Surface inspection apparatus and surface inspection method

Abstract

To reduce the effects of machining traces occurring to work surfaces when planning by milling and detect flaws such as dents on the work surfaces.SOLUTION: A surface inspection device 10 makes a search to see whether or not a rotation center VCi exists in a range of rotation radius r ± tolerance δ from a discretionary point Pn of an object surface image 101, on the basis of an object surface image 101 in which the surface S of an object 100 is imaged by an imaging unit 20, and rotation center image data 14a, when it exists, identifies a vector direction from the discretionary point Pn to the rotation center VCi, and calculates the direction vector of the discretionary point Pn. The surface inspection device calculates a brightness slope angle due to machining traces SM at the discretionary point, and corrects the pixel value of the discretionary point Pn to become equal to the average value around it, when the brightness slope angle and the vector angle of the direction vector are within a prescribed range.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a surface inspection apparatus and a surface inspection method capable of detecting scratches such as dents on a processed surface while reducing the influence of machining marks generated on the processed surface when performing surface finishing by milling.

Background Art

[0002] Conventionally, a surface inspection method for separating and detecting scratches present on the surface of an object from grinding marks is known. For example, in Patent Document 1, for each pixel of an image obtained by imaging the surface of an object, a vector having differential values in the X-axis direction and differential values in the Y-axis direction as components is calculated, and the frequency of the angle of each pixel vector with respect to the X-axis is measured. A direction perpendicular to the angle with a high frequency is specified as the extending direction of the grinding marks, and correction is performed to weaken the luminance value of the pixel of the vector with a high frequency angle among the pixels of the image data, or to enhance the luminance value of the pixel of the vector with a low frequency angle. A technique is disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the case of the above Patent Document 1, even if a pixel is caused by a scratch rather than a grinding mark when the frequency of the angle of the vector of each pixel becomes high, it is specified as the extending direction of the grinding mark and the luminance value is corrected. As a result, there arises a problem that scratches other than the grinding marks are regarded as grinding marks and removed.

[0005] The present invention was made to solve the above-mentioned problems, and aims to provide a surface inspection device and surface inspection method that can detect scratches such as dents on a machined surface while reducing the influence of machining marks on the machined surface when performing surface leveling by milling. [Means for solving the problem]

[0006] To solve the above-mentioned problems and achieve the objective, the present invention provides a surface inspection method for a surface inspection apparatus that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, the method comprising: a first identification step of identifying a second pixel on the movement trajectory of the rotation center of the cutting tool that affects any first pixel forming the object surface image; a second identification step of identifying the brightness gradient of a direction vector to the second pixel on the movement trajectory of the rotation center of the cutting tool from among a plurality of brightness gradients in the first pixel; and a correction step of correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified in the second identification step.

[0007] Furthermore, in the above invention, based on the corrected image obtained by the correction step in which the object surface image is corrected, the present invention applies the following to the surface of the object. As a result of cutting The method further includes an inspection process for inspecting for damage caused by factors other than processing marks.

[0008] Furthermore, the present invention is characterized in that, in the above invention, the cutting tool is a face milling cutter or polishing brush for polishing the surface of an object, wherein a plurality of blades are mounted on the circumference of a predetermined rotating body and are formed to be rotatable about the predetermined rotation axis.

[0009] Furthermore, the present invention is characterized in that, in the above invention, the first identification step is to identify the second pixel on the movement trajectory of the rotation center of the cutting tool that affects the first pixel forming the object surface image, using a movement trajectory image in which predetermined pixel values ​​are assigned to pixels forming the movement trajectory of the rotation center of the cutting tool.

[0010] Furthermore, the present invention is characterized in that, in the above invention, the correction step corrects the pixel value of the first pixel on the object surface image that has a gradient angle of the brightness gradient identified by the second specific step.

[0011] Furthermore, the present invention is characterized in that, in the above invention, the correction step reduces the pixel value of the first pixel on the object surface image that has a gradient angle of the brightness gradient identified by the second specific step.

[0012] Furthermore, the present invention relates to a surface inspection method for a surface inspection apparatus that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, and is characterized by comprising: a first identification step of identifying a first pixel that is affected by a second pixel on the movement trajectory of the rotation center of the cutting tool; a second identification step of identifying the gradient angle of the brightness gradient in the direction from the first pixel to the second pixel among a plurality of brightness gradients at the first pixel identified in the first identification step; and a correction step of correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified in the second identification step.

[0013] Furthermore, the present invention relates to a surface inspection apparatus that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, and comprises: a first identification means for identifying a second pixel on the movement trajectory of the rotation center of the cutting tool that affects any first pixel forming the object surface image; a second identification means for identifying the gradient angle of the brightness gradient in the direction from the first pixel to the second pixel among a plurality of brightness gradients in the first pixel identified by the first identification means; and a correction means for correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified by the second identification means.

[0014] Furthermore, the present invention relates to a surface inspection apparatus for inspecting the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, the apparatus comprising: a first identification means for identifying a first pixel that is affected by a second pixel on the movement trajectory of the rotation center of the cutting tool; a second identification means for identifying the gradient angle of a brightness gradient in the direction from the first pixel to the second pixel among a plurality of brightness gradients at the first pixel identified by the first identification means; and a correction means for correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified by the second identification means. [Effects of the Invention]

[0015] According to the present invention, when performing surface leveling by milling, it is possible to detect scratches such as dents on the machined surface while reducing the influence of machining marks generated on the machined surface. [Brief explanation of the drawing]

[0016] [Figure 1] Figure 1 is a functional block diagram showing the configuration of a surface inspection apparatus according to Embodiment 1. [Figure 2] Figure 2 is an explanatory diagram illustrating the process of identifying the center of rotation from an arbitrary point Pn. [Figure 3] Figure 3 is an explanatory diagram illustrating the calculation of the direction vector. [Figure 4] Figure 4 is a flowchart showing the processing procedure of the surface inspection apparatus shown in Figure 1. [Figure 5] Figure 5 is a flowchart showing the processing procedure for the correction process shown in Figure 4. [Figure 6] Figure 6 shows an example of an object surface image and a processed image from the surface inspection device shown in Figure 1. [Figure 7] Figure 7 is a functional block diagram showing the configuration of the surface inspection apparatus according to Embodiment 2. [Figure 8] Figure 8 is an explanatory diagram illustrating the process of determining the coordinates of an arbitrary point from the center of rotation. [Figure 9] Figure 9 is an explanatory diagram illustrating the calculation of the direction vector. [Figure 10] Figure 10 is a flowchart showing the processing procedure of the surface inspection apparatus shown in Figure 7. [Modes for carrying out the invention]

[0017] Embodiments of the surface inspection apparatus and surface inspection method according to the present invention will be described in detail below with reference to the drawings. In this embodiment, a case will be described in which a cutting tool is used to perform face milling of an object, using a rotating body with blades attached to multiple positions on the circumferential edge, which is rotated around a rotation axis.

[0018] [Embodiment 1] <Configuration of surface inspection device 10> First, the configuration of the surface inspection device 10 according to this embodiment 1 will be described. Figure 1 is a functional block diagram showing the configuration of the surface inspection device 10 according to embodiment 1. As shown in Figure 1, the surface inspection device 10 has a display unit 11, an input unit 12, a storage unit 14, a control unit 15, and an imaging unit 20.

[0019] The display unit 11 is a display device such as a liquid crystal display that displays various information. The input unit 12 is an input device such as a mouse or keyboard.

[0020] The memory unit 14 is a storage device such as a hard disk drive or non-volatile memory, and stores rotation center image data 14a and image data 14b. The rotation center image data 14a is the rotation center VC of the cutting tool. i The coordinates and the rotation center VC of the cutting tool. i This is image data showing the rotation center trajectory L, which is the trajectory of the object. Image data 14b is image data of the surface of object 100 captured by the imaging unit 20. Note that the pixels in the rotation center image data 14a and the pixels in image data 14b are associated with the same position on the object surface.

[0021] The control unit 15 controls the entire surface inspection apparatus 10 and includes an image acquisition processing unit 15a, a rotation center coordinate identification unit 15b, a direction vector calculation unit 15c, a brightness gradient angle identification unit 15d, a correction processing unit 15e, and a scratch detection unit 15f. In practice, these programs are loaded into the CPU and executed, causing the image acquisition processing unit 15a, the rotation center coordinate identification unit 15b, the direction vector calculation unit 15c, the brightness gradient angle identification unit 15d, the correction processing unit 15e, and the scratch detection unit 15f to execute the processes corresponding to each of them.

[0022] The image acquisition processing unit 15a controls the imaging unit 20 to capture an object surface image of the surface S of the object 100, and acquires the captured object surface image of the surface S of the object 100. The position of the object surface corresponding to the pixels forming the image data 14b is associated with the position of the object surface forming the rotation center image data 14a. In this way, the image data 14b is aligned, scaled, rotated, and distortion corrected so that it corresponds to the same area of ​​the object surface indicated by the rotation center image data 14a stored in the storage unit 14 beforehand.

[0023] The rotation center coordinate identification unit 15b determines the rotation center VC of the cutting tool that caused the machining mark when a machining mark occurs at the coordinate position of any pixel in the image data 14b (hereinafter referred to as "arbitrary point Pn"). iIt is a processing unit that specifies the coordinates. That is, when the position of the object surface corresponding to an arbitrary point Pn in such image data 14b is cut by a cutting tool, the rotation center VC of the cutting tool must be at a position a predetermined distance away from the arbitrary point Pn. i should have existed. Therefore, the coordinates of the rotation center VC of the cutting tool existing at a position a predetermined distance away from the arbitrary point Pn i are specified. Note that if the rotation center VC of the cutting tool existing at a position a predetermined distance away from the arbitrary point Pn i does not exist and the pixel value of this arbitrary point Pn is, for example, decreased, it can be understood that the scratch generated at this arbitrary point Pn is not a processing mark.

[0024] Specifically, the rotation center coordinate specifying unit 15b checks whether the rotation center VC of the cutting tool exists within the range of the rotation radius r ± allowable error δ from an arbitrary point Pn in the rotation center image data 14a. If the rotation center VC i exists, the coordinates of the rotation center VC i are specified, and the process of calculating the vector angle θ i from the arbitrary point Pn to the rotation center VC i is performed. C is performed.

[0025] The direction vector calculation unit 15c performs the process of calculating the direction vector from the coordinates of the rotation center VC i specified by the rotation center coordinate specifying unit 15b to the arbitrary point Pn. For example, when the brightness of the portion of the object surface damaged by the blade provided on the cutting tool decreases, a gradient of decreasing brightness occurs in the direction from the rotation center VC i to the arbitrary point Pn. Here, the direction vector is a vector indicating the direction orthogonal to the direction of the processing mark at the arbitrary point Pn.

[0026] The brightness gradient angle determination unit 15d is a processing unit that calculates multiple brightness gradients around an arbitrary point Pn by applying a differential operator to the pixels of an arbitrary point Pn in the object surface image captured by the imaging unit 20, and determines whether the brightness gradient angle falls within a predetermined angle range that includes the direction vector calculated by the direction vector calculation unit 15c. As this differential operator, a first-order differential operator such as Sobel or Roberts, a second-order differential operator, etc., can be used. For example, the brightness gradient V in the X-axis direction can be determined by applying the Sobel differential operator in the X-axis direction. X It generates a Y-axis lightness gradient V by applying the Sobel differential operator in the Y-axis direction. Y Generates.

[0027] The brightness gradient angle specification unit 15d then determines the brightness gradient V in the X-axis direction. X and the brightness gradient V in the Y-axis direction Y The ratio is calculated, and the inverse tangent function (tan) of the calculated ratio of brightness gradients is calculated. -1 (V X / V Y The brightness gradient angle is calculated by calculating ). After that, the brightness gradient angle determination unit 15d determines whether the calculated brightness gradient angle falls within a predetermined angle range that includes the direction vector calculated by the direction vector calculation unit 15c. The brightness gradient angle determination unit 15d also determines whether the calculated brightness gradient angle falls within a predetermined angle range that includes the inverse vector direction of the direction vector calculated by the direction vector calculation unit 15c.

[0028] The correction processing unit 15e performs a correction process to reduce the pixel value of an arbitrary point Pn in the image data 14b to the average value of its surroundings if the brightness gradient angle determination unit 15d determines that the calculated brightness gradient angle falls within a predetermined angle range that includes the direction vector calculated by the direction vector calculation unit 15c. If the brightness gradient angle determination unit 15d determines that the calculated brightness gradient angle does not fall within a predetermined angle range that includes the direction vector calculated by the direction vector calculation unit 15c, the correction process is not performed.

[0029] Furthermore, the correction processing unit 15e performs a correction process to reduce the pixel value of an arbitrary point Pn in the image data 14b to the average value of the surrounding area if the brightness gradient angle determination unit 15d determines that the calculated brightness gradient angle falls within a predetermined angle range that includes the inverse vector direction of the direction vector calculated by the direction vector calculation unit 15c. If the brightness gradient angle determination unit 15d determines that the calculated brightness gradient angle does not fall within a predetermined angle range that includes the inverse vector direction of the direction vector calculated by the direction vector calculation unit 15c, the correction process is not performed. As a result, processing marks are reduced in the image data 14b.

[0030] The scratch detection unit 15f is a processing unit that detects information about scratches from image data 14b corrected by the correction processing unit 15e. For example, it can output the probability of scratch occurrence using a trained model that has been supervised and trained using deep learning or machine learning, and output a scratch score by multiplying this scratch occurrence probability by a coefficient. It can also detect scratches longer than a predetermined length using template matching or line segment tracking technology.

[0031] <Rotation Center VC> i Process to identify > Next, from an arbitrary point Pn, the rotation center VC i The process for identifying the point is described below. Figure 2 shows the rotation center VC from an arbitrary point Pn. i This is an explanatory diagram illustrating the process of identifying the cutting tool. Here, the image data 14b and the rotation center image data 14a are superimposed. The object surface image 101 is an image captured by the imaging unit 20, and here the rotation center VC of the cutting tool is shown. i The coordinates and the rotation center VC of the cutting tool i The trajectory (rotation center trajectory L) is being overlaid.

[0032] First, with an arbitrary point Pn as the center, within the range of rotation radius r ± tolerance δ, the rotation center VC i Determine whether or not it exists. When making such a determination, the center of the circle template is set to an arbitrary point Pn, and the rotation center VC that exists within the circle is determined. i We just need to identify the coordinates.

[0033] In this way, the rotation center VC i Once the coordinates are determined, from an arbitrary point Pn, the rotation center VC can be accessed. i Find the rotation center vector CV pointing towards the X-axis, and the vector angle θ between this rotation center vector CV and the X-axis. C The following is calculated. Furthermore, multiple rotation centers VC are located within the range of rotation radius r ± tolerance δ from an arbitrary point Pn. i If there is a center of rotation VC, i Identify the coordinates and the vector angle θ of each rotation center vector CV. Cn Calculate the amount.

[0034] <Direction vector at arbitrary point Pn> Next, we will explain how to calculate the direction vector BV at an arbitrary point Pn. Figure 3 is an explanatory diagram for illustrating the calculation of the direction vector BV. Here, the vector of the machining mark created at an arbitrary point Pn by the cutting tool's edge will be denoted as the machining mark vector SV.

[0035] As shown in Figure 3(a), the machining mark vector SV at an arbitrary point Pn is orthogonal to the rotation center vector CV that points from the arbitrary point Pn to the rotation center coordinates. Furthermore, the direction vector BV with respect to the machining mark vector SV is orthogonal to the machining mark vector SV, and as a result, the direction vector BV is the inverse vector of the rotation center vector CV (the vector angle θ of the rotation center vector CV). C This results in a phase difference of 180 degrees.

[0036] As shown in Figure 3(b), schematically representing the shape of the surface around an arbitrary point Pn, the arbitrary point Pn on the processing mark vector SV is at the bottom of the gouge created as a processing mark, and the area around it is raised along the processing mark vector SV. In other words, if the image is a 256-level grayscale image and the pixel value increases with the white pixels, then if the pixel value of the pixel that becomes the processing mark is low, then the pixel value of the arbitrary point Pn will be low, and the rotation center VC i The pixel value increases as you move towards the center. Therefore, the direction vector BV of an arbitrary point Pn is equal to the rotation center VC. iThis becomes a vector pointing towards any point Pn, and its direction is the inverse vector direction of the rotation center vector CV.

[0037] <Processing procedure for surface inspection device 10> Next, the processing procedure of the surface inspection device 10 shown in Figure 1 will be described. Figure 4 is a flowchart showing the processing procedure of the surface inspection device 10 shown in Figure 1. As shown in Figure 4, the surface inspection device 10 first acquires an object surface image 101 of the surface S of the object 100 captured by the imaging unit 20 (step S101).

[0038] The surface inspection device 10 then uses this object surface image 101 and the rotation center VC of the cutting tool. i The coordinates and the rotation center VC of the cutting tool i The object surface image 101 is aligned with a rotation center image, which is a movement trajectory image showing the trajectory, and preprocessing is performed to remove noise from the object surface image 101 (step S102). For this noise removal process, for example, a known smoothing filter or median filter may be applied.

[0039] Subsequently, any pixel on the object surface image 101 from which noise has been removed is selected (step S103). Then, based on the object surface image 101 and the rotation center image, the surface inspection device 10 determines the rotation center VC from a predetermined pixel of the image within the range of rotation radius r ± tolerance δ. i Determine whether or not it exists, and the rotation center VC i If a rotation center VC exists, i Identify the coordinates (step S104).

[0040] The surface inspection device 10 has a rotation center VC. i Determine whether the coordinates of the rotation center VC have been identified. i If the coordinates cannot be determined (step S105; No), select the next pixel (step S110) and proceed to step S104.

[0041] In contrast, the rotation center VC iIf the coordinates are identified (Step S105; Yes), rotate from any point Pn to the rotation center VC. i The rotation center vector CV is calculated for the coordinates of (step S106). Then, the surface inspection device 10 calculates the direction vector BV of an arbitrary point Pn based on the calculated rotation center vector CV (step S107).

[0042] Subsequently, the surface inspection device 10 performs a pixel value correction process on the selected pixel (step S108) and determines whether the processed pixel is the last pixel (step S109). If it is not the last pixel (step S109; No), it selects the next pixel (step S110) and proceeds to step S104. On the other hand, if it is the last pixel (step S109; Yes), it detects defects based on the image after processing all pixels (step S111) and terminates the series of processes.

[0043] <Processing procedure for correction> Next, the correction process will be explained. Figure 5 is a flowchart showing the processing procedure for the correction process shown in Figure 4. As shown in Figure 5, the surface inspection device 10 checks the brightness gradient V in the X-axis direction of the selected pixel (arbitrary point Pn). X In addition to calculating the brightness gradient V in the Y-axis direction of this pixel (step S201), Y Calculate (Step S202).

[0044] Subsequently, the surface inspection device 10 determines the brightness gradient V in the X-axis direction. X and the brightness gradient V in the Y-axis direction Y The ratio (V X / V Y Find the ratio and the inverse tangent function of that ratio tan -1 (V X / V Y ) is calculated as the brightness gradient angle (step S203).

[0045] Then, the surface inspection device 10 compares the calculated brightness gradient angle with the vector direction (vector angle) of the direction vector BV (step S204). If the calculated brightness gradient angle and the vector direction of the direction vector BV are not within a predetermined range (step S205; No), the process proceeds to step S109 in Figure 4.

[0046] In contrast, if the calculated brightness gradient angle and the vector direction of the direction vector BV are within a predetermined range (step S205; Yes), the pixel value is corrected to the average value of the surrounding area (step S206), and the process proceeds to step S109 in Figure 4. Here, the predetermined range for correction processing is, for example, ±10 degrees with respect to the angle of the direction vector BV, and the direction of the direction vector BV and the direction of its inverse vector are the targets of correction.

[0047] <Example of object surface image 101 and processed image> Next, an example of the object surface image 101 and processed image of the surface inspection device 10 shown in Figure 1 will be described. Figure 6 shows an example of the object surface image 101 and processed image of the surface inspection device 10 shown in Figure 1. As shown in Figure 6(a), the object surface image 101 captured by the imaging unit 20 is an image that is difficult to visually inspect because it is difficult to distinguish between unintended dents and other scratches on the object 100 and processing marks caused by processing.

[0048] In contrast, if the object surface image 101 in Figure 6(a) is processed by the surface inspection device 10, as shown in Figure 6(b), the brightness gradient of the processing marks is corrected in each pixel, resulting in a processed image from which the processing marks have been removed. This makes it possible to obtain an image in which the defective areas P1, P2, P3, and P4, which are not processing marks, are clearly visible.

[0049] Thus, in this embodiment 1, the surface inspection device 10, based on the object surface image 101 captured by the imaging unit 20 of the surface S of the object 100 and the rotation center image data 14a, determines the rotation center VC within the range of rotation radius r ± tolerance δ from an arbitrary point Pn on the object surface image 101. iThe system searches for the existence of a point Pn, and if it does, it searches for the rotation center VC from an arbitrary point Pn. i The vector direction is identified, and the direction vector BV of an arbitrary point Pn is calculated. Then, the brightness gradient angle caused by the processing mark SM at the arbitrary point Pn is calculated, and when the brightness gradient angle and direction vector BV are within a predetermined range, the pixel value of the arbitrary point Pn is configured to be the average value of the surrounding area. This makes it possible to detect scratches such as dents on the processed surface while reducing the influence of processing marks.

[0050] [Embodiment 2] By the way, in the above embodiment 1, in order to remove the processing marks SM from the object surface image 101, the rotation center VC is moved from an arbitrary point Pn. i We have described the case where the coordinates of are searched, but in this embodiment 2, the rotation center VC i This section describes a case where an arbitrary point Pn where a machining mark SM occurs is determined, and the machining mark SM at that arbitrary point Pn is removed. Note that parts similar to those in Embodiment 1 are given the same reference numerals, and their detailed descriptions are omitted.

[0051] <Configuration of surface inspection device 30> Next, the configuration of the surface inspection device 30 according to this second embodiment will be described. Figure 7 is a functional block diagram showing the configuration of the surface inspection device 30 according to this second embodiment. As shown in Figure 7, the surface inspection device 30 has a display unit 11, an input unit 12, a storage unit 14, a control unit 35, and an imaging unit 20.

[0052] The control unit 35 is a control unit that controls the entire surface inspection apparatus 30 and includes an image acquisition processing unit 15a, a direction vector calculation unit 15c, a brightness gradient angle determination unit 15d, a correction processing unit 15e, a scratch detection unit 15f, and an arbitrary point coordinate determination unit 35a. In practice, by loading these programs into the CPU and executing them, the processes corresponding to the image acquisition processing unit 15a, the direction vector calculation unit 15c, the brightness gradient angle determination unit 15d, the correction processing unit 15e, the scratch detection unit 15f, and the arbitrary point coordinate determination unit 35a are executed, respectively.

[0053] The arbitrary point coordinate identification unit 35a identifies an arbitrary rotation center VC of the rotation center image data 14a. i This processing unit identifies the coordinates of an arbitrary point where a cutting tool leaves a machining mark, centered on the rotation center image data 14a. In other words, it identifies the coordinates of an arbitrary rotation center VC of the rotation center image data 14a. i When the cutting tool rotates around an arbitrary rotation center VC, i Machining marks should appear at a predetermined distance from the rotation center VC. i Determine the coordinates of an arbitrary point Pn located at a predetermined distance from [the specified point].

[0054] Specifically, the coordinates of an arbitrary point Pn on the circumference of a circle with a rotation radius r ± tolerance δ are determined from the rotation center VCi of the rotation center image data 14a, and the rotation center VC i The vector angle θ of the arbitrary point vector PV pointing from an arbitrary point Pn to an arbitrary point Pn P The process is performed to identify the specific issue.

[0055] <Process to identify an arbitrary point Pn> Next, the rotation center VC i The process of determining the coordinates of an arbitrary point Pn is described below. Figure 8 shows the rotation center VC. i This is an explanatory diagram illustrating the process of determining the coordinates of an arbitrary point Pn. Here, the image data 14b and the rotation center image data 14a are superimposed. The object surface image 101 is an image captured by the imaging unit 20, and the rotation center VC of the cutting tool is shown here. i The coordinates and the rotation center VC of the cutting tool i The trajectories are overlapping.

[0056] As shown in Figure 8, a predetermined rotation center VC on the image i From this, determine the coordinates of an arbitrary point Pn on the circumference within the range of rotation radius r ± tolerance δ.

[0057] In this way, once the coordinates of an arbitrary point Pn are determined, the rotation center VC i Find the vector PV pointing from an arbitrary point Pn, and the vector angle θ between this vector PV and the X-axis. P Calculate the amount.

[0058] <Calculation of Direction Vector BV> Next, we will explain how to calculate the direction vector BV at an arbitrary point Pn. Figure 9 is an explanatory diagram for explaining the calculation of the direction vector BV. As shown in Figure 9, the machining mark vector SV at an arbitrary point Pn is equal to the rotation center VC i The direction vector BV, which points from the arbitrary point Pn to the arbitrary point Pn, is orthogonal to the arbitrary point vector PV. Furthermore, the direction vector BV relative to the machining mark vector SV is orthogonal to the machining mark vector SV, so as a result, the direction vector BV is the same direction vector as the arbitrary point vector PV.

[0059] <Processing procedure for surface inspection device 30> Next, the processing procedure of the surface inspection device 30 will be described. Figure 10 is a flowchart showing the processing procedure of the surface inspection device 30 as shown in Figure 7. As shown in Figure 10, the surface inspection device 30 first acquires an object surface image 101 of the surface S of the object 100 captured by the imaging unit 20 (step S301).

[0060] The surface inspection device 30 then uses the object surface image 101 and the rotation center VC of the cutting tool. i The coordinates and the rotation center VC of the cutting tool i The object surface image 101 is aligned with a rotation center image showing its trajectory, and preprocessing is performed to remove noise from the object surface image 101 (step S302). For this noise removal process, for example, a known smoothing filter or median filter may be applied.

[0061] Subsequently, the surface inspection device 30 can determine any rotation center VC on the screen from which noise has been removed. i The coordinates are selected (step S303). Then, the coordinates of an arbitrary point Pn to be processed on the circumference of a circle with a rotation radius r ± tolerance δ are determined from the rotation center coordinates (step S304).

[0062] The surface inspection device 30 has a rotation center VC. iThe arbitrary point vector PV is calculated from the coordinates of an arbitrary point Pn (step S305). Then, based on the arbitrary point vector PV, the direction vector BV is calculated (step S306), and a correction process is performed (step S307). The surface inspection device 30 determines whether the processed arbitrary point Pn is the last arbitrary point. If it is not the last arbitrary point (step S308; No), it selects the next arbitrary point (step S309) and proceeds to step S304.

[0063] In contrast, if the arbitrary point Pn that was processed is the last arbitrary point (step S308; Yes), the rotation center VC that was processed is i The final rotation center VC i It is determined whether or not this is the case (step S310). The rotation center VC that has been processed is determined. i The final rotation center VC i Otherwise (step S310; No), the next rotation center VC i Select (step S311) and proceed to step S303.

[0064] In contrast, the rotation center VC that was processed... i The final rotation center VC i If this is the case (step S310; Yes), then damage is detected (step S312), and the series of processes is terminated. Note that the correction process in Figure 10 (step S307) is the same as the correction process in Figure 4 of Embodiment 1 (step S108), so its explanation is omitted.

[0065] Thus, in this second embodiment, the surface inspection device 30 determines the rotation center VC based on the object surface image 101 captured by the imaging unit 20 of the object 100. i From this, determine the coordinates of an arbitrary point Pn within the range of rotation radius r ± tolerance δ, and the rotation center VC iThe vector direction from the point to an arbitrary point Pn is calculated, and the direction vector BV of the arbitrary point Pn is identified. Then, the brightness gradient angle caused by the machining marks SM at the arbitrary point Pn is calculated, and if the brightness gradient angle is within a predetermined range of the vector angle of the direction vector BV, the pixel value of the arbitrary point Pn is set to the average value of the surrounding area. This makes it possible to detect scratches such as dents on the machined surface while reducing the influence of machining marks.

[0066] In Embodiments 1 and 2 described above, the movement trajectory of the rotation center of the cutting tool was described using rotation center image data, which is a movement trajectory image in which predetermined pixel values ​​are assigned to pixels that form the movement trajectory of the rotation center of the cutting tool. However, the present invention is not limited to this, and may also be machining data including the trajectory of the rotation center. Alternatively, it may be coordinate data indicating the trajectory of the rotation center. Furthermore, the movement trajectory image in which predetermined pixel values ​​are assigned to pixels that form the movement trajectory of the rotation center of the cutting tool may be an image in bitmap format or vector format.

[0067] In Embodiments 1 and 2 described above, the case in which the brightness gradient angle of an arbitrary point Pn is determined and corrected was explained, but a line concentration filter can also be used. Furthermore, in Embodiments 1 and 2 described above, the case in which a face milling cutter is used as the cutting tool was explained, but the present invention is not limited thereto, and a polishing brush may also be used as the cutting tool.

[0068] The configurations illustrated in each of the above embodiments are functional schematics and do not necessarily have to be physically represented as shown. In other words, the distributed and integrated forms of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. [Industrial applicability]

[0069] The surface inspection apparatus and surface inspection method according to the present invention are suitable for detecting scratches such as dents on a machined surface while reducing the influence of machining marks generated on the machined surface when performing surface leveling by milling. [Explanation of symbols]

[0070] 10 Surface inspection device 11 Display section 12 Input section 14 Storage section 14a Rotation center image data 14b Image data 15 Control Unit 15a Image acquisition processing unit 15b Rotation center coordinate identification unit 15c Direction vector calculation unit 15d Brightness gradient angle determination unit 15e Correction processing unit 15f Scratch detection unit 20 Imaging Department 30 Surface inspection equipment 35 Control Unit 35a Arbitrary point coordinate specifying part 100 objects 101 Object surface image BV direction vector CV (Center of Rotation) vector L Rotation center trajectory Pn arbitrary point PV (Arbitrary Point Vector) P1, P2, P3, P4 Defective Surfaces r turning radius S surface SM machining marks SV machining trace vector VCi rotation center δ tolerance θC Rotation center vector angle θP is an arbitrary point vector angle.

Claims

1. A surface inspection method in a surface inspection apparatus that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, A first identification step of identifying a second pixel on the movement trajectory of the rotation center of the cutting tool that affects any first pixel forming the object surface image, A second identification step involves identifying the brightness gradient of a direction vector to a second pixel on the movement trajectory of the rotation center of the cutting tool, from among a plurality of brightness gradients in the first pixel identified by the first identification step, A correction step is performed to correct the pixel value of each pixel forming the object surface image based on the gradient angle determined by the second specific step described above. A surface inspection method characterized by including the following.

2. The surface inspection method according to claim 1, further comprising an inspection step of inspecting for scratches on the surface of the object that are not caused by machining marks resulting from the cutting process, based on the corrected image obtained by correcting the object surface image in the correction step.

3. The aforementioned cutting tool is The surface inspection method according to claim 1, characterized in that a plurality of blades are mounted on the circumference of a predetermined rotating body and the surface is formed to be rotatable about the predetermined axis of rotation, or a polishing brush for polishing the surface of an object.

4. The first specific step is, The surface inspection method according to claim 1, characterized in that a second pixel on the movement trajectory of the rotation center of the cutting tool that affects the first pixel forming the object surface image is identified using a movement trajectory image in which predetermined pixel values ​​are assigned to pixels forming the movement trajectory of the rotation center of the cutting tool.

5. The correction step is, The surface inspection method according to claim 4, characterized in that the pixel value of the first pixel on the object surface image that forms a gradient angle of the brightness gradient identified by the second specific step is corrected.

6. The correction step is, The surface inspection method according to claim 5, characterized in that the pixel value of the first pixel on the object surface image that forms a gradient angle of the brightness gradient identified by the second specific step is reduced.

7. A surface inspection method in a surface inspection apparatus that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, A first identification step of identifying a first pixel that is affected by a second pixel on the movement trajectory of the rotation center of the cutting tool, A second identification step, in which, among a plurality of brightness gradients in the first pixel identified by the first identification step, the brightness gradient of the direction vector from the second pixel to the first pixel on the movement trajectory of the rotation center of the cutting tool, A correction step is performed to correct the pixel value of each pixel forming the object surface image based on the gradient angle determined by the second specific step described above. A surface inspection method characterized by including the following.

8. A surface inspection device that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, A first identifying means for identifying a second pixel on the movement trajectory of the rotation center of the cutting tool that affects any first pixel forming the object surface image, A second identification means for identifying the brightness gradient of a direction vector to a second pixel on the movement trajectory of the rotation center of the cutting tool, among a plurality of brightness gradients in the first pixel identified by the first identification means, Correction means for correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified by the second identification means, A surface inspection apparatus characterized by being equipped with the following features.

9. A surface inspection device that inspects the surface of a predetermined object using an object surface image captured by an imaging unit that images the surface of an object that has been machined while rotating a cutting tool attached to a predetermined rotating shaft, A first identification means for identifying a first pixel that is affected by a second pixel on the movement trajectory of the rotation center of the cutting tool, A second identification means for identifying the brightness gradient of a direction vector from a second pixel to the first pixel on the movement trajectory of the rotation center of the cutting tool, among a plurality of brightness gradients in the first pixel identified by the first identification means, Correction means for correcting the pixel value of each pixel forming the object surface image based on the gradient angle identified by the second identification means, A surface inspection apparatus characterized by being equipped with the following features.

Images