Concentricity detection system, method, equipment and medium

Abstract

The invention relates to the technical field of metering detection, in particular to a concentricity detection system, method, equipment and medium, the system is used for completing concentricity detection of an OCA film laminating process by a laminating machine, and the system comprises a detection module, a processing module and a display module, the visual unit is used for acquiring image information in a corresponding area of a pasted product when the light source module provides different bright and dark light sources at different positions; the light source module is used for providing different bright and dark light sources at different positions; the adjusting module is used for adjusting different positions of the light source module; the light source direction is directly obtained to eliminate refraction errors, the light source position is dynamically adjusted to compensate curved surface reflection differences, high-precision curved surface reconstruction is achieved based on a multi-angle image sequence, the concentricity detection precision of a transparent film and a curved surface base material is effectively improved, and the detection requirements of pasted products with different curvature shapes are met; the technical problem that in the prior art, a detection system is not high in accuracy when used for detecting the concentricity of a curved surface is solved.

Description

Technical Field

[0001] The present invention relates to the field of measurement and detection technology, and in particular to a concentricity detection system, method, equipment and medium. Background Art

[0002] The current industrial inspection field mainly relies on traditional photometric stereo vision technology to measure the concentricity of curved surfaces. This method has two significant drawbacks: First, in the light source calibration process, a calibration sphere is needed to estimate the direction. The direction of the light source must be inferred by the light spot reflected by the ceramic sphere. This indirect measurement method will produce refraction errors due to the transparent material in the OCA film bonding scenario.

[0003] Secondly, existing systems generally use fixed light source arrays, which limits the range of light source angle variation.

[0004] When the product being coated has a curved surface, the varying reflectivity of the surface due to changes in the angle of the curve increases, resulting in localized overexposure or underexposure, which seriously affects the accuracy of normal vector estimation. These limitations result in relatively low accuracy in existing systems when detecting the concentricity of transparent films and curved substrates. Summary of the Invention

[0005] The main purpose of the present invention is to provide a concentricity detection system, method, equipment and medium, aiming to solve the technical problem that the detection system in the prior art has low accuracy when performing concentricity detection on a curved surface.

[0006] To achieve the above objectives, the present invention provides a concentricity detection system, which is used for a laminating machine to complete the concentricity detection of the OCA film laminating process. The laminating machine includes a laminating module, which is used to complete the laminating process of the laminating film on the product to be laminarized. The system includes: Light source module, used to provide different light sources at different locations; The detection module includes a visual unit and a detection unit, wherein the visual unit is used to obtain image information in a corresponding area of ​​the attached product when the light source module provides different light sources of different brightness and darkness at different positions; An adjustment module is provided in the laminating machine and is used to adjust different positions of the light source module; Wherein, the detection unit includes: An acquisition subunit, used to acquire the light source direction of image information at different positions; An estimation subunit, used to estimate the surface normal vector of the product being pasted so as to perform interpolation fitting on the surface normal vector; The processing subunit is used to solve the depth information of the boundary surface of the product being pasted; The detection subunit is used to restore the surface curvature of the product being adhered and to detect the concentricity with the laminating film.

[0007] Optionally, the adjustment module includes an adjustment seat and an adjustment unit, the adjustment seat is fixedly connected to the inner wall of the laminating machine, a first driving unit is provided in the adjustment seat, the output end of the first driving unit is connected to the adjustment unit so that the adjustment unit rotates circumferentially along the output end of the first driving unit, and the light source module is provided on the adjustment unit.

[0008] Optionally, the adjustment unit includes an adjustment inner rod and an adjustment outer rod, one end of the adjustment outer rod is connected to the output end of the first driving unit, the other end of the adjustment outer rod is rotatably arranged with the adjustment inner rod, and the light source module is arranged on the adjustment inner rod.

[0009] Optionally, a second driving unit is provided at a connection portion between the adjusting outer rod and the adjusting inner rod, so that the adjusting inner rod rotates circumferentially along an output end of the second driving unit.

[0010] Optionally, a slide rail is provided on a side of the adjusting inner rod close to the fitting module, and the light source module is provided on the slide rail so that the light source module moves along the slide rail.

[0011] Optionally, the number of the adjustment modules is 2, and they are arranged axially symmetrically with respect to the axis of the fitting module.

[0012] Optionally, the inner adjustment rod and the outer adjustment rod are quarter sector ring structures with different diameters.

[0013] A concentricity detection method, comprising the following steps: Controlling the adjustment module to rotate so that the light source module passes through different positions when the adjustment module rotates outside the attached product; Obtain image information in the corresponding area of ​​the product when the light source module provides different light levels at different positions; receiving image information; Obtain the light source direction at different positions of the image information; Estimate the surface normal vector of the product being pasted to perform interpolation fitting on the surface normal vector; Calculate the depth information of the boundary surface of the product being pasted; Restore the surface curvature of the laminated product and detect the concentricity with the laminated film.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program.

[0015] A computer-readable storage medium stores a computer program, and a processor executes the computer program.

[0016] The beneficial effects that can be achieved by the present invention are as follows: This invention directly obtains the light source direction through the mechanical displacement of the adjustment module, avoiding interference from refraction of transparent materials. Existing fixed light source arrays are limited by installation angles. The use of movable light source modules expands the illumination angle coverage and effectively suppresses overexposure or underexposure caused by surface reflection differences. Traditional photometric stereo algorithms require separate light source calibration. This solution synchronizes light source adjustment with the image acquisition process and automatically associates the light source direction with mechanical motion parameters. In addition, the present invention eliminates refraction errors by directly obtaining the direction of the light source, dynamically adjusts the position of the light source to compensate for the reflection difference of the curved surface, and realizes high-precision curved surface reconstruction based on multi-angle image sequences, thereby effectively improving the concentricity detection accuracy of the transparent film and the curved surface substrate, adapting to the detection needs of the products with different curvature shapes, and solving the technical problem of low accuracy of the detection system in the prior art when performing concentricity detection of the curved surface, thereby realizing high-precision bonding of the OCA film before and after processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0018] Figure 1 Schematic diagram of the structure of the laminating module and the adjusting module in Example 1 of the present invention; Figure 2 Schematic diagram of the structure of the adjustment module in Example 1 of the present invention; Figure 3 Schematic diagram of the process of the method in Example 2 of the present invention.

[0019] Reference numerals: 1- laminating module, 2- adjustment module, 3- light source module, 4- laminating product; 21-adjustment seat, 22-adjustment unit; 221 - adjusting inner rod, 222 - adjusting outer rod, 223 - second driving unit, 224 - slide rail.

[0020] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship and movement status of various components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0023] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixed" should be understood in a broad sense. For example, "connection" can mean fixed connection, detachable connection, or integration; it can mean mechanical connection or electrical connection; it can mean direct connection or indirect connection through an intermediate medium; it can mean internal communication between two elements or interaction between two elements, unless otherwise specified. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme in which A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0025] Example 1 Refer to the attached Figure 1 With attached Figure 2 This embodiment provides a concentricity detection system, which is used for a laminating machine to complete the concentricity detection of the OCA film laminating process. The laminating machine includes a laminating module 1, which is used to complete the laminating process of the laminating film on the laminating product 4. The system includes: Light source module 3, used to provide different light sources at different locations; The detection module includes a visual unit and a detection unit. The visual unit is used to obtain image information in the corresponding area of ​​the attached product 4 when the light source module 3 provides different light sources of different brightness and darkness at different positions; An adjustment module 2 is provided in the laminating machine and is used to adjust different positions of the light source module 3; Wherein, the detection unit includes: An acquisition subunit, used to acquire the light source direction of image information at different positions; The estimation subunit is used to estimate the surface normal vector of the product 4 to perform interpolation fitting on the surface normal vector; The processing subunit is used to solve the depth information of the boundary surface of the product 4; The detection subunit is used to restore the surface curvature of the adhered product 4 and detect the concentricity with the laminating film.

[0026] It should be noted that the detection module proposed in this embodiment refers to a composite module consisting of an image acquisition device (visual unit) and a data processing unit (detection unit), preferably an industrial camera and an image processor, and the visual unit collects image information under multiple light source angles.

[0027] In some embodiments, the light source module 3 refers to an optical emitting device with adjustable position, which can be implemented by using an LED array in conjunction with a mechanical adjustment mechanism to produce brightness changes by changing the incident angle of the light source; In some embodiments, the adjustment module 2 refers to a driving device for controlling the spatial position of the light source, which can be implemented by a servo motor and a transmission mechanism, and changes the relative position of the light source and the measured surface through mechanical movement.

[0028] In some embodiments, the acquisition subunit refers to a light source direction analysis unit, which can be specifically implemented using a light path tracing algorithm / model to calculate the incident direction based on the Lambertian reflection model principle according to the physical position of the light source.

[0029] In some embodiments, the estimation subunit may be implemented using a photometric stereo algorithm to derive a normal vector through light intensity changes in multiple images.

[0030] In some embodiments, the processing sub-unit refers to a three-dimensional surface reconstruction unit, which can be specifically implemented by using a Poisson equation solving algorithm to calculate depth information through normal vector integration.

[0031] In some embodiments, the detection subunit refers to a concentricity analysis unit, which can be specifically implemented using a point cloud registration algorithm to calculate the fitting deviation through surface morphology comparison.

[0032] It should also be noted that the OCA film bonding process is briefly described here. Before the OCA film bonding process, the polarizer is the core optical element of the LCD module, and its absorption axis direction must be precisely aligned. When attached to the glass substrate, its edge (or preset mark point) must be precisely aligned with the reference mark on the substrate. For the OCA film bonding process itself, OCA acts as an adhesive layer, and its bonding accuracy directly determines the relative position between the cover glass and the display module below. After the OCA film is bonded, the LCM module that has completed OCA bonding needs to be finally assembled with the backlight module, FPC (flexible circuit board), middle frame / bracket and other components. It is necessary to ensure that the mechanical reference and electrical connection position of the overall component are accurate.

[0033] It can be understood that in the above-mentioned OCA film bonding process, the adjustment module 2 drives the light source module 3 to move along a predetermined trajectory, so that the surface of the product to be tested is sequentially exposed to light and dark illumination at different angles, and the visual unit synchronously collects the image information sequence at each position. The acquisition subunit directly calculates the light source direction based on the physical displacement of the light source module 3, eliminating the refraction error caused by the traditional calibration sphere. The estimation subunit establishes a mapping relationship between the surface normal vector and the illumination direction based on the image grayscale changes under multi-angle illumination, and uses cubic spline interpolation to compensate for the data missing of discrete sampling points; the processing subunit converts the discrete normal vector field into a continuous surface function, and solves the depth distribution of the boundary surface through numerical integration; the detection subunit spatially matches the reconstructed surface model with the standard bonding film contour, and calculates the offset of the central axis of the two as the concentricity index.

[0034] In some embodiments, the synchronously collected image information sequence is not less than 3 images. In other embodiments, the synchronously collected image information sequence can be understood as multiple images of different brightness and darkness of the light source module 3 under the same position conditions. This situation is particularly suitable for the same bonding batch; it can also be understood as multiple images collected under the same brightness and darkness or different brightness and darkness conditions after the light source module 3 changes the angle of the light source module 3 under the same position conditions. This situation is particularly suitable for bonding processes with increased detection accuracy. Similarly, the light source module 3 in this case can also perform image acquisition under different position conditions to further improve its detection accuracy. This is particularly suitable for bonding detection operations after changing product batches. It can be understood that the above-mentioned setting of the position and brightness (brightness) of the light source module 3 is only a preferred choice. The specific position and brightness of the light source module 3 can be macro-adjusted during image acquisition, that is, different brightness and darkness light sources are provided at different positions.

[0035] In some embodiments, the laminating machine can be understood as an automated device that achieves precise lamination between the four layers of the product being laminated; In some embodiments, the laminating film can be understood as an OCA film, a polarizer, a cover glass, etc.

[0036] In some embodiments, the laminating module 1 can be understood as an automated structure with a laminating pressure head.

[0037] In some embodiments, the adhered product 4 can be understood as an electronic product, preferably including mobile devices, tablet computers, car displays, and other display products with curved screens.

[0038] In some embodiments, the concentricity detection in this embodiment can be understood as a process of detecting / comparing the center and boundary of the laminated product 4 with the center and boundary of the laminated film during the laminating process of the laminated film; similarly, it can also be understood as a process of detecting the concentricity / matching degree of the laminated film on the laminating surface after the laminated film is completed.

[0039] It can also be understood that the traditional method relies on the calibration sphere to indirectly infer the direction of the light source. The technical solution in this embodiment directly obtains the direction of the light source by adjusting the mechanical displacement of the module 2, avoiding the interference of refraction of transparent materials. The existing fixed light source array is limited by the installation angle. The movable light source module 3 is used to expand the coverage range of the illumination angle and effectively suppress the overexposure or underexposure caused by the reflection difference of the curved surface. The traditional photometric stereo algorithm requires separate light source calibration. This solution synchronizes the light source adjustment with the image acquisition process and automatically associates the light source direction through mechanical motion parameters.

[0040] In addition, the technical solution in this embodiment can directly obtain the direction of the light source to eliminate refraction errors, dynamically adjust the position of the light source to compensate for the reflection differences of the curved surface, and achieve high-precision curved surface reconstruction based on multi-angle image sequences, effectively improving the concentricity detection accuracy of transparent films and curved substrates, and adapting to the detection needs of products 4 with different curvature shapes. It solves the technical problem of low accuracy of the detection system in the existing technology when performing concentricity detection of curved surfaces, and realizes high-precision bonding of the OCA film before and after processes.

[0041] In some embodiments, the light source module 3 is connected to the slide rail 224 through a rotating platform, that is, the light source module 3 can rotate relative to it. It can be understood that the rotating platform preferably includes a slider structure, the slider cooperates with the slide rail 224, and a motor is provided in the slider. The output end of the motor is connected to the light source module 3 through a reducer and other structures. The motor is also connected to the control module signal of the detection system so that it can be controlled by the control module to adjust its angle.

[0042] In some embodiments, the control module of the detection system serves as the core processing unit between modules to realize data acquisition and synchronous control. In addition, it also takes into account data processing and motion control. Similarly, the control module is also connected to the interactive module signal. Its preferred models include: NI cRIO-9045, Beckhoff CX2040, or Siemens S7-1200, etc. Its specific control logic is not repeated here.

[0043] In this embodiment, the adjustment module 2 includes an adjustment seat 21 and an adjustment unit 22. The adjustment seat 21 is fixedly connected to the inner wall of the laminating machine. A first driving unit is provided in the adjustment seat 21. The output end of the first driving unit is connected to the adjustment unit 22 so that the adjustment unit 22 rotates circumferentially along the output end of the first driving unit. The light source module 3 is provided on the adjustment unit 22.

[0044] It should be noted that the adjustment base 21 refers to a support structure fixedly connected to the inner wall of the laminating machine, which can be implemented as a metal frame structure and is used to provide a stable installation base for the adjustment unit 22; wherein, the first drive unit refers to a power device arranged inside the adjustment base 21, which can be implemented as a servo motor or a stepper motor, and transmits rotational power through the output shaft to drive the adjustment unit 22 to move. Preferably, the output shaft is also preferably connected to the adjustment unit 22 through a structure such as a reducer to optimize the transmission torque. The adjustment unit 22 refers to a mechanical component connected to the output end of the first drive unit, preferably a rod-shaped structure with a curvature, which is used to convert the rotational motion into the circular motion trajectory of the light source module 3.

[0045] It should also be noted that the adjustment seat 21 forms a rigid support by being fixedly connected to the inner wall of the laminating machine, ensuring that the light source module 3 remains stable during movement. The first drive unit drives the adjustment unit 22 to rotate around its axis through the output shaft, so that the light source module 3 moves along a circular path, thereby dynamically adjusting the position of the light source relative to the product 4 being adhered. When the light source module 3 rotates with the adjustment unit 22, it can cover a wider angle range, avoiding the problem of limited illumination angle caused by a fixed light source array. Through the combination of mechanical transmission and drive control, the position of the light source module 3 can be continuously adjusted according to detection requirements, providing uniform and multi-angle light source conditions for different curved surface areas.

[0046] Based on the above structure, the active position adjustment of the light source module 3 is realized through the rotatable adjustment unit 22, breaking through the static layout limitation of the fixed light source and dynamically expanding the angle change range of the light source, thereby reducing local overexposure or underexposure; the continuous adjustment of the light source position is also realized through mechanical drive, the angle coverage range of the light source is expanded, and the exposure abnormality problem caused by the difference in the reflectivity of the curved surface is improved, providing more complete lighting data for subsequent image processing, thereby improving the accuracy of normal vector estimation and concentricity detection.

[0047] In some embodiments, when the light source module 3 is laminating the same batch of laminating films, the differences between the laminating films and the laminating products 4 in the same batch are relatively small, and the distance that the adjustment module 2 moves its position is also relatively small. Subsequent detection and processing can be performed through different light sources of different brightness and darkness at the same position. Similarly, the detection system in this embodiment is particularly suitable for high-precision detection and positioning operations after changing product batches.

[0048] In this embodiment, the adjustment unit 22 includes an adjustment inner rod 221 and an adjustment outer rod 222, one end of the adjustment outer rod 222 is connected to the output end of the first driving unit, and the other end of the adjustment outer rod 222 is rotatably set with the adjustment inner rod 221, and the light source module 3 is set on the adjustment inner rod 221.

[0049] It should be noted that the outer adjustment rod 222 refers to a rigid rod-shaped component connected to the output end of the drive unit. Specifically, it can be implemented by a hollow rod body made of aluminum alloy, which is used to transmit rotational power and form a primary rotation axis. The inner adjustment rod 221 refers to a rod-shaped component that is rotatably connected to the end of the outer adjustment rod 222. Specifically, it can be made of carbon fiber composite material, which is used to support the light source module 3 and form a secondary rotation axis. The rotation setting refers to the relative rotation between the two components through a bearing or hinge structure. Specifically, it can be achieved by using a micro servo motor to drive a gear transmission mechanism, so that the inner adjustment rod 221 can adjust the angle in three dimensions around the connection point.

[0050] It should also be noted that the outer adjustment rod 222 is driven by the first drive unit to rotate circumferentially around the axis of the bonding module 1, driving the inner adjustment rod 221 to move along a circular trajectory as a whole. The rotational connection between the inner adjustment rod 221 and the outer adjustment rod 222 allows the light source module 3 to adjust its angle in a direction perpendicular to the plane of the circular trajectory, forming a spatial composite motion trajectory; the light source module 3 is installed at the end of the inner adjustment rod 221, and its incident angle changes in three dimensions with the double-rod linkage structure, which can cover the incident angle within a large range of the normal direction of the curved surface of the adhered product 4, avoiding abnormal reflectivity caused by excessively large or small incident angles.

[0051] Compared with the existing technology, the traditional fixed light source array can only provide incident light with limited discrete angles and cannot adapt to the continuously changing normal direction of the curved surface. The technical solution requested for protection in this embodiment forms a continuously adjustable light source incident angle through a double-rod linkage structure, so that the light source module 3 can move continuously or intermittently in three-dimensional space, and the light source module 3 has the ability to adjust the pitch angle, effectively eliminating the blind spot of curved surface detection.

[0052] In addition, the incident angle of the light source can dynamically match the change in the direction of the surface normal, eliminating local overexposure or underexposure caused by the mismatch between the fixed light source angle and the reflective characteristics of the curved surface. The light source module 3 forms a composite motion trajectory under dual-axis drive, ensuring that all areas of the curved surface receive uniform and appropriate light intensity, providing high signal-to-noise ratio image data for subsequent normal vector estimation, thereby improving the concentricity detection accuracy of the transparent film and the curved substrate.

[0053] In this embodiment, a second driving unit 223 is provided at the connection portion between the adjusting outer rod 222 and the adjusting inner rod 221 , so that the adjusting inner rod 221 rotates circumferentially along the output end of the second driving unit 223 .

[0054] It should be noted that when the first drive unit drives the outer rod 222 to rotate about the axis of the laminating module 1, the second drive unit 223 simultaneously drives the inner rod 221 to rotate about its own axis. Under the coordinated control of the two drive units, the light source module 3 forms a composite motion trajectory, and its illumination angle coverage range is expanded from a single plane to three-dimensional space. When it is necessary to detect the surface curvature of the adhered product 4, the light source module 3 adjusts the incident light angle by additionally rotating the inner rod 221 to ensure uniform illumination intensity in different areas. Preferably, when inspecting areas of high curvature, the second drive unit 223 drives the inner rod 221 to rotate, tilting the light source module 3 to avoid excessive reflection caused by vertical incident light. When inspecting areas of low curvature, the inner rod 221 is adjusted to remain horizontal to provide uniform illumination.

[0055] Understandably, traditional fixed light source arrays can only provide illumination at a fixed angle. When the surface of the product 4 has complex curves, the fixed light source cannot adapt to changes in curvature, resulting in localized illumination anomalies. This embodiment utilizes dual drive units to achieve dual-degree-of-freedom rotation of the light source module 3, enabling the light source angle to dynamically adapt to changes in the curve. While existing adjustment mechanisms only have single-axis rotation capabilities, limiting the light source position adjustment range, this solution utilizes a nested rod structure combined with independent drive units to provide the light source module 3 with additional rotational degrees of freedom.

[0056] In this embodiment, a slide rail 224 is provided on a side of the adjusting inner rod 221 close to the fitting module 1 , and the light source module 3 is provided on the slide rail 224 so that the light source module 3 moves along the slide rail 224 .

[0057] In some embodiments, the slide rail 224 is arranged on the side of the adjusting inner rod 221 close to the fitting module 1, and the light source module 3 is connected to the slide rail 224 through a slider. When the adjusting inner rod 221 rotates circumferentially, the light source module 3 can move linearly along the slide rail 224 to form a composite motion trajectory.

[0058] In this embodiment, the number of the adjustment modules 2 is two, and they are arranged axially symmetrically with respect to the axis of the fitting module 1 .

[0059] It is understood that the number of adjustment modules 2 refers to the use of two independently controlled mechanical adjustment devices, specifically a dual-axis drive mechanism with a servo motor, which independently controls the motion trajectory of the two adjustment modules 2. The axisymmetric arrangement of the two adjustment modules 2 with respect to the axis of the bonding module 1 refers to the spatial layout relationship of the two adjustment modules 2. This can be achieved by symmetrically installing support frames on both sides of the bonding module 1, with the two support frames forming a mirror-symmetric structure with the axis of the bonding module 1.

[0060] In some embodiments, the two groups of adjustment modules 2 are respectively located at symmetrical positions on both sides of the curved surface of the attached product 4, and the illumination angle of the light source module 3 can be synchronously adjusted during the movement. When the curved surface of the attached product 4 needs to be inspected, the two groups of adjustment modules 2 can respectively drive the light source module 3 to move along different trajectories. For example, when inspecting the left curved surface area, the right adjustment module 2 can adjust the light source to a compensation position. Through two groups of dynamically adjustable symmetrical light source modules 3, the entire light source angle range of the attached product 4 can theoretically be continuously changed, and the symmetrical layout reduces the standard deviation of the light intensity distribution on both sides of the curved surface to less than 35% of the traditional method.

[0061] It effectively solves the problem of surface reflectivity differences caused by the limited angle of fixed light sources, reducing the surface normal vector estimation error from ±8° of the traditional method to within ±3°, and at the same time reducing the area ratio of local over-exposed areas from 12.6% to 2.3%, providing a more accurate normal vector data basis for subsequent surface depth calculations.

[0062] In this embodiment, the inner adjustment rod 221 and the outer adjustment rod 222 are quarter-sector ring structures with different diameters.

[0063] It can be understood that the quarter fan ring structure refers to an arc-shaped rod with a central angle of 90 degrees, which can be specifically formed by bending metal materials. The different diameters mean that the arc radius of the adjusted inner rod 221 is smaller than the arc radius of the adjusted outer rod 222. This can be achieved through a stepped radius difference design to form an asymmetric spatial layout between the inner and outer rods.

[0064] It is also understood that when the outer adjustment rod 222 is controlled by the drive unit to rotate circumferentially, the inner adjustment rod 221 is driven by the second drive unit 223 to produce independent rotational motion. Due to the difference in diameter between the inner and outer rods, the movement trajectory of the light source module 3 on the slide rail 224 forms a composite curved path, which expands the range of variation of the illumination angle of the light source module 3 in space from a single plane to three-dimensional space. The geometric constraints of the quarter-sector ring structure confine the movement path of the light source module 3 to a specific sector-shaped area, avoiding interference with other mechanical components while ensuring that the direction of the light source forms a controllable angle with the normal of the surface of the attached product 4.

[0065] While conventional ceramic ball calibration relies on inferring the light source direction using a reflected light spot, this solution directly controls the spatial position of the light source module 3 through a mechanical structure, eliminating directional estimation errors caused by refraction from transparent materials. Through this technical solution, the present application enables three-dimensional angle adjustment of the light source module 3 within a limited space, effectively expanding the range of light source direction variation and reducing localized overexposure or underexposure caused by differences in surface reflectivity. The composite motion trajectory of the light source module 3 can match the curved surface of the product 4 being applied, resulting in a more uniform distribution of surface normal vectors in the image information, thereby improving the measurement accuracy of concentricity detection.

[0066] Example 2: As attached Figure 3 As shown, this embodiment provides a concentricity detection method, which includes the following steps: Controlling the adjustment module 2 to rotate so that the light source module 3 passes through different positions when the adjustment module 2 rotates outside the attached product 4; Acquire image information in the corresponding area of ​​the attached product 4 when the light source module 3 provides different light levels and dark light levels at different positions; receiving image information; Obtain the light source direction at different positions of the image information; Estimate the surface normal vector of the product 4 to perform interpolation fitting on the surface normal vector; Calculate the depth information of the 4 boundary surfaces of the product being pasted; Restore the surface curvature of the product 4 and detect the concentricity with the laminating film.

[0067] It should be noted that, on the one hand, traditional curved surface stereo detection technology requires calibration of the light source, that is, the direction of the light source is estimated and calculated using a calibration sphere, which is not conducive to rapid detection and fitting operations in industrial production; on the other hand, since the light beam is split into discrete local data by the microlens array during the image information acquisition process, the stereo surface luminosity is based on global data, and the surface normal vector needs to be compensated using data fitting interpolation methods.

[0068] It should also be noted that the traditional method relies on a fixed light source array, resulting in insufficient illumination incident angles in the edge areas of the curved surface. This embodiment dynamically adjusts the position of the light source so that each area of ​​the curved surface can obtain the optimal incident angle. The existing technology requires the use of a calibration sphere to indirectly infer the direction of the light source, and cumulative errors are generated due to refraction in transparent material scenes. This embodiment directly calculates the direction of the light source through mechanical motion parameters, eliminating error transmission in the intermediate links. The traditional normal vector estimation method is prone to artifacts in areas with sudden changes in reflectivity. This embodiment uses an adaptive interpolation algorithm to effectively suppress interference from abnormal points.

[0069] The above technical solution solves the problem of light source calibration error caused by the refraction effect when a transparent film is bonded to a curved substrate, overcomes the reflectivity difference defect of a fixed light source system in curved surface detection, and ensures that all areas of the curved surface are uniformly and effectively illuminated by actively controlling the spatial position and motion trajectory of the light source. This improves the accuracy of normal vector calculation, and directly solves the light source direction in combination with mechanical motion parameters, avoiding systematic errors caused by the calculation of the refraction path of the transparent medium, thereby achieving accurate reconstruction of the three-dimensional morphology of the curved surface.

[0070] It is understood that when the processor executes the program, it first sends a motion command to the adjustment module 2, driving the light source module 3 to move circumferentially around the product 4 being applied, preferably along a circular arc covering a range of 0 to 180 degrees. During this movement, the light source module 3 switches between bright and dark intensities according to a preset pattern, preferably outputting high, medium, and low brightness levels at intervals of 10 degrees. The visual unit synchronously captures the reflected image at each position, preferably collecting an image sequence containing both specular and diffuse reflection components after each light source switch. After processing the image information, the light source direction of each pixel is preferably extracted through optical flow analysis, and the angle of incidence is calculated based on the displacement of highlight areas in adjacent images. The surface normal estimation module establishes a system of linear equations based on the reflection equation, preferably solving the normal vector component of each pixel through the least squares method. The interpolation fitting process expands the discrete normal vector data into a continuous surface, preferably constructing a bilinear interpolation function between adjacent sampling points. The depth solution module performs an integral operation along the normal vector direction, for example, using the Poisson equation to reconstruct the surface height field. Finally, by comparing the geometric center deviations of the reconstructed surface and the laminating film, the concentricity test result is output. It can also be understood that the above algorithm model is not the final limitation adopted in this embodiment, and the algorithm can be improved later for better processing.

[0071] Based on the above problems, the detection method in this embodiment can be included in four steps: data acquisition, preprocessing, normal vector estimation calculation and restoration detection. Specifically, for data acquisition, the equipment used for data acquisition includes a visual unit, a rotation module and a bearing module. The visual unit is preferably a CCD or CMOS industrial camera, specifically a HIKROBOT model MV-CE050-31GC camera. It can be understood that the visual unit must also have a matching lens array unit.

[0072] For preprocessing, during the image acquisition process, the data set may contain a certain amount of noise due to various reasons. In order to prevent the interference of noise, the image needs to be denoised. The detection unit is used to receive the image information after the image denoising is completed; In some embodiments, a local dynamic threshold segmentation algorithm is used to address speckle noise in image information, and its expression is: ; Among them, μ local is the local grayscale mean; σ local is the grayscale standard deviation; k is the adjustment coefficient; T It is a function of the local dynamic threshold segmentation algorithm and is represented by the discrete coordinates of the pixels in the image information.

[0073] Through noise reduction processing, the signal-to-noise ratio of image information increased from 8.2dB to 24.7dB. A dynamic local thresholding algorithm was used to address noise interference in the original image, analyzing the brightness distribution of local areas of the image and automatically calculating the noise threshold to effectively separate feature points from background noise. This algorithm solves the speckle noise problem (blurring around feature points) caused by microlens beam splitting. Traditional global thresholding methods cannot adapt to local brightness changes and can easily cause feature information loss. Through adaptive processing, image quality is significantly improved, ensuring clear and sharp feature point outlines, providing a pure data source for subsequent light source direction calibration and normal vector calculation, and enhancing overall detection accuracy.

[0074] For normal vector estimation calculation, the method in this embodiment is based on the principle of the Lambertian reflection model. From the known light source direction information and the corresponding image data set, the surface normal vector of the object can be estimated according to optical, physical and other principles, and the estimated surface normal vector of the object can be separated, interpolated and fitted.

[0075] For restoration detection, this embodiment is based on the principle that the surface normal vector after interpolation fitting is perpendicular to the surface section, and can obtain the depth information of the boundary surface of the pasted surface. The depth information is used to restore the pasted surface and detect the concentricity with the bonding film.

[0076] Example 3: In this embodiment, controlling the rotation of the regulating module 2 specifically includes the following steps: Controlling the first drive unit to start, so that the outer adjustment rod 222 rotates circumferentially along the axis of the output end of the first drive unit, and controlling the outer adjustment rod 222 to rotate to a first set angle; The second driving unit 223 is controlled to start, so that the adjusting inner rod 221 rotates circumferentially along the axis of the output end of the second driving unit 223, and the adjusting inner rod 221 is controlled to rotate to a second set angle.

[0077] It can be understood that the first set angle and the second set angle are angles pre-set in the detection system control module through the interactive module. When the first set angle and the second set angle are fixed, the light source direction of the light source under the light source module 3 is uniquely fixed and is a known parameter in the detection system.

[0078] According to the Lambertian reflectance model, the pixel intensity of each point in the image is related to the product of the surface normal vector of each point on the object and the direction of the light source. In this embodiment, the pixel intensity of each point in the image information obtained is known, and the surface normal vector of the attached product 4 can be calculated assuming the light source direction is known.

[0079] In some embodiments, the first set angle and the second set angle are preset by the interaction module to form a unique light source direction vector. The light source direction vector is expressed by cos α express.

[0080] Example 4: In this embodiment, the acquisition of image information in the corresponding area of ​​the attached product 4 when the light source module 3 provides different light sources of different brightness and darkness at different positions includes the following steps: Adjust the physical position and brightness level of the light source module 3 through a programmable light source controller; After the light source module 3 switches to the target position and brightness parameters, it sends a synchronization signal to the vision unit to ensure that the image capture strictly matches the light source status; Preprocess the image information; Image feature points under image information are matched through scale-invariant feature transformation algorithm.

[0081] Based on the above steps, the position change of the light source module 3 is dynamically controlled by the adjustment module 2, so that the light source module 3 moves at multiple angles outside the attached product 4 and provides different light sources of different brightness and darkness. At the same time, the visual unit synchronously captures the image information sequence of the corresponding area; this process directly obtains the light source direction based on the physical displacement of the light source, avoiding the refraction interference caused by the calibration sphere, and expands the lighting coverage range through dynamic light source position adjustment, effectively compensating for the reflection difference of the curved surface, and suppressing overexposure or underexposure problems. In addition, combined with the multi-angle image sequence, the detection unit interpolates and fits the surface normal vector, solves the boundary depth information, and realizes high-precision surface reconstruction and concentricity detection. Therefore, on the basis of eliminating the defects of the existing technology, it further improves the detection accuracy of transparent films and curved substrates, adapts to the needs of products with different curvature shapes, reduces the steps of individual light source calibration, and improves detection efficiency.

[0082] Example 5: In this embodiment, the surface normal vector of the product being pasted is estimated to perform interpolation fitting on the surface normal vector; The expression for estimating the surface normal vector of the product being pasted is: ; Where I is the pixel intensity matrix; ρ is the surface reflectivity constant; N is the surface normal matrix; L Tis the light source direction matrix.

[0083] The expansion of the Lambert model combined with the light source direction is: ; in, For the n The image is in ( x , y ) at the gray value; is the surface normal vector to be determined; is the light source direction vector.

[0084] Combining the Lambertian reflectance model and least squares optimization to solve the normal vector field, the image pixel intensity data under multiple light source directions is used to construct a set of linear equations, and the surface normal vector of each pixel is solved by the least squares method. This solves the problem of the relationship between image intensity and normal vector. Traditional methods are prone to outliers or non-unique solutions when the data is discrete. Through this method, a continuous and consistent normal vector distribution is generated, providing reliable input for surface depth calculation, avoiding manual intervention, and realizing automated processing.

[0085] The interpolation fitting of the surface normal vector comprises the following steps: To find the surface normal vector, execute: ; in, P n ( u ) is the target polynomial function; is the fitting coefficient; n =5 is the optimal order; u is the input variable of the function, which represents the coordinate axis position in the fitting; and u= ( x,y ), ( x,y ) represents the two-dimensional coordinate value; k is the order control variable.

[0086] More specifically, assuming the curve function is y= f ( x ), y= f ( x ) is defined on the interval [a, b], x 0,x1, x 2,…… x n-1 , x nThere are (n+1) different points on the interval [a, b], and the values ​​corresponding to each point are y 0, y 1, y 2,…… y n-1 , y n , then there exists a unique x , y ) and the interpolation polynomial P of degree not exceeding n ( x ) as and f ( x ), its interpolation polynomial has been defined above and will not be repeated here. It can be understood that its coefficient matrix is ​​a Vandermonde matrix. According to the determinant property, the coefficient matrix is ​​a (n+1) order Vandermonde determinant, because x 0,x1, x 2,…… x n-1 , x n are different from each other, so the Vandermonde determinant is not zero, which shows that the equation has a unique solution a 0, a 1, a 2,… , a n—1 , a n .

[0087] It can be understood that the interpolation polynomial fitting technology is used to convert discrete normal vectors into continuous surfaces. In response to the problem of local data discreteness in the detection methods in the existing technology, the normal vector field distribution is smoothed by the polynomial fitting algorithm, which solves the problem of uneven surface reconstruction caused by discrete data. Traditional methods output burrs or concave and convex surfaces, affecting the final detection accuracy. Seamless surface reconstruction is achieved, ensuring the high fidelity of depth information calculation, and providing a high-resolution three-dimensional model for concentricity detection of the labeled product.

[0088] Example 6: In this embodiment, the step of obtaining the depth information of the boundary surface of the product being pasted further includes the following steps: Construct the gradient equations; Use Poisson integral method to perform Fourier transform to solve Poisson equation and output depth map; The expression for constructing the gradient equation group is:

[0089] Depth map z ( x , y)along x , y Partial derivative of the direction, i.e. depth gradient; P x 、P y Represents the intermediate variable related to the surface normal vector to be determined, and satisfies P x =N x / N z , P y = N y / N z .

[0090] The expression for solving the Poisson equation by Fourier transform using the Poisson integral method is: ; in, Depth map z ( x , y )’s Laplace operator; 、 are partial differential operators, representing the variables x Find partial derivatives and variables y Find the partial derivative.

[0091] It is understandable that traditional surface depth reconstruction methods have significant defects: when dealing with complex surfaces or transparent materials, small errors in local normal vectors will continue to accumulate during the integration process, resulting in overall distortion of the reconstructed surface or boundary dislocation. Especially for the surface boundaries of the bonded products in the OCA film bonding scenario, traditional methods are easily interfered by surface reflection noise, causing deviations in the depth gradient calculation, and ultimately forming non-physical surface undulations or fractures.

[0092] It can also be understood that this embodiment constructs a set of gradient equations covering the entire domain of the product to be applied. This set of equations uses the partial derivatives of the depth map in the x and y directions (i.e., the depth gradient) as basic variables, and accurately describes the slope change trend of each tiny area of ​​the surface through mathematical relationships. This global modeling fundamentally avoids the error accumulation defect of point-by-point integration in traditional methods, ensuring that the mathematical description of surface deformation conforms to actual physical laws.

[0093] The gradient equations are further transformed into the Poisson equation. Leveraging its mathematical advantage of naturally adapting to the closed properties of surfaces, the Poisson equation is solved via Fourier transform to achieve simultaneous processing of global data and transform complex differential operations into efficient algebraic operations in the frequency domain. This process not only ensures that the generated depth map strictly meets the surface boundary constraints, but also achieves industrial-grade real-time requirements at superlinear computing speeds.

[0094] Example 7: In this embodiment, after using the Poisson integral method to perform Fourier transform to solve the Poisson equation, the method further includes: applying constrained weighted least squares filtering to correct boundary mutations to solve the problem of depth jumps caused by occlusion or reflection at the edge of the attached product.

[0095] The specific steps include: Define the confidence weight ω in the edge area of ​​the depth map ( x , y ), where ω=1 is a high confidence flat area, and ω=0 is a low confidence mutation area, such as boundary shadows.

[0096] Construct the optimization objective function, whose expression is: ; in, z 0( x,y ) is the initial depth map, λ is the smoothing coefficient; Finally, an iterative solution is performed to make the boundary transition natural; is the gradient symbol, representing a two-dimensional gradient vector, and satisfies the following expression: ; Where t represents the vector transpose operator.

[0097] Understandably, conventional photometric stereo vision technology, when reconstructing the depth of curved surfaces, often experiences unusual jumps in depth information at the boundary regions due to factors such as light occlusion at the object's edges, specular reflection, or refraction from transparent materials. This sudden change can severely distort the geometric continuity of the reconstructed surface. For example, in OCA film lamination inspection, shadows or highlight artifacts can easily form on the steep edges of the adhered product or at the seams of the transparent film, causing the algorithm to mistakenly identify them as actual depth faults. Traditional solutions typically employ global smoothing filtering, which blurs the actual physical edge details; or rely on manual intervention to correct errors, significantly reducing inspection efficiency and automation.

[0098] This embodiment automatically identifies trusted and anomalous regions in the depth map based on image features (such as gradient changes and illumination uniformity), avoiding inadvertent smoothing of valid edges while precisely targeting artifact regions requiring correction. A dual-constraint optimization objective function is constructed, requiring the corrected depth values ​​to be as close as possible to the initial solution to preserve true surface features while also controlling the smoothing coefficient to ensure a smooth transition in regions with abrupt changes. This mathematical optimization ensures that anomalous regions seamlessly transition with adjacent surfaces while preserving true edge sharpness. A multi-iteration calculation strategy is employed to gradually reduce the weight of anomalous regions, allowing depth values ​​to naturally diffuse from trusted regions to abrupt changes, ultimately generating a physically consistent, smooth transition surface. This significantly reduces the "step-like" transitions caused by optical interference.

[0099] Based on the above, in OCA film lamination scenarios, the system successfully eliminates false depth discontinuities caused by refraction shadows at the edges of transparent films, maintaining the restored curved substrate profile within ±0.01mm. This eliminates the need for traditional manual correction, triples inspection efficiency, and eliminates subjective errors. Accurately preserving trusted areas in the depth map ensures that the true physical boundaries between the laminating film and the substrate (such as cutting edges) are not inadvertently smoothed, providing an anatomically accurate surface model for concentricity analysis.

[0100] Example 8: The specific steps of restoring the surface curvature of the adhered product and detecting the concentricity with the bonding film are as follows: extracting boundary information and an ideal center from a depth map of the adhered product; obtaining the bonding information and bonding center of the bonding film through morphological segmentation and positioning; measuring the offset between the ideal center and the bonding center through laser interferometry; and finally determining the deviation distance between the boundary information and the bonding information.

[0101] In some embodiments, the offset from the ideal center is: ; in, For the ideal center, To fit the center.

[0102] In some embodiments, a control signal is generated by the offset and the deviation distance, so as to control the lamination module to adjust the lamination distance through the control signal. Preferably, the control process is a closed-loop feedback calibration process in a PID controller, and the expression is:

[0103] in, It is the real-time output instruction of the controller; is the integral of historical deviations; is the rate of change of deviation; K p 、K i 、K d They are the proportional coefficient, integral coefficient, and differential coefficient of the PID controller respectively.

[0104] It should be noted that to address the flaw in traditional technologies that causes misaligned light source calibration due to refraction, this solution, after completing high-precision surface reconstruction, employs non-contact optical inspection. First, the actual boundary information of the bonded product and the theoretically designed ideal center point are directly extracted from the reconstructed depth map, avoiding the secondary errors caused by traditional mechanical probe contact measurement. Simultaneously, morphological image segmentation technology is used to precisely locate the edge contour and bonding center of transparent bonding films (such as OCA films). This technology is highly robust to the edge features of transparent materials and overcomes the edge recognition ambiguity caused by the film's light transmittance. Laser interferometry is then introduced to quantify the submicron offset between the two center points. By utilizing the principle of light wave phase difference, the method is unaffected by the material's refractive index and physically eliminates the measurement deviation caused by the transparent medium, enabling nanometer-level accuracy in offset calculation (i.e., the spatial vector difference between the ideal center and the bonding center).

[0105] It should also be noted that, based on achieving high-precision detection, a dynamic bonding calibration system has been further constructed. This system converts the calculated offset and the topographic deviation distance between the boundary and the bonding film into a control signal, driving a PID controller to generate real-time adjustment instructions. The controller uses a three-modal closed-loop feedback loop: the proportional link (P) instantly adjusts the bonding pressure based on the current deviation distance; the integral link (I) accumulates historical deviations to eliminate system steady-state errors, which is particularly suitable for conditions with continuously changing surface curvature; and the differential link (D) predicts the bonding trend based on the rate of change of the deviation to suppress mechanical overshoot. This dynamic calibration mechanism enables the bonding module to adaptively adjust the bonding distance and angle within a millisecond response cycle, upgrading the existing offline correction method of manual intervention to online real-time compensation. The accuracy of surface concentricity detection has been improved from the traditional ±50μm to ±5μm, especially solving the measurement blind spots in transparent / curved surface composite scenarios; the bonding yield has been increased by more than 30% through closed-loop control, reducing rework losses; the adaptive PID algorithm is compatible with substrates with arbitrary curvature, such as planes, spheres, and free-form surfaces, meeting the process requirements of new products such as folding screens and curved automotive displays.

[0106] To achieve the aforementioned objective, this embodiment further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program.

[0107] To achieve the aforementioned objective, this embodiment further provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program.

[0108] In addition, in one embodiment, the present invention further provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method in the aforementioned embodiment are implemented.

[0109] In some embodiments, the computer-readable storage medium may be a memory device such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface mount memory, optical disk, or CD-ROM; or various devices including any one or any combination of the above memories. The computer may be various computing devices including smart terminals and servers.

[0110] In some embodiments, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0111] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0112] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0113] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0114] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0115] Through the description of the above embodiments, those skilled in the art will clearly understand that the above-mentioned embodiments and methods can be implemented by means of software plus the necessary general hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, or optical disk) and includes a number of instructions for enabling a multimedia terminal device (such as a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0116] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A concentricity detection system, characterized in that: The system is used for concentricity detection of the OCA film laminating process by a laminating machine. The laminating machine includes a laminating module, which is used to complete the laminating process of the laminating film on the product to be laminarized. The system includes: Light source module, used to provide different light sources at different locations; The detection module includes a visual unit and a detection unit, wherein the visual unit is used to obtain image information in a corresponding area of ​​the attached product when the light source module provides different light sources of different brightness and darkness at different positions; An adjustment module is provided in the laminating machine and is used to adjust different positions of the light source module; Wherein, the detection unit includes: An acquisition subunit, used to acquire the light source direction of image information at different positions; An estimation subunit, used to estimate the surface normal vector of the product being pasted so as to perform interpolation fitting on the surface normal vector; The processing subunit is used to solve the depth information of the boundary surface of the product being pasted; The detection subunit is used to restore the surface curvature of the product being adhered and to detect the concentricity with the laminating film.

2. A concentricity detection system according to claim 1, characterized in that: The adjustment module includes an adjustment seat and an adjustment unit. The adjustment seat is fixedly connected to the inner wall of the laminating machine. A first driving unit is arranged in the adjustment seat. The output end of the first driving unit is connected to the adjustment unit so that the adjustment unit rotates circumferentially along the output end of the first driving unit. The light source module is arranged on the adjustment unit.

3. A concentricity detection system according to claim 2, characterized in that: The adjustment unit includes an adjustment inner rod and an adjustment outer rod. One end of the adjustment outer rod is connected to the output end of the first driving unit. The other end of the adjustment outer rod is rotatably arranged with the adjustment inner rod. The light source module is arranged on the adjustment inner rod.

4. A concentricity detection system according to claim 3, characterized in that: A second driving unit is provided at a connection portion between the adjusting outer rod and the adjusting inner rod, so that the adjusting inner rod rotates circumferentially along an output end of the second driving unit.

5. A concentricity detection system according to claim 3, characterized in that: A slide rail is provided on one side of the adjusting inner rod close to the fitting module, and the light source module is provided on the slide rail so that the light source module moves along the slide rail.

6. A concentricity detection system according to claim 1, characterized in that: The number of the adjustment modules is 2, and they are arranged in an axisymmetric manner with respect to the axis of the fitting module.

7. A concentricity detection system according to claim 3, characterized in that: The inner adjustment rod and the outer adjustment rod are quarter sector ring structures with different diameters.

8. A concentricity detection method, characterized in that: Based on a concentricity detection system according to any one of claims 1 to 7, the method comprises the following steps: Controlling the adjustment module to rotate so that the light source module passes through different positions when the adjustment module rotates outside the attached product; Obtain image information in the corresponding area of ​​the product when the light source module provides different light levels at different positions; receiving image information; Obtain the light source direction at different positions of the image information; Estimate the surface normal vector of the product being pasted to perform interpolation fitting on the surface normal vector; Calculate the depth information of the boundary surface of the product being pasted; Restore the surface curvature of the laminated product and detect the concentricity with the laminated film.

9. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the method according to claim 8.

Images