuit 142 segments the target back-drilling area through the first segmentation threshold and the second segmentation threshold obtained by the segmentation threshold calculation circuit 141, extracts the inner and outer boundary contour information of the target back-drilling, obtains the boundary position, and fits the center and radius of the inner circle boundary through the least squares method. Among them, the circle fitting is performed by the least squares method, and the optimization objective function of the square error is:

[0180]

[0181] Where: (x i ,y i )i=1,2,...,n are the coordinates of the feature points on the arc; n is the number of feature points involved in fitting. On the premise of maintaining the characteristics of the optimization objective function, in order to avoid the square root calculation, the error function is optimized. The meaning of formula (11) is that the minimum distance difference from all moving points to the fixed point becomes the minimum difference between the square of the distance from all moving points to the fixed point and the square of the radius, which is defined as follows:

[0182]

[0183] Then formula (12) is expanded to:

[0184]

[0185] At the same time, let B = -2y 0 , A=-2x 0 , That is, formula (13) can be expressed as:

[0186]

[0187] According to the principle of least squares method, parameters A, B, and C should make E obtain the minimum value. According to the method of finding the minimum value, A, B, and C should satisfy the following formula:

[0188]

[0189] Solve the system of equations and write it in matrix form to obtain formula (16):

[0190]

[0191] The parameters in formula (16) are calculated as follows:

[0192]

[0193]

[0194]

[0195]

[0196] So as to obtain the best fitting circle center coordinates (x 0 ,y 0 ), the fitted value of radius r:

[0197]

[0198] In this embodiment, when performing the least squares circle fitting, the number of fitting points has been determined, that is, the number of n is a known quantity, so x can be directly calculated using the above formula as a priori formula. 0 ,y 0 ,r three parameters.

[0199] S43. Calculate the eccentricity according to the obtained center and radius of the inner and outer boundaries.

[0200] Specifically, the eccentricity calculation circuit 143 calculates the eccentricity according to the center and radius of the inner and outer boundaries obtained by the first fitting circuit 142. Specifically, the center of the inner circle is (X 0 , Y 0 , R 0 ), the center of the outer circle is (X 1 , Y 1 , R 1 ), the corresponding eccentricity can be calculated according to the eccentricity formula. Wherein, the eccentricity formula is:

[0201]

[0202] S44. Obtain two-dimensional process parameters of inner and outer boundaries according to the obtained eccentricity.

[0203] Specifically, the process parameter acquisition circuit 144 acquires the two-dimensional process parameters of the inner and outer boundaries according to the eccentricity obtained by the eccentricity calculation circuit 143. For example, the calculation of the roundness process parameter in the two-dimensional process parameter is described as follows, the distance from all contour points on the circuit board with back-drilled holes to the center of the fitting circle is calculated, and then the roundness residual En is obtained by calculating the difference (i.e., absolute value) between the distance from each contour point on the circuit board with back-drilled holes to the center of the fitting circle and the radius R, and the mean of the roundness residual En is calculated, and finally (Rn-ave(En)) / Rn is used as the roundness process parameter.

[0204] S45, converting the two-dimensional process parameters of the back drilling into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

[0205] Specifically, the two-dimensional process parameters of the back drilling hole are converted into actual numerical parameters in the first coordinate system through the first parameter conversion circuit 145 to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries. Specifically, in the embodiment of the present application, all the parameters calculated above are the results in the image coordinate system, that is, the pixel unit, and the horizontal and vertical resolutions of the image are both 16um / pixel. The values ​​of the process parameters obtained by the above calculations are multiplied by the corresponding resolutions to obtain the actual numerical parameters in the first coordinate system.

[0206] S50, calculating characteristic parameters of the back-drilled hole on the three-dimensional actual height image according to the positional relationship between the inner and outer boundary circles and the inner and outer boundaries.

[0207] In the embodiments of this application, please refer to Fig.12 , the step S50 at least includes the following steps.

[0208] S51 , obtaining the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the obtained inner and outer boundary center positions and the inner and outer boundary positions of the back-drilled hole.

[0209] Specifically, the boundary data acquisition circuit 151 obtains the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the center positions of the inner and outer boundaries of the back-drilled hole and the positions of the inner and outer boundaries obtained by the back-drilled hole inner and outer boundary processing device 140. Specifically, the two-dimensional real-time image and the three-dimensional actual height image of the circuit board with the back-drilled hole are obtained simultaneously during the scanning process, and the two-dimensional real-time image and the three-dimensional actual height image have a one-to-one correspondence. Therefore, the boundary data acquisition circuit 151 can obtain the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the positional relationship between the center positions of the inner and outer boundaries of the back-drilled hole and the inner and outer boundaries obtained by the back-drilled hole inner and outer boundary processing device 140.

[0210] S52, calculating and fitting the first height plane and the second height plane according to the positions of the inner and outer boundaries of the back-drilled hole on the acquired three-dimensional actual height image.

[0211] Specifically, the second fitting circuit 152 calculates and fits the first height plane and the second height plane according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image acquired by the boundary data acquisition circuit 151. Specifically, the second fitting circuit 152 obtains the height value of the annular area of ​​the back-drilled hole according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image acquired by the boundary data acquisition circuit 151, obtains the first height plane by fitting through the least square method, recorded as Z1, and obtains the second height plane by fitting inside the area 1.5 times the radius of the back-drilled hole and outside the outer contour boundary of the back-drilled hole, recorded as Z2.

[0212] S53, calculating a first distance between the center height of the back-drilled hole and the first height plane and a second distance between the first height plane and the second height plane, and converting the obtained first distance and second distance into characteristic parameters of the back-drilled hole in a first coordinate system.

[0213] Specifically, the first distance between the center height of the back-drilled hole and the first height plane and the second distance between the first height plane and the second height plane are calculated by the second parameter conversion circuit 153, and the obtained first distance and second distance are converted into characteristic parameters of the back-drilled hole in the first coordinate system. Specifically, the first distance between the center height of the back-drilled hole and the first height plane is the height between the outer boundary of the back-drilled hole and the bottom of the center of the circle, and the second distance between the first height plane and the second height plane is the height value between the back-drilled hole of the circuit board and the outer boundary of the back-drilled hole. In the embodiment of the present application, the height resolution is about 12um / pixel, and the characteristic parameters of the back-drilled hole in the physical coordinate system are obtained by multiplying each height value calculated above by the corresponding resolution. In the exemplary embodiment of the present application, the characteristic parameters of the back-drilled hole include but are not limited to: the height value between the circuit board surface and the outer boundary of the back-drilled hole, the height value between the outer boundary of the back-drilled hole and the bottom of the center of the circle, etc.

[0214] In summary, the back-drilled hole 2D / 3D feature measurement method provided in the present application can realize the detection of circuit boards, thereby effectively improving the working efficiency of the circuit board production line and improving the market competitiveness of the products.

[0215] See also Fig.13 , which is a hardware structure diagram of a back-drilled hole two-dimensional / three-dimensional feature measurement device disclosed in an embodiment of the present application. Fig.13As shown, the back-drilled hole 2D / 3D feature measurement device 200 provided in the embodiment of the present application includes at least one processor 201 and a memory 202. The back-drilled hole 2D / 3D feature measurement device 200 also includes at least one bus 203. The processor 201 and the memory 202 are electrically connected through the bus 203. The back-drilled hole 2D / 3D feature measurement device 200 can be a computer or a server, which is not particularly limited in the present application.

[0216] The back-drilled hole 2D / 3D feature measuring device 200 may also include the above Figures 1 to 6 In the embodiment shown, the back-drilled hole 2D / 3D feature measurement system. In a specific implementation process, at least one processor 201 executes the computer-executable instructions stored in the memory 202, so that at least one processor 201 performs the following through the back-drilled hole 2D / 3D feature measurement system: Figure 7-Figure 12 The back-drilled hole 2D / 3D feature measurement method of the embodiment.

[0217] The specific implementation process of the processor 201 provided in the embodiment of the present application can be referred to above Figure 7-Figure 12 The implementation principle and technical effect of the back-drilled hole 2D / 3D feature measurement method embodiment of the embodiment are similar, and this embodiment will not be repeated here.

[0218] It can be understood that the processor 201 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method provided in the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0219] The memory 202 may be a high-speed random access memory (RAM) or a non-volatile memory (NVM).

[0220] The bus 203 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. For ease of representation, the bus 203 in the drawings of the present application is not limited to only one bus or one type of bus.

[0221] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A back-drilled hole 2D / 3D feature measurement system, characterized in that: include: An image acquisition device, used for acquiring a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes by moving the motion platform at equal intervals; A position acquisition device, electrically connected to the image acquisition device, for performing fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes to obtain position information of each back-drilled hole on the two-dimensional real-time image, and constructing a corresponding position conversion model with the position information of each back-drilled hole on the two-dimensional real-time image and preset standard data of the circuit board back-drilled hole manufacturing to obtain the position of each back-drilled hole in the two-dimensional real-time image; A back-drilled hole center extraction device, electrically connected to the position acquisition device, and used to acquire an image of a region of interest at the location of each back-drilled hole according to the location of each back-drilled hole in the two-dimensional real-time image, and to acquire the center of each back-drilled hole; a back-drilled hole inner and outer boundary processing device, electrically connected to the back-drilled hole center extraction device, the back-drilled hole inner and outer boundary processing device is used to perform double threshold segmentation according to the center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculate the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and convert the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries; A feature parameter generating device is electrically connected to the inner and outer boundary processing device of the back-drilled hole, and is used to calculate the feature parameters of the back-drilled hole on the three-dimensional actual height image transmitted by the image acquisition device according to the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

2. The back-drilled hole 2D / 3D feature measurement system according to claim 1, characterized in that: The image acquisition device includes a camera and a line laser, wherein the line laser emits a laser line, and an angle between the line laser and the camera is a preset angle.

3. The back-drilled hole 2D / 3D feature measurement system according to claim 1, characterized in that: The position acquisition device includes a contour point calculation circuit, a feature hole acquisition circuit, a matching result acquisition circuit, a secondary center position calculation circuit and a conversion model calculation circuit, wherein: The contour point calculation circuit is used to perform fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes and extract contours, calculate the centroid set of each contour point in the circuit board with back-drilled holes, and transmit the centroid set of each contour point to the feature hole acquisition circuit; The characteristic hole acquisition circuit is electrically connected to the contour point calculation circuit, and the characteristic hole acquisition circuit is used to screen the centroid sets of each of the contour points to obtain a preset number of global characteristic hole sets; The matching result acquisition circuit is electrically connected to the characteristic hole acquisition circuit, and the matching result acquisition circuit is used to obtain the corresponding matching result according to the preset number of global characteristic hole sets; The secondary center position calculation circuit is electrically connected to the matching result acquisition circuit, and the secondary center position calculation circuit is used to calculate the corresponding secondary center position of the back-drilled hole in the circuit board according to the matching result; The conversion model calculation circuit is electrically connected to the secondary center position calculation circuit, and the conversion model calculation circuit is used to calculate a position conversion model based on the center position of the two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled hole making board to obtain the position of each back-drilled hole in the two-dimensional real-time image.

4. The back-drilled hole 2D / 3D feature measurement system according to claim 1, characterized in that: The back-drilling hole center extraction device includes an area of ​​interest image acquisition circuit, a threshold segmentation processing circuit and a three-time center position calculation circuit, wherein: The region of interest image acquisition circuit is used to acquire the region of interest image at the center position on the two-dimensional real-time image according to the position conversion model; The threshold segmentation processing circuit is electrically connected to the region of interest image acquisition circuit, and the threshold segmentation processing circuit is used to perform adaptive threshold segmentation processing according to the region of interest image of each back-drilled hole on the two-dimensional real-time image; The third-order center position calculation circuit is electrically connected to the threshold segmentation processing circuit, and the third-order center position calculation circuit is used to calculate the corresponding third-order center position of the back-drilled hole in the circuit board according to the segmentation threshold.

5. The back-drilled hole 2D / 3D feature measurement system according to claim 1, characterized in that: The back-drilling hole inner and outer boundary processing device comprises a segmentation threshold calculation circuit, a first fitting circuit, an eccentricity calculation circuit, a process parameter acquisition circuit and a first parameter conversion circuit, wherein: The segmentation threshold calculation circuit is used to calculate the first segmentation threshold and the second segmentation threshold according to the center of the back-drilled hole; The first fitting circuit is electrically connected to the segmentation threshold calculation circuit, and the first fitting circuit is used to segment the target back-drilling area according to the first segmentation threshold and the second segmentation threshold, and to obtain the center and radius of the inner and outer boundaries by fitting; The eccentricity calculation circuit is electrically connected to the first fitting circuit, and the eccentricity calculation circuit is used to calculate the eccentricity according to the center and radius of the inner and outer boundaries; The process parameter acquisition circuit is electrically connected to the eccentricity calculation circuit, and the process parameter acquisition circuit is used to acquire the two-dimensional process parameters of the inner and outer boundaries according to the eccentricity; The first parameter conversion circuit is electrically connected to the process parameter acquisition circuit, and is used for converting the two-dimensional process parameters into actual numerical parameters in a first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries.

6. The back-drilled hole 2D / 3D feature measurement system according to claim 1, characterized in that: The characteristic parameter generating device comprises a boundary data acquisition circuit, a second fitting circuit and a second parameter conversion circuit, wherein: The boundary data acquisition circuit is used to obtain the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image according to the center positions of the inner and outer boundaries and the positions of the inner and outer boundaries; The second fitting circuit is electrically connected to the boundary data acquisition circuit, and the second fitting circuit is used to calculate and fit the first height plane and the second height plane according to the positions of the inner and outer boundaries of the back-drilled hole on the three-dimensional actual height image; The second parameter conversion circuit is electrically connected to the second fitting circuit, and the second parameter conversion circuit is used to calculate the first distance between the first height planes and the second distance between the first height plane and the second height plane, and convert the obtained first distance and second distance into characteristic parameters of the back drilling hole in the first coordinate system.

7. A back-drilled hole 2D / 3D feature measurement method, performed by the back-drilled hole 2D / 3D feature measurement system according to any one of claims 1 to 6, characterized in that: The back-drilled hole two-dimensional / three-dimensional feature measurement method comprises: The motion platform is moved at equal intervals to obtain a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes; Performing fixed threshold segmentation on the acquired two-dimensional real-time image of the circuit board with back-drilled holes to obtain position information of each back-drilled hole on the two-dimensional real-time image, and constructing a corresponding position conversion model with the position information of each back-drilled hole and the preset standard data of the circuit board back-drilled hole manufacturing to obtain the position of each back-drilled hole in the two-dimensional real-time image; Acquire an image of a region of interest at the location of each back-drilled hole according to the location of each back-drilled hole in the acquired two-dimensional real-time image, and acquire the center of each back-drilled hole by calculation; Performing double threshold segmentation according to the obtained center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculating the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries; The characteristic parameters of the back-drilled hole are calculated on the three-dimensional actual height image according to the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries.

8. The back-drilled hole 2D / 3D feature measurement method according to claim 7, characterized in that: The method of acquiring a two-dimensional real-time image and a three-dimensional actual height image of a circuit board with back-drilled holes by moving the motion platform at equal intervals includes: Acquire a two-dimensional real-time image and a three-dimensional actual height image of the circuit board with back-drilled holes in the current column by moving the motion platform at equal intervals along the first direction; Acquire a two-dimensional real-time image and a three-dimensional actual height image of the next row of the circuit boards with back-drilled holes by moving the motion platform at equal intervals along a second direction, wherein the second direction is perpendicular to the first direction; The circuit board with the back-drilled holes is scanned in sequence along the second direction by the motion platform to obtain a two-dimensional real-time image and a three-dimensional actual height image of the entire circuit board with the back-drilled holes.

9. The back-drilled hole 2D / 3D feature measurement method according to claim 8, characterized in that: The method of performing fixed threshold segmentation on the acquired two-dimensional real-time image of the circuit board with back-drilled holes to obtain position information of each back-drilled hole on the two-dimensional real-time image, and constructing a corresponding position conversion model based on the position information of each back-drilled hole and preset standard data of the circuit board back-drilled hole manufacturing to obtain the position of each back-drilled hole in the two-dimensional real-time image, includes: Performing fixed threshold segmentation on the two-dimensional real-time image of the circuit board with back-drilled holes and extracting contours, and calculating a centroid set of each contour point in the circuit board with back-drilled holes; Screening the centroid sets of each of the contour points to obtain a preset number of global feature hole sets; Obtaining corresponding matching results according to the preset number of global feature hole sets; Calculate the secondary center position of the back-drilled hole in the corresponding circuit board according to the obtained matching result; A position conversion model is calculated based on the center position of the obtained two-dimensional real-time image of the circuit board with back-drilled holes and the center position of the corresponding standard hole of the circuit board back-drilled hole making board to obtain the position of each back-drilled hole in the two-dimensional real-time image.

10. The back-drilled hole 2D / 3D feature measurement method according to claim 9, characterized in that: The step of obtaining an image of a region of interest at the location of each back-drilled hole according to the location of each back-drilled hole in the acquired two-dimensional real-time image, and obtaining the center of each back-drilled hole by calculation, comprises: Acquire an image of a region of interest at a central position on the two-dimensional real-time image according to the position conversion model; Performing adaptive threshold segmentation processing according to the region of interest image of each back-drilled hole on the two-dimensional real-time image; The three center positions of the corresponding back-drilled holes in the circuit board are calculated according to the obtained segmentation threshold.

11. The back-drilled hole 2D / 3D feature measurement method according to claim 10, characterized in that: The method of performing double threshold segmentation according to the obtained center of the back-drilled hole to obtain the inner and outer boundaries of the back-drilled hole, calculating the two-dimensional process parameters of the inner and outer circle centers of the back-drilled hole, and converting the two-dimensional process parameters of the back-drilled hole into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary centers and the inner and outer boundaries, includes: Calculating a first segmentation threshold and a second segmentation threshold according to the center of the back-drilled hole; The target back-drilling area is segmented by using the first segmentation threshold and the second segmentation threshold, and the center and radius of the inner and outer boundaries are obtained by fitting; The eccentricity is calculated based on the center and radius of the inner and outer boundaries; Obtain two-dimensional process parameters of inner and outer boundaries according to the obtained eccentricity; The two-dimensional process parameters of the back drilling hole are converted into actual numerical parameters in the first coordinate system to obtain the positional relationship between the inner and outer boundary circle centers and the inner and outer boundaries.

12. The back-drilled hole 2D / 3D feature measurement method according to claim 11, characterized in that: The characteristic parameters of the back drilling hole are calculated on the three-dimensional actual height image according to the positional relationship between the inner and outer boundary centers and the inner and outer boundaries, including: According to the obtained inner and outer boundary center positions and the inner and outer boundary positions of the back-drilled hole, the center height data of the back-drilled hole and the positions of the inner and outer boundaries on the three-dimensional actual height image are obtained; The first height plane and the second height plane are calculated and fitted according to the positions of the inner and outer boundaries of the back-drilled hole on the acquired three-dimensional actual height image; A first distance between the center height of the back-drilled hole and the first height plane and a second distance between the first height plane and the second height plane are calculated, and the obtained first distance and second distance are converted into characteristic parameters of the back-drilled hole in a first coordinate system.

13. A back-drilled hole 2D / 3D feature measurement device, characterized in that: include: At least one processor and a memory, at least one of the processors executes computer-executable instructions stored in the memory, and at least one of the processors executes the back-drilling two-dimensional / three-dimensional feature measurement method according to any one of claims 7 to 12.

Images