Method for generating a processing device, program, and trained model

Abstract

To provide a processing device that quickly detects a processing mark with high accuracy from an image in which a processed workpiece is reflected, a program determining a boundary line reflected in the image, and a generation method of a learned model for a determination.SOLUTION: In a processing device for processing a processed workpiece 11, a cutting device 2 comprises: a chuck table 10 holding a processed workpiece; processing units 20A and 20B processing the processed workpiece held by the chuck table; an imaging unit 42 that images the processed workpiece held by the chuck table; and a control unit 56 that includes a processor and a memory. The control unit makes the imaging unit image a front surface 11a of the processed workpiece which is processed by the processing unit and to which a processing mark is formed to create information related to a boundary line reflected in an image acquired, and comprises a learned model that is constructed by a machine learning so as to input a determination result that indicates whether or not the boundary line is an edge of the processing mark when the information on the boundary line is input.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to a processing apparatus for processing a workpiece, a program for determining a boundary line shown in an image, a method for generating a learned model for generating a learned model for determining a boundary line shown in an image, and the like.

Background Art

[0002] By dividing a wafer on which a plurality of devices are formed into individual pieces, a plurality of device chips each including a device are manufactured. Further, a package substrate is formed by covering a plurality of device chips mounted on a mounting substrate with a sealing material (mold resin) made of resin. By dividing this package substrate into individual pieces, a plurality of package devices each including a packaged device chip are manufactured. Device chips and package devices are incorporated into various electronic devices such as mobile phones and personal computers.

[0003] When dividing a workpiece such as a wafer or a package substrate, a cutting device is used. The cutting device includes a chuck table for holding the workpiece and a processing unit (cutting unit) for performing cutting processing on the workpiece. The cutting unit incorporates a spindle, and an annular cutting blade is mounted on the tip of the spindle. The workpiece is held by the chuck table, and the cutting blade is rotated to cut into the workpiece, whereby the workpiece is cut and divided.

[0004] After processing the workpiece, a process of observing the processed area of the workpiece to inspect processing quality, processing accuracy, etc. may be performed. For example, Patent Document 1 discloses a cutting device capable of executing a process called kerf check for inspecting the presence or absence of processing defects (such as chipping of the workpiece, meandering of processing marks, displacement of processing mark positions, etc.) based on an image obtained by imaging the processed workpiece with a camera.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Japanese Patent Publication No. 2016-197702 [Overview of the project] [Problems that the invention aims to solve]

[0006] When performing a kerf check, it is necessary to identify the machining marks (kerf) from an image of the workpiece after processing. Conventionally, the machining marks were positioned near the center of the imaging unit's (camera's) field of view immediately after the workpiece was cut by the cutting unit, and an image of the workpiece was acquired by imaging the workpiece with the imaging unit. Image processing was then performed on the image to make it easier to extract the boundaries visible in the image, and the machining marks were identified by detecting the edges of the machining marks.

[0007] However, each type of workpiece has different complex structures (patterns of electrodes, wiring, terminals, circuits, etc.) formed on it, and the size and location of the processing marks formed on the workpiece may also differ depending on the type of workpiece. In addition, variations in the position and angle of the workpiece when imaging it, as well as variations in the intensity and color of the lighting, can cause variations in the image patterns and shading of the workpiece.

[0008] Thus, in processing equipment where various types of workpieces are imaged under various conditions, it is difficult to accurately identify processing marks with uniform image processing. Therefore, it has not been easy to appropriately identify the location of processing marks.

[0009] Furthermore, in order to improve the accuracy of detecting machining marks, it is conceivable to adjust the position and angle of the workpiece, the intensity and color of the lighting, etc., before imaging the workpiece to standardize the imaging conditions. However, if such work is performed every time the workpiece is imaged, the process and time required to identify machining marks will increase, and the processing efficiency of the workpiece by the processing equipment will decrease.

[0010] This invention has been made in view of the above problems, and aims to provide a processing device, etc., that can detect processing marks formed on a workpiece with high precision and speed. [Means for solving the problem]

[0011] According to one aspect of the present invention, a processing apparatus for processing a workpiece is provided, comprising: a chuck table for holding the workpiece; a processing unit for processing the workpiece held by the chuck table; an imaging unit for imaging the workpiece held by the chuck table; and a control unit having a processor and memory, wherein the control unit has a function to cause the imaging unit to image the surface of the workpiece processed by the processing unit and on which processing marks have been formed, and to create information about boundary lines captured in the acquired image, and is equipped with a trained model configured by machine learning to output a determination result indicating whether or not the boundary line is the edge of the processing mark when information about the boundary line is input.

[0012] Preferably, the information relating to the boundary line captured in the image includes one or more of the following: positional information of each point constituting the boundary line in the image; displacement of each point constituting the boundary line in a direction perpendicular to the position of the boundary line and the extension direction of the boundary line in the image; evaluation results of the straightness of the boundary line in the image; and the magnitude of the contrast ratio of the two regions on either side of the boundary line in the image.

[0013] Preferably, the control unit performs image processing on the image to enhance the boundary line to create a processed image, and creates information about the boundary line in the image based on the processed image.

[0014] Furthermore, according to another aspect of the present invention, a program is provided for determining whether a boundary line appearing in an image obtained by imaging a processed workpiece is the edge of a processing mark, and includes a trained model configured by machine learning to output a determination result indicating whether or not the boundary line is the edge of a processing mark when information about the boundary line appearing in the image is input, and is characterized by causing a computer to perform the following processes: inputting information about the boundary line into the trained model and performing calculations on the trained model.

[0015] Preferably, the information relating to the boundary line captured in the image includes one or more of the following: positional information of each point constituting the boundary line in the image; displacement of each point constituting the boundary line in a direction perpendicular to the position of the boundary line and the extension direction of the boundary line in the image; evaluation results of the straightness of the boundary line in the image; and the magnitude of the contrast ratio of the two regions on either side of the boundary line in the image.

[0016] Preferably, the computer is further instructed to perform image processing on the image to enhance the boundary line, create a processed image, detect the boundary line based on the processed image, and create information about the boundary line captured in the image.

[0017] Furthermore, according to another aspect of the present invention, a method for generating a trained model is provided for generating a trained model that determines whether or not a boundary line appearing in an image obtained by imaging a processed workpiece is the edge of a processing mark, comprising: an image acquisition step of imaging a sample corresponding to a processed workpiece on which a processing mark has been formed and acquiring an image; a detection step of detecting a boundary line appearing in the image acquired in the image acquisition step; an information acquisition step of acquiring first boundary line information relating to a boundary line corresponding to the edge of the processing mark and second boundary line information relating to a boundary line that does not correspond to the edge of the processing mark from among the boundary lines detected in the detection step; and a learning step of generating a trained model that, by machine learning using the first boundary line information and the second boundary line information, outputs a determination result indicating whether or not a boundary line is the edge of a processing mark when information regarding a boundary line appearing in an image obtained by imaging a processed workpiece is input.

[0018] Preferably, the first boundary information acquired in the information acquisition step includes one or more of the following: position information of each point constituting the boundary corresponding to the edge of the processing mark in the image; the position of the boundary corresponding to the edge of the processing mark in the image and the displacement of each point constituting the boundary in a direction perpendicular to the extension direction of the boundary corresponding to the edge of the processing mark; the evaluation result of the straightness of the boundary corresponding to the edge of the processing mark in the image; and the magnitude of the contrast ratio of the two regions on either side of the boundary corresponding to the edge of the processing mark in the image. The second boundary information acquired in the information acquisition step includes one or more of the following: position information of each point constituting the boundary that does not correspond to the edge of the processing mark in the image; the position of the boundary that does not correspond to the edge of the processing mark in the image and the displacement of each point constituting the boundary in a direction perpendicular to the extension direction of the boundary that does not correspond to the edge of the processing mark; the evaluation result of the straightness of the boundary that does not correspond to the edge of the processing mark in the image; and the magnitude of the contrast ratio of the two regions on either side of the boundary that does not correspond to the edge of the processing mark in the image.

[0019] Also, preferably, in the detection step, image processing for emphasizing the boundary line is performed on the image to create a processed image, and the boundary line is detected based on the processed image. In the information acquisition step, the processed image is used to acquire the first boundary line information and the second boundary line information.

Advantages of the Invention

[0020] In a processing apparatus or the like according to one aspect of the present invention, it is determined whether a boundary line shown in an image is an edge of a processing mark by a learned model configured by machine learning. Then, when performing a kerf check based on an image obtained by imaging a workpiece processed by a processing apparatus with an imaging unit, it is determined whether a boundary line shown in the image is an edge of a processing mark, and the processing mark is specified based on the result. Therefore, a false determination that determines a boundary line that is not an edge of a processing mark as an edge of a processing mark is prevented.

[0021] Further, by using the above-mentioned learned model, the characteristics of the edges of the processing marks are appropriately extracted for each workpiece. Therefore, even if the work of aligning the imaging conditions before imaging the workpiece is omitted, it is accurately determined whether the boundary line shown in the image is an edge of a processing mark. As a result, the processing marks formed on the workpiece can be detected with high precision and quickly, and an appropriate kerf check becomes possible.

Brief Description of the Drawings

[0022] [Figure 1] It is a perspective view showing a cutting apparatus. [Figure 2] FIG. 2(A) is a perspective view showing a workpiece, and FIG. 2(B) is a plan view showing a partially enlarged workpiece. [Figure 3] It is a perspective view showing a processing unit. [Figure 4] FIG. 4(A) is a perspective view showing a workpiece after cutting, and FIG. 4(B) is a plan view showing a partially enlarged workpiece after cutting. [Figure 5] It is a block diagram showing a control unit. [Figure 6]FIG. 6(A) is a plan view showing an image of the processed workpiece, and FIG. 6(B) is a plan view showing a processed image generated by performing image processing to emphasize the boundary line. [Figure 7] FIG. 7(A) is a front view showing a display unit that displays a boundary line determined to be an edge of a machining mark, and FIG. 7(B) is a front view showing a display unit that displays the probability that each boundary line is an edge of a machining mark. [Figure 8] It is a schematic diagram showing a learned model providing system. [Figure 9] It is a block diagram showing a cutting device at the time of generating a learned model. [Figure 10] FIG. 10(A) is a plan view showing an example of an image of a sample obtained in the image acquisition step, and FIG. 10(B) is a plan view showing a processed image obtained by performing image processing on the image of the sample. [Figure 11] It is a flowchart showing the flow of each step of the method for generating a learned model.

MODE FOR CARRYING OUT THE INVENTION

[0023] Hereinafter, an embodiment according to an aspect of the present invention will be described with reference to the accompanying drawings. First, a configuration example of the processing device according to the present embodiment will be described. FIG. 1 is a perspective view showing a cutting device 2. The cutting device 2 is a processing device that cuts a workpiece with an annular cutting blade. In FIG. 1, the X-axis direction (processing feed direction, left-right direction, first horizontal direction) and the Y-axis direction (indexing feed direction, front-rear direction, second horizontal direction) are perpendicular to each other. The Z-axis direction (vertical direction, up-down direction, height direction) is perpendicular to the X-axis direction and the Y-axis direction.

[0024] The cutting device 2 includes a rectangular parallelepiped base 4 that supports or accommodates each component of the cutting device 2. A rectangular opening 4a is provided at the front corner of the base 4. Inside the opening 4a is a cassette support base 6 that moves up and down by a lifting mechanism (not shown). A cassette 8 capable of accommodating multiple workpieces 11, which are the objects to be processed by the cutting device 2, is placed on the upper surface of the cassette support base 6. In Figure 1, only the outline of the cassette 8 is shown by a dashed line.

[0025] Figure 2(A) is a perspective view showing the workpiece 11. For example, the workpiece 11 is a disc-shaped wafer made of a semiconductor material such as single-crystal silicon, and has a surface (first surface) 11a and a back surface (second surface) 11b that are generally parallel to each other. The workpiece 11 is divided into multiple rectangular regions by multiple streets (planned division lines) 13 arranged in a grid pattern so as to intersect each other.

[0026] Devices 15, such as ICs (Integrated Circuits), LSIs (Large Scale Integrations), LEDs (Light Emitting Diodes), and MEMS (Micro Electro Mechanical Systems) devices, are formed on the surface 11a side of each of the multiple regions demarcated by the street 13. By dividing the workpiece 11 along the street 13, multiple device chips, each containing a device 15, can be obtained.

[0027] Figure 2(B) is a plan view showing an enlarged portion of the workpiece 11. Structures such as electrodes, wiring, terminals, and circuits are provided on the surface 11a side of the workpiece 11. For example, device 15 includes structures such as electrodes that constitute the device 15. In addition, parts of the thin films (conductive films, insulating films) that constitute the device 15, and structures such as TEGs (Test Element Groups) for inspecting the device 15 remain on the street 13. The arrangement of these structures forms a regular pattern on the surface 11a side of the workpiece 11.

[0028] When processing the workpiece 11 with the cutting device 2, the workpiece 11 is supported by an annular frame 17 for the convenience of handling (transporting, holding, etc.) the workpiece 11. The frame 17 is made of a metal such as SUS (stainless steel), and a circular opening 17a is provided in the center of the frame 17, penetrating the frame 17 in the thickness direction. The diameter of the opening 17a is larger than the diameter of the workpiece 11.

[0029] A circular tape 19 is attached to the workpiece 11 and the frame 17. For example, the tape 19 includes a circular film-like base material and an adhesive layer (glue layer) provided on the base material. The base material is made of a resin such as polyolefin, polyvinyl chloride, or polyethylene terephthalate. The adhesive layer is made of an epoxy, acrylic, or rubber-based adhesive. In addition, an ultraviolet-curing resin that hardens when exposed to ultraviolet light may be used for the adhesive layer.

[0030] The workpiece 11 is placed inside the opening 17a of the frame 17, and the central part of the tape 19 is attached to the back surface 11b of the workpiece 11, while the outer edge of the tape 19 is attached to the frame 17. The workpiece 11 is then supported by the frame 17 and placed in the cassette 8 (see Figure 1).

[0031] There are no restrictions on the type, material, shape, structure, size, etc., of the workpiece 11. For example, the workpiece 11 may be a substrate made of semiconductors other than silicon (GaAs, InP, GaN, SiC, etc.), sapphire, glass (quartz glass, borosilicate glass, etc.), ceramics, resin, metal, etc. There are also no restrictions on the type, quantity, shape, structure, size, arrangement, etc., of the devices 15.

[0032] Furthermore, the workpiece 11 may also be a package substrate such as a CSP (Chip Size Package) substrate or a QFN (Quad Flat Non-leaded package) substrate. For example, a package substrate is formed by encapsulating multiple device chips mounted on a mounting substrate with a resin layer (molding resin). By dividing the package substrate into individual pieces, multiple package devices, each containing multiple packaged device chips, can be manufactured.

[0033] As shown in Figure 1, a rectangular opening 4b is provided behind the opening 4a, with its longitudinal direction aligned with the X-axis. Inside the opening 4b, a chuck table (holding table) 10 for holding the workpiece 11 is provided. A moving unit (moving mechanism) 12 is connected to the chuck table 10 to move the chuck table 10 along the X-axis.

[0034] The moving unit 12 is, for example, a ball screw type moving mechanism, and comprises an X-axis ball screw (not shown) arranged along the X-axis direction and an X-axis pulse motor (not shown) that rotates the X-axis ball screw. The moving unit 12 also includes a flat table cover 14 that surrounds the chuck table 10. On both sides of the table cover 14 are bellows-shaped dustproof and waterproof covers 16 that can be extended and retracted along the X-axis direction. The table cover 14 and the dustproof and waterproof covers 16 are provided to cover the components of the moving unit 12 (X-axis ball screw, X-axis pulse motor, etc.) located inside the opening 4b.

[0035] The upper surface of the chuck table 10 is a flat surface that is generally parallel to the horizontal direction (XY plane direction) and constitutes a holding surface 10a for holding the workpiece 11. The holding surface 10a is connected to a suction source (not shown), such as an ejector, via a flow path (not shown), a valve (not shown), etc., provided inside the chuck table 10.

[0036] The chuck table 10 is connected to a rotational drive source (not shown), such as a motor, which rotates the chuck table 10 around a rotation axis that is approximately parallel to the Z-axis direction. In addition, multiple clamps 18 are provided around the chuck table 10 to grip and fix the annular frame 17 that supports the workpiece 11.

[0037] Near the openings 4a and 4b, a transport unit (not shown) is provided for transporting the workpiece 11 between the cassette 8 and the chuck table 10. The workpiece 11 is pulled out of the cassette 8 by the transport unit and transported to the chuck table 10. The workpiece 11 is then placed on the holding surface 10a of the chuck table 10 via the tape 19. The frame 17 is also held by a plurality of clamps 18. In this state, when the suction force (negative pressure) of the suction source is applied to the holding surface 10a, the workpiece 11 is held by the chuck table 10 via the tape 19.

[0038] Above the chuck table 10 are machining units (cutting units) 20A and 20B for cutting the workpiece 11. Each of the machining units 20A and 20B is fitted with a cutting blade 58 (see Figure 3), which will be described later.

[0039] On the upper surface of the base 4, a gate-shaped support structure 22 is provided along the Y-axis direction, straddling the opening 4b, to support the processing units 20A and 20B. At both ends on the front side of the support structure 22, there are moving units (moving mechanisms) 24A for moving the processing unit 20A along the Y-axis direction and the Z-axis direction, and moving units (moving mechanisms) 24B for moving the processing unit 20B along the Y-axis direction and the Z-axis direction. The moving units 24A and 24B are mounted on a pair of Y-axis guide rails 26 arranged along the Y-axis direction on the front side of the support structure 22.

[0040] The moving unit 24A includes a flat Y-axis moving plate 28A. The Y-axis moving plate 28A is slidably mounted on a pair of Y-axis guide rails 26. A nut portion (not shown) is provided on the back side (rear side) of the Y-axis moving plate 28A. A Y-axis ball screw 30A, which is positioned approximately parallel to the Y-axis guide rails 26, is screwed into this nut portion. A Y-axis pulse motor 32 is connected to the end of the Y-axis ball screw 30A. When the Y-axis pulse motor 32 rotates the Y-axis ball screw 30A, the Y-axis moving plate 28A moves in the Y-axis direction along the Y-axis guide rails 26.

[0041] A pair of Z-axis guide rails 34A are fixed to the front surface of the Y-axis moving plate 28A along the Z-axis direction. A flat Z-axis moving plate 36A is slidably mounted on the pair of Z-axis guide rails 34A. A nut portion (not shown) is provided on the back surface of the Z-axis moving plate 36A. A Z-axis ball screw 38A, which is positioned approximately parallel to the Z-axis guide rails 34A, is screwed into this nut portion. A Z-axis pulse motor 40A is connected to the end of the Z-axis ball screw 38A. When the Z-axis ball screw 38A is rotated by the Z-axis pulse motor 40A, the Z-axis moving plate 36A moves along the Z-axis guide rails 34A in the Z-axis direction.

[0042] Similarly, the moving unit 24B includes a flat Y-axis moving plate 28B. The Y-axis moving plate 28B is slidably mounted on a pair of Y-axis guide rails 26. A nut portion (not shown) is provided on the back side (rear side) of the Y-axis moving plate 28B. A Y-axis ball screw 30B, which is positioned approximately parallel to the Y-axis guide rails 26, is screwed into this nut portion. A Y-axis pulse motor 32 is connected to the end of the Y-axis ball screw 30B. When the Y-axis pulse motor 32 rotates the Y-axis ball screw 30B, the Y-axis moving plate 28B moves in the Y-axis direction along the Y-axis guide rails 26.

[0043] A pair of Z-axis guide rails 34B are fixed to the front surface of the Y-axis moving plate 28B along the Z-axis direction. A flat Z-axis moving plate 36B is slidably mounted on the pair of Z-axis guide rails 34B. A nut portion (not shown) is provided on the back surface of the Z-axis moving plate 36B. A Z-axis ball screw 38B, which is positioned approximately parallel to the Z-axis guide rails 34B, is screwed into this nut portion. A Z-axis pulse motor 40B is connected to the end of the Z-axis ball screw 38B. When the Z-axis ball screw 38B is rotated by the Z-axis pulse motor 40B, the Z-axis moving plate 36B moves along the Z-axis guide rails 34B in the Z-axis direction.

[0044] The processing units 20A and 20B are fixed to the lower part of the Z-axis moving plates 36A and 36B, respectively. An imaging unit 42 is also provided adjacent to the processing unit 20A.

[0045] The imaging unit 42 is equipped with an image sensor such as a CCD (Charged-Coupled Devices) sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) sensor, and captures images of the workpiece 11 held by the chuck table 10. There are no restrictions on the type of imaging unit 42; for example, a visible light camera or an infrared camera can be used. The imaging unit 42 may also be equipped with an illumination (light source) to illuminate the subject during imaging.

[0046] The images acquired by the imaging unit 42 are used for alignment between the workpiece 11 held by the chuck table 10 and the processing units 20A and 20B. Furthermore, as described later, a kerf check is performed based on the image of the workpiece 11 acquired by the imaging unit 42.

[0047] A circular opening 4c is provided behind the opening 4b. Inside the opening 4c is a cleaning unit 44 for cleaning the workpiece 11. The cleaning unit 44 includes a spinner table (chuck table) 46 that holds and rotates the workpiece 11, and a nozzle 48 that supplies cleaning liquid (cleaning solution) to the workpiece 11 held by the spinner table 46.

[0048] The upper surface of the spinner table 46 is a flat surface that is generally parallel to the horizontal direction (XY plane direction) and constitutes a holding surface 46a for holding the workpiece 11. The holding surface 46a is connected to a suction source (not shown), such as an ejector, via a flow path (not shown), a valve (not shown), etc., provided inside the spinner table 46. The spinner table 46 is also connected to a rotation drive source (not shown), such as a motor, which rotates the spinner table 46 around a rotation axis that is generally parallel to the Z-axis direction.

[0049] The nozzle 48 supplies cleaning fluid toward the holding surface 46a of the spinner table 46. As the cleaning fluid, a liquid such as pure water, or a mixed fluid produced by mixing a liquid (such as pure water) and a gas (such as air) can be used.

[0050] The workpiece 11 processed by processing unit 20A or processing unit 20B is transported to the spinner table 46 by a transport unit (not shown) and placed on the holding surface 46a of the spinner table 46 via the tape 19. In this state, when the suction force (negative pressure) of the suction source is applied to the holding surface 46a, the workpiece 11 is held by the spinner table 46 via the tape 19. Then, when cleaning liquid is dripped from the nozzle 48 toward the workpiece 11 while the spinner table 46 is rotated, the cleaning liquid flows along the upper surface of the workpiece 11, and the workpiece 11 is cleaned.

[0051] A cover 50 is provided on the upper side of the base 4 to cover the components of the cutting device 2 that are placed on the base 4. In Figure 1, only the outline of the cover 50 is shown by a dashed line.

[0052] A display unit (display unit, display device) 52 is provided on the front side of the cover 50 to display various information related to the cutting device 2. For example, a touch panel display is used as the display unit 52. In this case, the display unit 52 also functions as an input unit (input device) for inputting various information into the cutting device 2, and the operator can input information such as machining conditions into the cutting device 2 by touching the display unit 52. In other words, the display unit 52 functions as a user interface.

[0053] An alert unit (alert section, alert device) 54 is provided on the top of the cover 50 to inform the operator of information. For example, the alert unit 54 may be an indicator light (warning light), and when an abnormality occurs in the cutting device 2, the indicator light will light up or flash to notify the operator of the abnormality. The alert unit 54 may also be a speaker that informs the operator of information by sound or voice.

[0054] The components of the cutting apparatus 2 (cassette support base 6, chuck table 10, moving unit 12, clamp 18, processing units 20A, 20B, moving units 24A, 24B, imaging unit 42, cleaning unit 44, display unit 52, notification unit 54, etc.) are connected to a control unit (control unit, control device) 56. The control unit 56 controls the operation of the cutting apparatus 2 by outputting control signals to each component of the cutting apparatus 2.

[0055] For example, the control unit 56 is composed of a computer and includes a calculation unit that performs calculations necessary for the operation of the cutting device 2, and a storage unit that stores various information (data, programs, etc.) used for the operation of the cutting device 2. The calculation unit includes a processor such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The storage unit includes memory such as ROM (Read Only Memory) and RAM (Random Access Memory).

[0056] The workpieces 11 contained in the cassette 8 are transported one by one to the chuck table 10 by a transport unit (not shown). Then, the workpieces 11 are cut by the processing unit 20A or processing unit 20B while being held in place by the chuck table 10. After that, the workpieces 11 are transported to the washing unit 44 by a transport unit (not shown) and washed. After washing, the workpieces 11 are placed back into the cassette 8.

[0057] Figure 3 is a perspective view showing the machining unit 20A. The machining unit 20A is equipped with an annular cutting blade 58 for cutting the workpiece 11.

[0058] The processing unit 20A includes a hollow cylindrical housing 60. The housing 60 houses a cylindrical spindle 62 arranged along the Y-axis. The tip (one end) of the spindle 62 is exposed from the housing 60, and a rotational drive source (not shown), such as a motor, for rotating the spindle 62 is connected to the base (other end) of the spindle 62.

[0059] A blade mount 64 supporting a cutting blade 58 is fixed to the tip of the spindle 62. The blade mount 64 comprises a disc-shaped flange portion 66 and a cylindrical boss portion (support shaft) 68 protruding from the center of the surface 66a of the flange portion 66. On the outer circumference of the flange portion 66, on the surface 66a side, an annular projection 66b is provided along the outer edge of the flange portion 66, protruding from the surface 66a. The tip surface of the projection 66b is a flat surface that is generally parallel to the surface 66a and constitutes a support surface 66c that supports the cutting blade 58. In addition, a screw groove 68a is formed on the outer circumference of the boss portion 68.

[0060] An annular cutting blade 58 for cutting the workpiece 11 is mounted on the blade mount 64. The cutting blade 58 comprises an annular base 58a made of a metal such as an aluminum alloy, and an annular cutting edge 58b formed along the outer edge of the base 58a. In addition, a cylindrical opening 58c is provided in the center of the cutting blade 58, which penetrates the cutting blade 58 in the thickness direction.

[0061] The cutting edge 58b is formed to protrude radially outward from the outer edge of the base 58a. For example, the cutting edge 58b includes abrasive grains made of diamond, cubic boron nitride (cBN), etc., and a binder such as a nickel plating layer that fixes the abrasive grains. There are no restrictions on the material of the abrasive grains, the particle size of the abrasive grains, the material of the binder, etc., and they are appropriately selected according to the material of the workpiece 11, etc.

[0062] An annular fixing nut 70 for securing the cutting blade 58 is fastened to the threaded groove 68a of the boss portion 68. A cylindrical opening 70a is provided in the center of the fixing nut 70, penetrating the fixing nut 70 in the thickness direction. Furthermore, a threaded groove corresponding to the threaded groove 68a of the boss portion 68 is formed on the inner circumferential surface of the fixing nut 70 that is exposed inside the opening 70a.

[0063] The cutting blade 58 is mounted on the blade mount 64 such that the boss portion 68 is inserted into the opening 58c. In this state, when the fixing nut 70 is screwed into the threaded groove 68a of the boss portion 68 and tightened, the cutting blade 58 is clamped between the support surface 66c of the flange portion 66 and the fixing nut 70. In this way, the cutting blade 58 is mounted on the tip of the spindle 62. The cutting blade 58 then rotates around a rotation axis that is approximately parallel to the Y-axis direction by power transmitted from the rotation drive source via the spindle 62 and the blade mount 64.

[0064] Although the configuration of processing unit 20A was described above, processing unit 20B (see Figure 1) is configured similarly to processing unit 20A. A pair of cutting blades 58 are mounted in processing units 20A and 20B so as to face each other. In other words, the cutting device 2 is a so-called facing dual-spindle type cutting device. However, the cutting device 2 may have only one set of processing units.

[0065] The workpiece 11 is cut by the cutting device 2 described above. For example, by cutting the workpiece 11 along the street 13 with the cutting blade 58, the workpiece 11 is divided into multiple device chips. Below, as an example, we will describe the case in which the workpiece 11 is cut and divided by the cutting blade 58 mounted on the processing unit 20A. However, the workpiece 11 may also be cut by the cutting blade 58 mounted on the processing unit 20B.

[0066] When machining the workpiece 11 with the cutting device 2, the workpiece 11 is first held in place by the chuck table 10. For example, the workpiece 11 is placed on the chuck table 10 such that the front surface 11a is exposed upwards and the back surface 11b (tape 19 side) faces the holding surface 10a. The frame 17 is also fixed by multiple clamps 18. In this state, when the suction force (negative pressure) of the suction source is applied to the holding surface 10a, the workpiece 11 is held in place by the chuck table 10 via the tape 19.

[0067] Next, the workpiece 11 is cut along the street 13 (see Figure 2(A)) with the cutting blade 58. Specifically, first, the chuck table 10 is rotated to align the length of the predetermined street 13 with the X-axis direction. The position of the machining unit 20A in the Y-axis direction is also adjusted so that the cutting blade 58 is positioned on the extension of the predetermined street 13. Furthermore, the height of the machining unit 20A is adjusted so that the lower end of the cutting blade 58 is positioned below the back surface 11b (upper surface of the tape 19) of the workpiece 11. The difference in height between the surface 11a of the workpiece 11 and the lower end of the cutting blade 58 at this time corresponds to the depth of cut by the cutting blade 58 into the workpiece 11.

[0068] Then, while rotating the cutting blade 58, the chuck table 10 is moved along the X-axis. This causes the chuck table 10 and the cutting blade 58 to move relative to each other along the X-axis (machining feed), and the cutting blade 58 cuts into the workpiece 11 along the street 13. As a result, the workpiece 11 is cut and divided along the street 13. The same procedure is then repeated until the workpiece 11 is cut along all of the streets 13.

[0069] Figure 4(A) is a perspective view showing the workpiece 11 after cutting. When the workpiece 11 is cut with the cutting blade 58 as described above, machining marks (kerfs) 11c are formed along the street 13, extending from the surface 11a to the back surface 11b of the workpiece 11. As machining marks 11c are formed along all of the street 13, the workpiece 11 is divided along the street 13, resulting in multiple device chips, each containing a device 15.

[0070] Figure 4(B) is a plan view showing an enlarged portion of the workpiece 11 after cutting. For example, the machining marks 11c are formed linearly along the length of the street 13, at the center in the width direction of the street 13 (midpoint between adjacent devices 15). If a structure such as a TEG exists on the street 13, that structure is also cut along with the workpiece 11.

[0071] After processing the workpiece 11, a process called kerf check may be performed to inspect the processing quality, processing accuracy, etc., by observing the processed area of ​​the workpiece 11. In a kerf check, the processed area of ​​the workpiece 11 after processing is imaged by an imaging unit 42, and the presence or absence of processing defects (such as chipping of the workpiece 11, meandering of the processing marks 11c, or misalignment of the processing marks 11c) is inspected from the obtained image.

[0072] When performing a kerf check, it is necessary to identify the machining marks (kerfs) 11c from an image of the workpiece 11 after processing. Conventionally, immediately after cutting the workpiece 11 with the processing units 20A and 20b, the machining marks 11c were positioned near the center of the field of view of the imaging unit 42, and an image of the workpiece 11 was acquired by imaging the workpiece 11 with the imaging unit 42. Image processing was then performed on the image to make it easier to extract the boundaries of each element in the image, and the machining marks 11c were identified by detecting the edges of the machining marks 11c.

[0073] However, each type of workpiece 11 has different complex patterns (electrodes, wiring, terminals, circuits, etc.) formed on it, and the size and position of the processing marks 11c formed on the workpiece 11 may also differ depending on the type of workpiece 11. In addition, variations in the position and angle of the workpiece 11 when imaging the workpiece 11, as well as variations in the intensity and color of the illumination, may cause variations in the image pattern and density of the image of the workpiece 11.

[0074] Thus, in a cutting apparatus 2 where various types of workpieces 11 are processed under various conditions, it is difficult to accurately identify processing marks 11c by applying uniform image processing to images obtained by capturing the workpiece 11 after processing. Therefore, it has not been easy to accurately identify the formation location and shape of processing marks 11c.

[0075] Furthermore, in order to improve the detection accuracy of machining marks 11c, it is conceivable to adjust the position and angle of the workpiece 11, the intensity and color of the illumination, etc., before imaging the workpiece 11 to standardize the imaging conditions. However, if such work is performed every time the workpiece 11 is imaged, the process and time required to identify machining marks 11c will increase, and the processing efficiency of the workpiece 11 by the cutting device 2 will decrease.

[0076] Therefore, in this embodiment, a control unit 56 is used that detects a boundary line from an image obtained by imaging the surface 11a of the workpiece 11 on which the processing marks 11c are formed using an imaging unit 42, and creates information about the boundary line captured in the image. Then, when this boundary line information is input, a trained model configured by machine learning is used to output a determination result indicating whether or not the boundary line is the edge of the processing marks 11c formed on the workpiece 11.

[0077] This allows for the appropriate extraction of boundary line features from images captured under various conditions, and accurately determines whether the boundary line in the image is the edge of the processing mark 11c. Based on this result, the processing mark 11c is identified, and a calf check is performed based on the image. Therefore, misidentification of a boundary line that is not the edge of the processing mark 11c as the edge of the processing mark 11c is prevented, and an appropriate calf check can be performed.

[0078] Figure 5 is a block diagram of the control unit 56. In addition to a block diagram showing the functional configuration of the control unit 56, Figure 5 schematically illustrates the chuck table 10, imaging unit 42, display unit 52, and notification unit 54. The control unit 56 performs the determination of whether or not the boundary line captured in the image is the edge of the processing mark 11c. The control unit 56 includes an image processing unit 74, an information creation unit 76, and a determination unit 80 that determines whether or not the boundary line is a kerf edge.

[0079] When the imaging unit 42 images the workpiece 11, an enlarged image of the workpiece 11, image 72, is acquired and sent to the image processing unit 74. The image processing unit 74 processes image 72 to create a processed image 72a. The information creation unit 76 then uses the processed image 72a to identify the boundary lines visible in image 72 and creates information 78a and 78b regarding the boundary lines to be judged. The judgment unit 80 receives the information 78a and 78b regarding the boundary lines, and based on the information 78a and 78b, the judgment unit 80 determines whether the boundary line to be judged is a kerf edge or not and outputs the judgment result.

[0080] Furthermore, the control unit 56 includes a storage unit 82 capable of storing various types of information (data, programs, etc.) and a notification control unit 84 that notifies the notification unit (display unit 52, notification unit 54, etc.) of the result of the determination by the determination unit 80. The determination result of the determination unit 80 is output to the storage unit 82 and the notification control unit 84.

[0081] The configurations of the control unit 56 and the determination process will be described in detail. Figure 6(A) is a schematic plan view showing an image 72 formed by the imaging unit 42 imaging the processed workpiece 11. For the sake of explanation, Figure 6(A) shows a magnified view of the surface 11a of the workpiece 11 in a state where it has been processed in one direction and a processing mark 11c has been formed. The process of determining whether each boundary line along the direction shown in the image 72 is the edge of the processing mark 11c formed on the workpiece 11 will be explained below, but the following explanation can also be used to refer to the determination of boundary lines along other directions.

[0082] As shown in Figure 6(A), the image 72, which shows the surface 11a side of the workpiece 11 after processing, shows not only the processing marks 11c formed on the workpiece 11, but also each layer (each thin film) that makes up the device 15, and structures such as TEGs and electrodes formed on the street 13. Furthermore, the image 72 shows not only the edges (kerf edges) of the processing marks 11c, but also the contours of each layer that makes up the device 15 and the contours of structures formed on the street 13 as boundary lines 21a, 21b, 21c, 21d, 21e, 21f, and 21g.

[0083] In particular, in image 72, if the colors and textures on both sides of a certain boundary line are similar, it is not easy to detect the boundary line from image 72. Therefore, the image processing unit 74 of the control unit 56 of the cutting device (processing device) 2 performs image processing on image 72, which is formed by the imaging unit 42 imaging the workpiece 11, to enhance the boundary line so that it is easier to extract the boundary line. The resulting processed image 72a can be called a boundary line-enhanced image.

[0084] For example, when the image processing unit 74 recognizes a continuous area in image 72 where the color (hue, lightness, saturation) is almost the same as a single area, it emphasizes the boundary between two adjacent areas with different colors (hue, lightness, saturation) and does not emphasize areas other than the boundary in image 72, thereby creating a processed image depicted with lines. Here, it is possible to adjust the pixels that are emphasized as boundaries by adjusting the degree of color difference that is allowed for the same area. In other words, it is possible to adjust the detection sensitivity of the boundary.

[0085] Alternatively, the image processing unit 74 evaluates the color difference between each pixel constituting the image 72 and its surrounding pixels, and creates a processed image by highlighting the pixels with the largest color difference as pixels corresponding to the boundary. Here, the magnitude of the color difference between a pixel and its surrounding pixels, which serves as the criterion for determining whether or not a pixel should be highlighted as a boundary pixel, is adjustable. In other words, the sensitivity of boundary detection can be adjusted.

[0086] However, the image processing performed by the image processing unit 74 on image 72 is not limited to these, and there are no particular restrictions. Figure 6(B) is a schematic plan view showing the processed image 72a obtained by the image processing unit 74 performing image processing on image 72. In the processed image 72a shown in Figure 6(B), pixels corresponding to the boundary lines are colored white, and the other pixels are colored black. In this processed image 72a, the boundary lines can be easily detected.

[0087] The information creation unit 76 of the control unit 56 of the cutting device (processing device) 2 creates, for example, information 78a and 78b regarding the boundary lines captured in the image 72 based on the processed image 72a. However, the control unit 56 does not necessarily have an image processing unit 74, and the information creation unit 76 may directly create information regarding the boundary lines from the image 72 formed by the imaging unit 42 imaging the workpiece 11.

[0088] The following explanation will continue using the example of the case where the information creation unit 76 creates boundary line information 78a and 78b based on the processed image 72a. Here, boundary line information 78a and 78b is information that is useful when the determination unit 80 determines whether or not the boundary line is the edge of the processing mark 11c, as will be described later.

[0089] For example, the information 78a and 78b regarding the boundary lines in the image is the positional information of each point constituting the boundary line in image 72, or more specifically, the coordinates of each of these points in image 72. Alternatively, for example, the information 78a and 78b regarding the boundary lines in image 72 is a combination of the position of the boundary line in image 72 and the magnitude of the displacement or variation of each point constituting the boundary line in a direction perpendicular to the extension direction of the boundary line. In other words, the information 78a and 78b regarding the boundary lines in image 72 is a combination of the position of the reference line, which is a line segment along street 13, and the magnitude of the displacement or variation of each point constituting the boundary line in a direction perpendicular to street 13. This information reflects the shape of each boundary line.

[0090] Here, we will explain the correlation between the shape of the boundary line in Image 72 and the process of its formation. The machining marks 11c formed by cutting the workpiece 11 along the street 13 with the cutting blade 58 are formed in a straight line along the street 13. However, because minute chips and other irregularities occur randomly on the edges of the machining marks 11c, when observed from a microscopic perspective, the edges of the machining marks 11c are not straight, but rather consist of countless irregular shapes.

[0091] On the other hand, if variations in shape occur in the layers or structures formed on the workpiece 11, it is possible that variations in the performance of the device chip cut and formed from the workpiece 11 may occur, or that the device chip may not function properly. Therefore, the layers (each thin film) that make up the device 15, and structures such as TEGs formed on the street 13, are generally formed precisely on the workpiece 11 by processes such as photolithography.

[0092] Due to these circumstances, the contours of each layer (each thin film) and structures such as the TEG that make up the device 15 are composed of straight lines, broken lines, and curves without any disorder. Furthermore, when these contours are observed from a microscopic perspective, unlike the edges of the processing marks 11c, no random uneven shapes appear.

[0093] Thus, there is a significant difference in morphology between the edges of the processing marks 11c and the contours of the various layers (each thin film) and structures such as the TEG that make up the device 15. Conversely, there is a correlation between the shape of the boundary line in image 72 and the process by which that boundary line is formed. Therefore, based on the shape of the boundary line shown in the boundary line information 78a and 78b in image 72, it is possible to determine whether or not that boundary line is the edge of the processing marks 11c.

[0094] The boundary information 78a and 78b created by the information creation unit 76 is not limited to information that can identify the shape of the boundary. For example, the information creation unit 76 may directly evaluate the straightness of each boundary in the image 72, or output the evaluation result as boundary information 78a and 78b. If the straightness of the boundary in the image 72 is low, it can be determined that the boundary is the edge of the processing mark 11c.

[0095] Furthermore, the boundary information 78a and 78b created by the information creation unit 76 is not limited to information regarding the shape of the boundary. For example, the information creation unit 76 may evaluate the magnitude of the contrast ratio between the two regions on either side of the boundary in the image 72, and output this magnitude of the contrast ratio as boundary information 78a and 78b.

[0096] Here, we will explain the correlation between the magnitude of the contrast ratio between the two regions on either side of the boundary line in image 72 and the process by which that boundary line is formed. Light reaching the surface 11a of the workpiece 11 is reflected by the metal material formed on the surface 11a of the workpiece 11 and by the workpiece 11 itself, and reaches the imaging unit 42. The color of each structure, etc., shown in image 72 is determined by the type and surface shape of the metal material, etc. that reflects the light, and also by the type and thickness of the insulating film, etc. that overlaps each structure.

[0097] In any case, the imaging unit 42 receives light reflected from various structures formed on the surface 11a of the workpiece 11. On the other hand, there are no structures that reflect light at the height of the surface 11a on the machining marks 11c formed on the workpiece 11. Since the imaging unit 42 focuses on the surface 11a of the workpiece 11, the machining marks 11c usually appear extremely dark in the image 72.

[0098] Therefore, at the edges of the processing marks 11c, the contrast ratio between the two separated regions tends to be larger compared to the contours of each structure formed on the surface 11a of the workpiece 11. Conversely, among the boundary lines visible in the image 72, those where the magnitude of the contrast ratio between the two regions on either side of the boundary line exceeds a predetermined value can also be determined to be edges of the processing marks 11c. Therefore, when the information creation unit 76 outputs the magnitude of this contrast ratio, it is useful in determining whether or not the boundary line is an edge of the processing marks 11c.

[0099] The above shows examples of boundary line information 78a and 78b, but the boundary line information 78a and 78b are not limited to these. Furthermore, the boundary line information 78a and 78b do not need to be limited to just one of these, and may be a combination of multiple elements from these. In addition, some of the information exemplified does not need to be included in the boundary line information 78a and 78b created by the information creation unit 76, and may instead be used as detection conditions for detecting boundary lines that appear in image 72. The information creation unit 76 detects boundary lines from the processed image 72a, etc., and creates and outputs boundary line information 78a and 78b that appear in image 72.

[0100] The determination unit 80 in the control unit 56 of the cutting device (processing device) 2 receives information 78a and 78b regarding the boundary lines in the image 72 from the information creation unit 76 and includes a trained model 90 that determines whether or not the boundary lines in the image 72 are edges of the processing marks 11c. The trained model 90 is configured by machine learning to output a determination result indicating whether or not the boundary lines are edges (calf edges) of the processing marks 11c when information 78a and 78b regarding the boundary lines in the image 72 is input.

[0101] There are no restrictions on the type of pre-trained model 90; support vector machines (SVMs), logistic regression, k-nearest neighbors, decision trees, neural networks, etc., can be used. Below, we will explain the case where the pre-trained model 90 is a neural network (NN) as an example.

[0102] A neural network (NN) is a hierarchical neural network that includes an input layer 92 into which data is input, an output layer 94 that outputs data, and multiple hidden layers (intermediate layers) 96 placed between the input layer 92 and the output layer 94. Each of the input layer 92, output layer 94, and hidden layer 96 contains multiple neurons (units, nodes). The neurons in the input layer 92 are connected to the neurons in the first hidden layer 96, and the neurons in the output layer 94 are connected to the neurons in the final hidden layer 96. In addition, the neurons in the hidden layer 96 are connected to the neurons in the input layer 92 or the previous hidden layer 96, and to the neurons in the output layer 94 or the subsequent hidden layer 96.

[0103] There are no restrictions on the number of neurons in the input layer 92, output layer 94, and hidden layer 96, the activation function of each neuron, or the connectivity between neurons. There are also no restrictions on the number of hidden layers 96. A neural network (NN) containing two or more hidden layers 96 can be called a deep neural network (DNN). Furthermore, the training of a deep neural network can be called deep learning.

[0104] The neural network (NN) is trained to receive information 78a and 78b about the boundary lines in image 72 as input to the input layer 92, and then output a determination result from the output layer 94 indicating whether or not the boundary line is an edge (calf edge) of the processing mark 11c. There are no restrictions on the training method of the neural network (NN). Specific examples of neural network (NN) training methods will be described later.

[0105] After the workpiece 11 held by the chuck table 10 is processed by the processing units 20A and 20B, it is captured by the imaging unit 42 and an image 72 is obtained. When determining whether the boundary line shown in the image 72 is the edge of the processing mark 11c, the image processing unit 74 performs image processing on the image 72 to emphasize the boundary line, and a processed image 72a is created. Next, based on the processed image 72a, the information creation unit 76 detects the boundary line shown in the image 72, and information 78a and 78b related to the boundary line shown in the image 72 are created.

[0106] Subsequently, information 78a and 78b regarding the boundary lines in image 72 are input to the neural network NN, and the neural network NN uses inference to determine whether or not the boundary line is an edge of the processing mark 11c. Specifically, calculations using information 78a and 78b as input data are performed sequentially in the input layer 92, the hidden layer 96, and the output layer 94, and data corresponding to the classification result of whether the boundary line is an edge of the processing mark 11c or another boundary line is output from the output layer 94. This allows for automatic determination.

[0107] For example, the output layer 94 contains two neurons to which the softmax function is applied as the activation function. Each neuron outputs a numerical value (first output value) corresponding to the probability that the boundary line to be judged is an edge of the processing mark 11c, and a numerical value (second output value) corresponding to the probability that the boundary line to be judged is a boundary line other than an edge of the processing mark 11c.

[0108] Furthermore, the determination unit 80 includes a determination result processing unit 98 that processes the determination results made by the trained model 90. For example, the determination result processing unit 98 compares the first output value and the second output value output from the output layer 94 of the neural network NN.

[0109] If the first output value is greater than the second output value, the determination result processing unit 98 outputs a signal (first determination signal) indicating that the boundary line to be determined is the edge of the machining mark 11c. On the other hand, if the second output value is greater than the first output value, the determination result processing unit 98 outputs a signal (second determination signal) indicating that the boundary line to be determined is a boundary line other than the edge of the machining mark 11c. The first determination signal and the second determination signal correspond to the determination result by the determination unit 80.

[0110] However, there are no restrictions on the content of the processing performed by the determination result processing unit 98. For example, the determination result processing unit 98 may determine whether the boundary line to be judged is the edge of the processing mark 11c by comparing the first output value and the second output value with a pre-set threshold (lower limit).

[0111] Specifically, if the first output value is greater than or equal to a threshold, the judgment result processing unit 98 outputs a first judgment signal. On the other hand, if the second output value is greater than or equal to a threshold, the judgment result processing unit 98 outputs a second judgment signal. The threshold values ​​compared with the first and second output values ​​can be set appropriately according to the required judgment accuracy. For example, the threshold is set to 0.6 or higher (60% or higher), preferably 0.8 or higher (80% or higher).

[0112] The determination unit 80 of the control unit 56 performs a determination on all boundary lines to be determined using the trained model 90, and then has the determination result processing unit 98 perform processing on the determination result. Specifically, the trained model 90 receives information 78a and 78b regarding each boundary line to be determined, and outputs a first output value and a second output value corresponding to each. The determination result processing unit 98 processes the first output value and the second output value corresponding to each boundary line and outputs a first determination signal or a second determination signal, etc. The determination result processing unit 98 may also output the first output value corresponding to each boundary line input from the trained model 90 as is.

[0113] Furthermore, the processed mark 11c has a total of two edges, one on one side wall and the other on the other side wall. This can be used in the processing by the determination result processing unit 98. For example, even if both the first output value and the second output value are below a threshold for some of the boundary lines to be determined, it may be determined which boundary line is an edge of the processed mark 11c by comparing the first output value or the second output value corresponding to each boundary line.

[0114] More specifically, the determination result processing unit 98 outputs a signal (first determination signal) indicating that the boundary line is an edge of the machining mark 11c for any boundary line whose first output value is one of the top two values. Alternatively, it outputs a signal (first determination signal) indicating that the boundary line is an edge of the machining mark 11c for any boundary line whose second output value is one of the bottom two values. Then, the determination result processing unit 98 outputs a signal (second determination signal) indicating that the other boundary line is a boundary line other than an edge of the machining mark 11c.

[0115] Furthermore, the determination result processing unit 98 may output a signal (third determination signal) indicating that the series of determinations being performed by the determination unit 80 should be stopped when the number of boundary lines where the first output value is equal to or greater than the threshold exceeds three. Alternatively, the third determination signal may be output when the second output value is equal to or greater than the threshold for all boundary lines.

[0116] In these cases, the problem may lie in the image 72 itself or in the field of view of the imaging unit 42 when the image 72 was acquired. Therefore, when the third judgment signal is output from the judgment result processing unit 98, the control unit 56 should move the chuck table 10 and the processing units 20A and 20B relatively to allow the imaging unit 42 to reacquire the image 72 with a different field of view. The control unit 56 should then repeat the series of processes. Alternatively, when the third judgment signal is output from the judgment result processing unit 98, the control unit 56 may stop all processes and notify the operator of the error.

[0117] The result of the determination by the determination unit 80 is stored in the storage unit 82. The storage unit 82 is a computer-readable non-temporary recording medium that includes memory such as ROM and RAM. The storage unit 82 stores the determination result of the determination unit 80 together with the image 72. As a result, a dataset containing the image 72 and the determination result is accumulated in the storage unit 82.

[0118] Furthermore, the notification control unit 84 notifies the operator of the determination result of the determination unit 80. For example, the notification control unit 84 generates a control signal to display the determination result of the determination unit 80 on the display unit 52 and outputs it to the display unit 52. As a result, the determination result of the determination unit 80 is displayed on the display unit 52 and notified to the operator. Figures 7(A) and 7(B) show examples of display screens displayed on the display unit 52.

[0119] Figure 7(A) is a front view of a display unit 52 that displays a determination result display screen 52a showing the boundary line determined to be the edge of the processing mark 11c. For example, the determination result display screen 52a displayed by the display unit 52 includes an image 72 and a display field 52b that shows the boundary line determined to be the edge of the processing mark 11c. The display field 52b displays a string of characters (message), code, shape, symbol, etc., indicating that the boundary line is the edge (calf edge) of the processing mark 11c.

[0120] Figure 7(B) is a front view of a display unit 52 that displays a judgment result display screen 52c, which shows the probability that each boundary line subject to judgment is an edge of the processing mark 11c. For example, the judgment result display screen 52c displayed by the display unit 52 includes an image 72 and a display field 52d that shows the probability that each boundary line is an edge of the processing mark 11c. For example, the value corresponding to the first output value of each boundary line output from the trained model 90 is displayed as a percentage in the display field 52d as this probability.

[0121] When image 72 is displayed in both display fields 52b and 52d on the display unit 52, the operator can simultaneously check and compare image 72 with the judgment result. This allows the operator to confirm, based on their own judgment, whether the judgment made by the trained model 90 is valid or not.

[0122] The trained model 90 may be implemented using either software or hardware. For example, the operations in the input layer 92, output layer 94, and hidden layer 96 of the neural network NN may be described by a program, and this program may be stored in the memory unit 82. Similarly, the image processing unit 74 and information creation unit 76 of the control unit 56 may also be implemented using either software or hardware. For example, the processing performed by the image processing unit 74 and information creation unit 76 may be described by a program, and this program may be stored in the memory unit 82.

[0123] Then, when identifying the edges of the processing marks 11c from the boundary lines shown in image 72, these programs are read from the memory unit 82 and executed by the control unit 56. As a result, the computer performs the processes of inputting information 78a and 78b about each boundary line into the trained model 90 and performing calculations on the trained model 90, and it is determined whether or not each boundary line is an edge of the processing marks 11c.

[0124] The determination of whether each boundary line shown in image 72 is an edge of the machining mark 11c is performed at a predetermined timing after machining the workpiece 11 and prior to the kerf check performed by the control unit 56. The control unit 56 then identifies the area between the two boundary lines determined to be edges of the machining mark 11c shown in image 72 as the machining mark 11c, and performs a predetermined process related to the kerf check on the identified machining mark 11c.

[0125] If, in this case, two boundary lines that can be determined to be the edges of the processing marks 11c cannot be identified from the boundary lines shown in image 72, and the processing marks 11c shown in image 72 cannot be identified, the notification control unit 84 may cause the display unit 52 and the notification unit 54 to send a warning. Also, even if the processing marks 11c shown in image 72 are identified, if the kerf check is performed and it is confirmed that the processing marks 11c are not formed to a predetermined quality, the notification control unit 84 may cause the display unit 52 and the notification unit 54 to send a warning.

[0126] For example, the notification control unit 84 outputs a control signal to the display unit 52, causing the display unit 52 to display a message indicating the occurrence and nature of an abnormality. The notification control unit 84 also outputs a control signal to the notification unit 54, causing the notification unit 54 to light up in a predetermined color or pattern. This notifies the operator of any abnormalities in the processing status of the workpiece 11, enabling the operator to take appropriate measures according to the nature of the abnormality.

[0127] As described above, the cutting apparatus 2 according to this embodiment is equipped with a control unit 56 that has a trained model 90 capable of determining whether each boundary line visible in the image of the workpiece 11 (image 72) is an edge of a machining mark 11c. This makes it possible to identify machining marks 11c visible in image 72 with high accuracy and speed prior to kerf checking, thereby preventing false detection of machining marks 11c and inappropriate kerf checking.

[0128] Furthermore, the trained model 90, constructed using machine learning, can extract features 78a and 78b related to each boundary line from images 72 of the workpiece 11 acquired under various imaging conditions, and determine whether or not the boundary line is the edge of a machining mark 11c, thus offering high versatility. Therefore, even when various structures formed on the surface 11a of the workpiece 11, the size and position of the machining marks 11c, etc., differ for each type of workpiece 11, the features 78a and 78b related to the boundary lines are appropriately extracted, and the edge of the machining mark 11c can be identified with high accuracy.

[0129] Furthermore, the trained model 90, constructed using machine learning, is generated from images 72 of the workpiece 11 acquired under various imaging conditions. Therefore, even if the work of standardizing imaging conditions before imaging the workpiece 11 (adjusting the position and angle of the workpiece 11, adjusting the light intensity and color of the illumination, etc.) is omitted, it is possible to correctly determine whether each boundary line is an edge of the processing mark 11c. This makes it possible to determine the edges of the processing mark 11c in the image 72 with high accuracy and speed.

[0130] Here, we will explain how to perform a kerf check using the cutting apparatus 2 according to this embodiment, which is configured as described above, and summarize the cutting apparatus 2 according to this embodiment. The cutting apparatus 2 cuts (processes) the workpiece 11 to form a processing mark 11c along the street 13 on the workpiece 11. Then, the surface 11a of the workpiece 11 on which the processing mark 11c has been formed is imaged by the imaging unit 42 as shown in Figure 5 to obtain an image 72.

[0131] Subsequently, the control unit 56 performs predetermined image processing on image 72 to generate a processed image 72a, and uses this processed image 72a to detect boundary lines in image 72. The control unit 56 then creates information 78a and 78b regarding the boundary lines in image 72 and inputs this into the trained model 90. The trained model 90 then outputs a determination result indicating whether or not these boundary lines are the edges (kerf edges) of the machining marks 11c formed on the workpiece 11.

[0132] This allows for the appropriate extraction of boundary line features from images 72 acquired under various conditions, and enables accurate determination of whether or not the boundary line in image 72 is the edge of the processing mark 11c. Therefore, misidentification of a boundary line that is not the edge of the processing mark 11c as the edge of the processing mark 11c is prevented, enabling proper calf checking.

[0133] In other words, the region between the two boundary lines identified as edges of the processing marks 11c by the trained model 90 is highly likely to be the region where the processing marks (kerf) 11c are visible in image 72. Therefore, the control unit 56 should perform a kerf check on the processing marks 11c visible in image 72 to evaluate the condition of the processing marks 11c and the precision of the processing.

[0134] If, as a result of the training model 90, no boundary line determined to be the edge of the processing mark 11c is detected in the image 72, the control unit 56 changes the area of ​​the workpiece 11 being imaged by the imaging unit 42 and repeats the series of processes. Alternatively, the control unit 56 may cause the display unit 52 and the notification unit 54 to issue a warning.

[0135] There are no restrictions on how the pre-trained model 90 can be installed in the cutting device 2. For example, the manufacturer of the cutting device 2 can generate the pre-trained model 90, incorporate it into the cutting device 2, and then provide the cutting device 2 to the user. Alternatively, the manufacturer of the cutting device 2 can provide the user with a cutting device 2 equipped with the pre-trained model 90 retrospectively by distributing the pre-trained model 90 to the user's conventional cutting device (a cutting device that does not have the pre-trained model 90 installed).

[0136] Figure 8 is a schematic diagram showing a trained model provision system 100 that provides a trained model 90 to a cutting machine 2A. The trained model provision system 100 includes a distribution unit 102 that distributes the trained model 90, and a network 104 that connects the distribution unit 102 to multiple cutting machines 2 used by the user.

[0137] The distribution unit 102 corresponds to a server or the like managed by the manufacturer of the cutting device 2, and is connected to the network 104 by wire or wireless. The cutting device 2A is a conventional cutting device used by the user and does not have a pre-trained model 90 built in. The configuration of the cutting device 2A is the same as that of the cutting device 2 (see Figure 1), except for the presence or absence of the pre-trained model 90. The control unit 56 of the cutting device 2A is connected to the network 104 by wire or wireless.

[0138] The manufacturer of the cutting device 2 manages the distribution unit 102 and distributes the trained model 90 from the distribution unit 102 to the cutting device 2A via the network 104. Specifically, first, the manufacturer of the cutting device 2 generates the trained model 90 using machine learning and creates a program 106 that describes the trained model 90. The program 106 may include processes that cause the computer to execute the functions of the image processing unit 74 and the information creation unit 76.

[0139] Program 106 is a program that causes the computer to perform the following processes: inputting boundary information 78a and 78b into the trained model 90, and performing calculations on the trained model 90. Furthermore, program 106 may also cause the computer to perform the following processes: performing image processing on image 72, and creating boundary information 78a and 78b that are captured in image 72.

[0140] The manufacturer of the cutting device 2 then supplies the program 106 to the cutting device 2A via the network 104, in response to the user's request. The program 106, distributed by the distribution unit 102, is received by the cutting device 2A and stored in the control unit 56 of the cutting device 2A. This results in the production of the cutting device 2 equipped with the learned model 90. The control unit 56 of the cutting device 2 then reads and executes the program 106 at a predetermined timing to determine whether the boundary line shown in the image 72 is the edge of the machining trace 11c (see Figure 5).

[0141] Furthermore, the manufacturer of the cutting device 2 may also provide the program 106 using a recording medium 108. Specifically, the manufacturer of the cutting device 2 provides the user of the cutting device 2A with a recording medium 108 on which the program 106 is stored. The recording medium 108 is a computer-readable non-temporary recording medium such as an optical disc or flash memory. The user of the cutting device 2A then has the control unit 56 read and store the program 106 stored on the recording medium 108.

[0142] As described above, by distributing the program 106 using the network 104 or recording medium 108, the user can retrospectively install the trained model 90 into the cutting machine 2A that is currently in use. Furthermore, if the trained model 90 is updated, the manufacturer of the cutting machine 2 can distribute a program describing the updated trained model 90, or data corresponding to the parameters of the updated trained model 90, using the network 104 or recording medium 108. This ensures that the user is provided with a cutting machine 2 equipped with the latest trained model 90.

[0143] Next, a specific example of the method for generating a trained model according to this embodiment will be described. For example, the trained model 90 is generated by performing supervised learning using information about boundary lines, which are edges of processing marks, and information about boundary lines that are not edges of processing marks. Figure 11 is a flowchart showing the flow of each step in the method for generating a trained model according to this embodiment. Below, as an example, the method for generating a trained model using the cutting device 2 will be described in detail.

[0144] Figure 9 is a block diagram showing the cutting apparatus 2 during the generation of the trained model 90. When generating the trained model 90, first, an image is acquired by imaging a sample (workpiece for image acquisition, workpiece for training) 23 on which machining marks 11c have been formed, corresponding to the machined workpiece 11 (image acquisition step S10).

[0145] Sample 23 is a workpiece having the same or similar configuration as the workpiece 11 to be processed by the cutting device 2. For example, Sample 23 is a disc-shaped wafer made of the same material as the workpiece 11, and has a surface (first surface) 23a and a back surface (second surface) 23b that are generally parallel to each other. Furthermore, Sample 23 is divided into multiple regions by multiple streets (planned division lines) arranged in a grid pattern so as to intersect each other, and a device is formed on the surface 23a side of each of the multiple regions divided by the streets.

[0146] The structure, dimensions, and arrangement of the device are the same as those of device 15 of the workpiece 11 (see Figure 2(A)). In addition, structures such as electrodes, wiring, terminals, and circuits are provided on the surface 23a side of sample 23, forming a regular pattern.

[0147] Sample 23 is placed inside the opening of the annular frame 29 and supported by the frame 29 via the tape 31. The material and structure of the frame 29 and tape 31 are the same as those of frame 17 and tape 19 (see Figure 2(A)). Sample 23 is then housed in cassette 8 (see Figure 1) while supported by the frame 29.

[0148] In the image acquisition step S10, the sample 23 contained in the cassette 8 (see Figure 1) is first transported to the chuck table 10 and held by the chuck table 10. The operation of the cutting device 2 when the sample 23 is transported and held is the same as when the workpiece 11 is transported and held.

[0149] Next, sample 23 is processed. For example, sample 23 is cut along the street with a cutting blade 58 (see Figure 3) to divide it into multiple chips. The operation of the cutting device 2 when cutting sample 23 is the same as when cutting workpiece 11. When sample 23 is processed, a processing mark (kerf) is formed on sample 23 along the street, from the surface 23a to the back surface 23b. Then, in the image acquisition step S10, the surface 23a side of sample 23 is imaged by the imaging unit 42, and an image of the processed sample 23 is acquired.

[0150] Figure 10(A) is an image (captured image, training image) 110A of sample 23 including processing marks 23c. For ease of explanation, Figure 10(A) shows a magnified view of the surface 23a of sample 23 in a state where processing has been carried out along one direction and processing marks 23c have been formed along the same direction. Processing marks 23c formed on sample 23 may also be formed along streets in other directions.

[0151] As shown in Figure 10(A), image 110A, which shows the surface 23a side of the processed sample 23, shows not only the processing marks 23c formed on the sample 23, but also each layer (each thin film) that makes up the device 27, and structures such as TEGs and electrodes formed on the street 25. Furthermore, in image 110A, not only the edges (calf edges) of the processing marks 23c, but also the contours of each layer that makes up the device 27 and the contours of structures formed on the street 25 are shown as boundary lines 33a, 33b, 33c, 33d, 33e, 33f, and 33g.

[0152] Furthermore, in the image acquisition step S10, the imaging unit 42 may be raised and lowered along the Z-axis using the moving unit 24A (see Figure 1) to change the imaging range and focal position of the imaging unit 42, while capturing the sample 23 multiple times. This allows for the acquisition of multiple images 110A with different magnifications and degrees of blurring.

[0153] Furthermore, the imaging unit 42 may be equipped with lighting to illuminate the sample 23 during imaging. In this case, in the image acquisition step S10, multiple images 110A with different brightness or saturation may be acquired by imaging the sample 23 multiple times while changing the amount or color of the light irradiated onto the sample 23 from the lighting. By imaging the processed sample 23 multiple times as described above, for example, 1000 to 2000 images 110A may be acquired.

[0154] Next, a detection step S20 is performed to detect the boundary lines in the image 110A acquired in the image acquisition step S10. In the detection step S20, first, the image processing unit 74 of the control unit 56 performs image processing on the image 110A to enhance the boundary lines in order to facilitate boundary line extraction. The resulting processed image can be called a boundary line-enhanced image.

[0155] The image processing performed by the image processing unit 74 on image 110A is the same as the image processing performed by the image processing unit 74 on image 72 (see Figure 6(A)). Therefore, the explanation is omitted here. Figure 10(B) is a schematic plan view showing the processed image 110B obtained by the image processing unit 74 performing image processing on image 110A. That is, in the detection step S20, it is preferable to perform image processing on image 110A to emphasize the boundary lines and create the processed image 110B. In the processed image 110B shown in Figure 10(B), pixels corresponding to the boundary lines are colored white, and the other pixels are colored black.

[0156] In detection step S20, the boundary lines visible in image 110A are detected based on the processed image 110B. For example, the information creation unit 76 of the control unit 56 detects the boundary lines visible in image 110A based on the processed image 110B. Subsequently, for each boundary line detected in detection step S20, an information acquisition step S30 is performed to acquire information about the boundary line. In information acquisition step S30, information about the boundary lines visible in image 110A is created mainly by the functions of the information creation unit 76.

[0157] Here, the procedure by which the information creation unit 76 creates information about the boundary lines visible in image 110A is almost the same as the procedure by which the information creation unit 76 creates information about the boundary lines visible in image 72 (see Figure 6(A)) 78a and 78b (see Figure 5), so redundant explanations are omitted.

[0158] Furthermore, the information regarding the boundaries captured in the image 110A created by the information creation unit 76 will be used as training data for supervised learning in the learning step S40 described below. For this purpose, in the information acquisition step S30, label information indicating whether or not the boundary is the edge of the processing mark 23c formed on the sample 23 is added to the information regarding each boundary captured in the image 110A.

[0159] Figure 10(B) is a schematic plan view of the processed image 110B. Figure 10(B) shows an example of labels for detected boundaries in image 110A. Each label is created, for example, by an operator using the cutting device 2. In this case, the control unit 56 displays image 110A or the processed image 110B and the detected boundaries on the display unit 52.

[0160] The operator then sequentially checks each detected boundary line and inputs a label (classification information) indicating whether it is a "calf edge" or "other boundary line." For example, as shown in Figures 10(A) and 10(B), boundary lines 33a and 33b are labeled as "calf edges," while boundary lines 33c, 33d, 33e, 33f, and 33g are labeled as "other boundary lines."

[0161] In this way, labels are added to each piece of information relating to the boundary lines shown in image 110A, creating boundary line information 78c and 78d, which are stored in the learning information storage unit 82a included in the storage unit 82. More specifically, in the information acquisition step S30, first boundary line information 78c relating to the boundary line corresponding to the edge of the processing mark 23c, and second boundary line information 78d relating to the boundary line not corresponding to the edge of the processing mark are created and acquired. The acquired first boundary line information 78c and second boundary line information 78d are stored in the learning information storage unit 82a as training data.

[0162] Here, the first boundary information 78c acquired in the information acquisition step S30 includes, for example, positional information of each point constituting the boundary line corresponding to the edge of the processing mark 23c in image 110A. Alternatively, it may include the position of the boundary line corresponding to the edge of the processing mark 23c in image 110A and the displacement of each point constituting the boundary line in a direction perpendicular to the extension direction of the boundary line corresponding to the edge of the processing mark 23c. Furthermore, it may include the evaluation result of the straightness of the boundary line corresponding to the edge of the processing mark 23c in image 110A, and may also include the magnitude of the contrast ratio of the two regions on either side of the boundary line corresponding to the edge of the processing mark 23c in image 110A. The first boundary information 78c includes one or more of these.

[0163] Furthermore, the second boundary information 78d acquired in the information acquisition step S30 includes, for example, positional information of each point constituting the boundary that does not correspond to the edge of the processing mark 23c in image 110A. Alternatively, it may include the position of the boundary that does not correspond to the edge of the processing mark 23c in image 110A and the displacement of each point constituting the boundary in a direction perpendicular to the extension direction of the boundary that does not correspond to the edge of the processing mark 23c. In addition, it may include an evaluation result of the straightness of the boundary that does not correspond to the edge of the processing mark 23c in image 110A, and may also include the magnitude of the contrast ratio of the two regions on either side of the boundary that does not correspond to the edge of the processing mark 23c in image 110A. The second boundary information 78d includes one or more of these.

[0164] Furthermore, in order to generate a trained model with high judgment accuracy in the learning step S40 described next, the image acquisition step S10, detection step S20, and information acquisition step S30 described so far may be repeated. In addition, a large number of first boundary information 78c and second boundary information 78d may be acquired. For example, if 1000 to 2000 images 110A are acquired, image processing is performed on each image 110A, the boundary lines in each image 110A are detected, and the first boundary information 78c and second boundary information 78d are acquired.

[0165] Furthermore, when the cutting device 2 processes multiple types of workpieces 11 with different materials, structures, dimensions, etc., the image acquisition step S10, the detection step S20, and the information acquisition step S30 are performed using multiple types of samples 23 corresponding to each workpiece 11. As a result, first boundary information 78c and second boundary information 78d are collected for each type of sample 23.

[0166] Furthermore, the first boundary information 78c and the second boundary information 78d used as training data may be collected by other methods. For example, if images of the processed workpiece 11 acquired in the past are stored in a database or the like, the first boundary information 78c and the second boundary information 78d may be created and acquired from the images of the workpiece 11.

[0167] Next, we will describe the learning step S40, which generates a trained model that, when information about a boundary line appearing in an image obtained by imaging a processed workpiece is input, outputs a determination result indicating whether or not the boundary line is the edge of a processing mark. In learning step S40, a trained model is generated by machine learning using the first boundary line information 78c and the second boundary line information 78d.

[0168] For example, in learning step S40, supervised learning is performed using first boundary information 78c, which includes classification information that the boundary is a "calf edge," and second boundary information 78d, which includes classification information that the boundary is another boundary, as training data. Specifically, the first boundary information 78c and the second boundary information 78d are input to the neural network NN, and classification information of "calf edge" or "another boundary" is input to the neural network NN as the correct label.

[0169] Then, the parameters of the neural network (NN) (such as neuron weights and biases) are updated so that the error between the output of the neural network (NN) and the correct label is minimized. As a result, the neural network (NN) is reconfigured so that when information about a boundary line is input to the input layer 92, the output layer 94 outputs a determination result indicating whether or not that boundary line is a machined edge (kerf edge). For example, backpropagation can be used as a learning algorithm.

[0170] The trained neural network NN is stored in the control unit 56. This results in a cutting machine 2 equipped with the trained model 90. Alternatively, the calculations for training the neural network NN may be performed by a large-scale, high-performance computer located outside the cutting machine 2. In this case, the trained neural network NN (or the parameters of the trained neural network NN) are input to and stored in the control unit 56.

[0171] As described above, in the method for generating a trained model according to this embodiment, a large amount of boundary information 78c and 78d used for training is acquired by sequentially performing imaging of the sample 23 on which the processing marks 23c are formed, boundary detection, creation of boundary information, and addition of boundary classification information. This makes it possible to efficiently collect a large amount of training data necessary for generating the trained model 90.

[0172] Furthermore, according to the trained model 90, misidentification of a boundary line in the image 72 showing the processed workpiece 11, which is not the edge of a processing mark, as the edge of a processing mark is prevented. As a result, processing marks 11c formed on the workpiece 11 can be detected with high accuracy and speed, enabling appropriate kerf checking.

[0173] In the above embodiment, the case described was one in which, in an image 72 showing the processed workpiece 11, a trained model 90 was used to determine whether a boundary line along one direction is the edge (calf edge) of the processing mark 11c. However, the present invention is not limited to this, and the trained model 90 may also be used to determine whether a boundary line along another direction shown in the image 72 is the edge (calf edge) of the processing mark 11c.

[0174] The trained model 90 may also output a determination result that determines whether the boundary line along the first direction in which the processed workpiece 11 is captured in the image 72, or the boundary line along the second direction, is an edge (calf edge) of the processing mark 11c. In this case, the trained model 90 should be generated by machine learning in the same manner as described above so that it can determine both the boundary line along the first direction in which the image 72 is captured and the boundary line along the second direction.

[0175] Furthermore, the structures, methods, etc., according to the above embodiments can be modified as appropriate without departing from the scope of the objectives of the present invention. [Explanation of Symbols]

[0176] 11 Workpiece 11a, 23a Surface (first side) 11b, 23b Back side (2nd side) 11c, 23c processing marks (calfskin) 13,25 Street (planned division line) 15,27 devices 17,29 frames 17a aperture 19,31 Tape 21a,21b,21c,21d,21e,21f,21g border 23 samples 33a,33b,33c,33d,33e,33f,33g border 2,2A cutting equipment 4 bases 4a,4b,4c opening 6 Cassette support stand 8 cassettes 10. Chuck table (holding table) 10a Holding surface 12. Mobile Unit (Movement Mechanism) 14 Table Covers 16 Dustproof and splashproof cover 18 clamps 20A, 20B Machining Unit (Cutting Unit) 22 Support structure 24A, 24B Mobile Unit (Mobile Mechanism) 26 Y-axis guide rail 28A, 28B Y-axis moving plate 30A, 30B Y-axis ball screw 32 Y-axis pulse motor 34A, 34B Z-axis guide rail 36A, 36B Z-axis movement plate 38A, 38B Z-axis ball screw 40A, 40B Z-axis pulse motor 42 Imaging Units 44 Washing Unit 46 Spinner Table (Chuck Table) 46a Holding surface 48 nozzles 50 Covers 52 Display unit (display section, display device) 52a,52c Judgment result display screen 52b,52d Display column 54. Notification Unit (Notification Section, Notification Device) 56 Control Unit (Control Unit, Control Device) 58 cutting blades 58a base 58b Cutting blade 58c aperture 60 Housing 62 spindles 64 Blade Mount 66 Flange section 66a surface 66b Convex part 66c support surface 68 Boss section (support shaft) 68a Thread groove 70 Fixing nut 70a aperture 72 images 72a Processed image 74 Image Processing Unit 76 Information Creation Department Information for 78a, 78b, 78c, and 78d. 80 Judgment section 82 Memory section 84 Notification Control Unit 90 pre-trained models 92 Input Layers 94 Output Layers 96 Hidden Layer (Mesosphere Layer) 98. Determination Result Processing Unit 100 Pre-trained Model Provisioning Systems 102 Distribution Department 104 Network 106 Programs 108 Recording media 110A Image 110B Processed Image

Claims

1. A processing device for processing a workpiece, A chuck table for holding the workpiece, A processing unit for processing the workpiece held by the chuck table, An imaging unit for imaging the workpiece held by the chuck table, A control unit having a processor and memory, The control unit is, The processing unit has a function to cause the imaging unit to image the surface of the workpiece on which processing marks have been formed, and to create information about the boundary lines that appear in the acquired image. The system includes a pre-trained model configured by machine learning to output a determination result indicating whether or not the boundary line is the edge of the processing mark, when information about the boundary line is input. The processing apparatus is characterized in that the information relating to the boundary line captured in the image includes one or more of the following: positional information of each point constituting the boundary line in the image; displacement of each point constituting the boundary line in a direction perpendicular to the position of the boundary line and the extension direction of the boundary line in the image; evaluation result of the straightness of the boundary line in the image; and magnitude of the contrast ratio of the two regions on either side of the boundary line in the image.

2. The processing apparatus according to claim 1, characterized in that the control unit performs image processing on the image to enhance the boundary line to create a processed image, and creates information regarding the boundary line depicted in the image based on the processed image.

3. A program for determining whether a boundary line appearing in an image obtained by imaging a processed workpiece is the edge of a processing mark, The system includes a pre-trained model configured by machine learning to output a determination result indicating whether or not the boundary line is the edge of a processing mark, when information about the boundary line in the image is input. The process of inputting information about the boundary line into the trained model, The process of performing calculations on the trained model is to be executed by a computer, The program is characterized in that the information relating to the boundary line captured in the image includes one or more of the following: positional information of each point constituting the boundary line in the image; displacement of each point constituting the boundary line in a direction perpendicular to the position of the boundary line and the extension direction of the boundary line in the image; evaluation result of the straightness of the boundary line in the image; and magnitude of the contrast ratio of the two regions on either side of the boundary line in the image.

4. A process of performing image processing on the image to enhance the boundary line to create a processed image, and then detecting the boundary line based on the processed image, The program according to claim 3, further characterized in that it causes the computer to perform a process of creating information about the boundary lines captured in the image.

5. A method for generating a trained model that generates a trained model for determining whether or not a boundary line visible in an image obtained by imaging a processed workpiece is the edge of a processing mark, An image acquisition step involves capturing an image of a sample in which processing marks have been formed, corresponding to the processed workpiece, and obtaining an image of that sample. A detection step to detect boundaries visible in the image obtained in the image acquisition step, An information acquisition step which acquires, among the boundaries detected in the detection step, first boundary information relating to the boundary corresponding to the edge of the processing mark, and second boundary information relating to the boundary not corresponding to the edge of the processing mark, A method for generating a trained model, comprising: a learning step of generating a trained model that, when information about a boundary line appearing in an image obtained by imaging a processed workpiece is input, outputs a determination result indicating whether or not the boundary line is the edge of a processing mark, by machine learning using the first boundary line information and the second boundary line information.

6. The first boundary information acquired in the information acquisition step includes one or more of the following: position information of each point constituting the boundary corresponding to the edge of the processing mark in the image; displacement of each point constituting the boundary in a direction perpendicular to the extension direction of the boundary corresponding to the position of the boundary corresponding to the edge of the processing mark in the image and the boundary corresponding to the edge of the processing mark; evaluation result of the straightness of the boundary corresponding to the edge of the processing mark in the image; and magnitude of the contrast ratio of the two regions on either side of the boundary corresponding to the edge of the processing mark in the image. The method for generating a trained model according to claim 5, characterized in that the second boundary information obtained in the information acquisition step includes one or more of the following: position information of each point constituting the boundary that does not correspond to the edge of the processing mark in the image; displacement of each point constituting the boundary in a direction perpendicular to the extension direction of the boundary that does not correspond to the edge of the processing mark in the image and the position of the boundary that does not correspond to the edge of the processing mark; evaluation result of the straightness of the boundary that does not correspond to the edge of the processing mark in the image; and magnitude of the contrast ratio of the two regions on either side of the boundary that does not correspond to the edge of the processing mark in the image.

7. In the detection step, image processing is performed on the image to enhance the boundary line to create a processed image, and the boundary line is detected based on the processed image. The method for generating a trained model according to claim 5 or 6, characterized in that the processed image is used to acquire the first boundary information and the second boundary information in the information acquisition step.

Images