Information processing method and information processing apparatus

Abstract

The present disclosure provides an information processing method and an information processing apparatus. The information processing method includes the steps of calculating a position of a feature corresponding to a trace in a first coordinate system defined with respect to a field of view of an image; calculating a position of the feature corresponding to the trace in a second coordinate system defined with respect to a position of a workpiece (4) recorded in the image; calculating a size of a first distribution of the position of the feature corresponding to the trace in the first coordinate system and a size of a second distribution of the position of the feature corresponding to the trace in the second coordinate system; and in a case where a difference between the size of the first distribution and the size of the second distribution exceeds a first given value, outputting information indicating that the feature corresponding to the trace means a trace formed on a surface of the workpiece (4) in a machining process, and in a case where the difference is equal to or less than the first given value, outputting information indicating that the feature corresponding to the trace means a false detection of the trace in an inspection process.

Description

Technical Field

[0001] This disclosure relates to an information processing method and an information processing apparatus for detecting traces formed on the surface of a workpiece. Background Technology

[0002] A manufacturing line for producing workpieces includes: a processing step for machining the workpiece; and an inspection step for inspecting the appearance of the workpiece that has been machined in the processing step. Patent Document 1 discloses a technique in which the cause of a mark is determined based on inspection information that detects a mark formed on the surface of the workpiece during the inspection step.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: JP 2004-153228 Summary of the Invention

[0006] One aspect of this disclosure relates to an information processing method for detecting traces formed on the surface of a workpiece during an inspection process included in a manufacturing line for producing workpieces. The inspection process involves photographing the workpiece after it has been processed in a machining process to inspect its appearance. The information processing method includes the following steps: (a) if the image photographed during the inspection process contains features corresponding to the traces, calculating for each workpiece the position of the feature corresponding to the trace in a first coordinate system defined with respect to the field of view of the image; (b) if the image contains features corresponding to the traces, calculating for each workpiece a second coordinate system defined with respect to the position of the workpiece recorded in the image. (c) Calculate the size of a first distribution of the locations ... Attached Figure Description

[0007] Figure 1 This is a diagram illustrating the concept of a manufacturing line involved in the implementation method.

[0008] Figure 2It is a flowchart illustrating the overall process of the manufacturing line involved in the implementation method.

[0009] Figure 3 It is a specific expression Figure 2 The flowchart shows the contents of step S104 (inspection process).

[0010] Figure 4 This is an example of an image of a workpiece captured by a camera during an inspection process.

[0011] Figure 5 It is used for explanation Figure 3 The flowchart shows the steps of S1045.

[0012] Figure 6 It is used for explanation Figure 3 The flowchart shows the steps S1050 and S1051.

[0013] Figure 7 This is an example of a diagram representing location coordinate information stored in a database.

[0014] Explanation of reference numerals in the attached figures

[0015] 2 Manufacturing Line

[0016] 4. Workpiece

[0017] 4a Top surface

[0018] 6. Processing Equipment No. 1

[0019] 8. Second processing equipment

[0020] 10. Third processing equipment

[0021] 12 First Transport Unit

[0022] 14. Processing Unit 1

[0023] 16,30 chuck

[0024] 17. Inspect the equipment.

[0025] 18. Transport equipment

[0026] 20 cameras

[0027] 22. Server for storage

[0028] 24 Databases

[0029] 26. Terminal for parsing

[0030] 28. Display the analysis results on the monitor.

[0031] 32 images

[0032] 34 Features Detailed Implementation

[0033] In the prior art disclosed in Patent Document 1, it is not possible to clearly distinguish between the traces generated in the processing steps and the traces in the inspection steps, resulting in false detection.

[0034] The purpose of this disclosure is to provide an information processing method and an information processing apparatus that can clearly distinguish between traces generated in the processing step and traces in the inspection step to prevent false detection.

[0035] One aspect of this disclosure relates to an information processing method for detecting traces formed on the surface of a workpiece in an inspection process included in a manufacturing line for producing workpieces. This inspection process involves photographing the workpiece after it has been processed in a machining process to inspect its appearance. The information processing method includes the following steps: (a) if the image captured in the inspection process contains features corresponding to the traces, calculating for each workpiece the position of the features corresponding to the traces in a first coordinate system defined with respect to the field of view of the image; (b) if the image contains features corresponding to the traces, calculating for each workpiece a second coordinate system defined with respect to the position of the workpiece recorded in the image. (c) Calculate the size of a first distribution of the locations ...

[0036] This method can clearly distinguish between false detections of traces generated during the processing and those generated during the inspection process. As a result, it can improve the accuracy of visual inspection of workpieces during the inspection process.

[0037] For example, the processing method may be configured such that, in the processing step, a first processing device is used to perform the first processing on the workpiece while gripping it, and the information processing method further includes the following steps: (e) calculating the difference between the position of the feature corresponding to the mark in the second coordinate system and the gripping position of the first processing device on the workpiece in the second coordinate system, i.e., the first difference; in step (d), if the difference between the size of the first distribution and the size of the second distribution exceeds the first given value and the first difference is less than the second given value, outputting information indicating that the cause of the mark is the gripping of the workpiece by the first processing device.

[0038] According to this method, it can be determined that the cause of the mark is the gripping of the workpiece by the first processing equipment.

[0039] For example, the processing method may also be configured such that, in the processing step, a second processing device is used to perform a second processing on the workpiece while gripping it, and the information processing method further includes the following steps: (f) calculating the difference between the position of the feature corresponding to the mark in the second coordinate system and the gripping position of the workpiece by the second processing device in the second coordinate system, i.e., the second difference; in step (d), if the difference between the size of the first distribution and the size of the second distribution exceeds the first given value, and the first difference is smaller than the second difference, and the first difference is less than the second given value, information indicating that the cause of the mark is the gripping of the workpiece by the first processing device is output.

[0040] According to this method, when the cause of a mark is the gripping of a workpiece by any of the multiple processing devices included in the processing step, the processing device that is the cause of the mark can be accurately identified.

[0041] For example, it can also be configured such that, in (c), after calculating the size of the second distribution, the size of the first distribution is calculated using the result of calculating the size of the second distribution.

[0042] According to this method, after calculating the size of the second distribution, the size of the first distribution is calculated using the result of the calculation of the size of the second distribution, thereby making it easy to compare the size of the first distribution with the size of the second distribution.

[0043] One aspect of this disclosure relates to an information processing apparatus for detecting traces formed on the surface of a workpiece in an inspection process included in a manufacturing line for producing workpieces. This inspection process involves photographing the workpiece after it has been processed in a machining process to inspect its appearance. The information processing apparatus includes: a processor; and a memory storing a program executable by the processor. The processor uses the program stored in the memory to execute: if the image captured in the inspection process contains features corresponding to the traces, calculating for each workpiece the position of the feature corresponding to the trace in a first coordinate system defined with respect to the field of view of the image; and if the image contains the position of the feature corresponding to the trace, calculating the position of the feature corresponding to the trace in the first coordinate system defined with respect to the field of view of the image. The position of the workpiece recorded in the image is the position of the feature corresponding to the mark in the second coordinate system defined by the reference. The size of the first distribution of the position of the feature corresponding to the mark in the first coordinate system and the size of the second distribution of the position of the feature corresponding to the mark in the second coordinate system are calculated. If the difference between the size of the first distribution and the size of the second distribution exceeds a given value, information indicating that the feature corresponding to the mark is the mark formed on the surface of the workpiece in the processing step is output. If the difference between the size of the first distribution and the size of the second distribution is less than the given value, information indicating that the feature corresponding to the mark is a false detection of the mark in the inspection step is output.

[0044] This method can clearly distinguish between false detections of traces generated during the processing and those generated during the inspection process. As a result, it can improve the accuracy of visual inspection of workpieces during the inspection process.

[0045] Furthermore, these general or specific methods can be implemented by systems, methods, integrated circuits, computer programs, or recording media such as computer-readable CD-ROMs, or by any combination of systems, methods, integrated circuits, computer programs, or recording media.

[0046] The following description, with reference to the accompanying drawings, details the implementation method.

[0047] Furthermore, the embodiments described below are all general or specific examples. The numerical values, shapes, materials, constituent elements, the arrangement of constituent elements, connection methods, steps, and the order of steps shown in the following embodiments are examples and are not intended to limit this disclosure. In addition, the constituent elements in the following embodiments that are not described in the independent claims representing the highest concept are described as arbitrary constituent elements.

[0048] (Implementation Method)

[0049] [1. Overview of the Manufacturing Line]

[0050] First refer to Figure 1 To illustrate the outline of manufacturing line 2 involved in the implementation method. Figure 1 This is a diagram illustrating the concept of manufacturing line 2 involved in the implementation method.

[0051] like Figure 1 As shown, manufacturing line 2 is a manufacturing line for producing workpiece 4, and includes machining and inspection processes. Workpiece 4 is, for example, a capacitor of approximately cylindrical shape.

[0052] In the machining process, workpiece 4 is machined, for example, in the order of first machining, second machining, and third machining. First machining equipment 6, second machining equipment 8, and third machining equipment 10 are used in the machining process.

[0053] The first processing equipment 6 includes: a first conveying device 12 for conveying a workpiece 4; and a first processing device 14 for performing first processing on the workpiece 4 conveyed by the first conveying device 12. The first conveying device 12 is provided with a plurality of chucks 16 for gripping the workpiece 4.

[0054] Although not shown in the figure, the second processing equipment 8 includes: a second conveying device for conveying the workpiece 4; and a second processing device for performing second processing on the workpiece 4 conveyed by the second conveying device. The second conveying device is equipped with multiple chucks for gripping the workpiece 4. Furthermore, the gripping position of the chucks of the second conveying device on the workpiece 4 differs from the gripping position of the chuck 16 of the first conveying device 12 on the workpiece 4.

[0055] Furthermore, although not shown in the figure, the third processing equipment 10 includes: a third conveying device for conveying the workpiece 4; and a third processing device for performing third processing on the workpiece 4 conveyed by the third conveying device. The third conveying device is equipped with multiple chucks for gripping the workpiece 4. Moreover, the gripping positions of the chucks of the third conveying device on the workpiece 4 are different from the gripping positions of the chuck 16 of the first conveying device 12 and the gripping positions of the chucks of the second conveying device on the workpiece 4.

[0056] In the inspection process, an inspection device 17 is used to inspect the appearance of workpiece 4 by photographing the workpiece 4 that has undergone the first, second, and third processing steps in the manufacturing process. The inspection device 17 includes a transport device 18, a camera 20, a storage server 22, a database 24, a parsing terminal 26 (an example of an information processing device), and a display 28 for displaying the parsing results.

[0057] The conveying device 18 is used to sequentially transport the workpieces 4 to the shooting area directly below the camera 20. The conveying device 18 is equipped with multiple chucks 30 for gripping the workpieces 4.

[0058] A camera 20 is positioned above the conveying device 18 to capture images of the workpiece 4 transported by the conveying device 18. In this embodiment, the camera 20 captures images of the circular top surface 4a of the workpiece 4. The camera 20 outputs image data representing the captured image of the workpiece 4 to a storage server 22.

[0059] Multiple image data from camera 20 are stored in storage server 22.

[0060] The database 24 stores in advance the position coordinate information of each position coordinate of the chuck 16 of the first processing equipment 6, the chuck of the second processing equipment 8, and the chuck of the third processing equipment 10 (that is, the gripping position of each chuck on the workpiece 4).

[0061] The analysis terminal 26 detects traces formed on the surface (top surface 4a) of each workpiece 4 by analyzing multiple image data stored in the storage server 22. Furthermore, in this specification, "trace" refers to scratches, abrasions, or stains formed on the surface of the workpiece 4 when it is gripped by any one of the chucks 16 of the first processing equipment 6, the chuck of the second processing equipment 8, or the chuck of the third processing equipment 10.

[0062] Furthermore, when the analysis terminal 26 detects a mark formed on the surface of the workpiece 4, it uses the reference database 24 to determine the processing equipment that is the cause of the mark from the first processing equipment 6, the second processing equipment 8, and the third processing equipment 10. The analysis terminal 26 outputs information representing the analysis result to the analysis result display 28.

[0063] Furthermore, the parsing terminal 26 may be configured as, for example, a personal computer. The parsing terminal 26 consists of a processor and a memory, and the processor performs various processes by reading and executing software programs stored in the memory.

[0064] Display 28 is a display used to display the parsing results from parsing terminal 26.

[0065] [2. Overall Manufacturing Line Flow]

[0066] Next, refer to Figure 2 This will explain the overall process of manufacturing line 2 involved in the implementation method. Figure 2 This is a flowchart illustrating the overall process of manufacturing line 2 involved in the implementation method.

[0067] like Figure 2 As shown, firstly, the workpiece 4 is processed by the first processing device 6 (S101). Specifically, the workpiece 4, which is gripped by the chuck 16 of the first transport device 12, is processed by the first processing device 14.

[0068] Then, the workpiece 4 is subjected to a second processing (S102) by the second processing device 8. Specifically, the workpiece 4, which is gripped by the chuck of the second transport device, is subjected to a second processing by the second processing device.

[0069] Then, the workpiece 4 is subjected to a third processing (S103) by the third processing device 10. Specifically, the workpiece 4, which is gripped by the chuck of the third transport device, is subjected to a third processing by the third processing device.

[0070] Finally, the workpiece 4 is visually inspected using inspection equipment 17 (S104).

[0071] As described above, the processing steps are performed in steps S101 to S103, and then the inspection step is performed in step S104.

[0072] [3. Inspection process flow]

[0073] Next, refer to Figures 3-7 This section details the inspection process. Figure 3 It is a specific expression Figure 2 The flowchart shows the contents of step S104 (inspection process). Figure 4 This is an example of an image 32 of workpiece 4 taken by camera 20 during the inspection process. Figure 5 It is used for explanation Figure 3 The flowchart shows the steps of S1045. Figure 6 It is used for explanation Figure 3 The flowchart shows the steps S1050 and S1051. Figure 7 This is an example of a diagram representing the location coordinate information stored in database 24.

[0074] like Figure 3 As shown, in the inspection process, firstly, the workpiece 4, which is the object of visual inspection, is photographed by camera 20 (S1041). Figure 4 In the example shown, the top surface 4a of the workpiece 4 is recorded in image 32 captured by camera 20. The top surface 4a of the workpiece 4 contains features 34 that correspond to traces (e.g., black dots). In addition, the so-called feature 34 that corresponds to traces is an image-like feature contained in image 32 that may be a trace formed on the top surface 4a of the workpiece 4.

[0075] The camera 20 outputs image data representing the captured image 32 to the storage server 22. The storage server 22 stores the image data from the camera 20 (S1042). If no given period (e.g., 2 hours) has elapsed since the start of the appearance inspection (or, the previous extraction of multiple image data by the parsing terminal 26) (S1043 "No"), the process returns to step S1041 described above.

[0076] If a given period has elapsed since the start of the visual inspection (or, the previous extraction of multiple image data by the parsing terminal 26) (S1043 "Yes"), the parsing terminal 26 extracts the multiple image data stored in the storage server 22 by accessing the storage server 22 (S1044). The parsing terminal 26 samples the extracted multiple image data (S1045). That is, the parsing terminal 26 samples the extracted multiple image data at given time intervals (e.g., 2-hour intervals).

[0077] Specifically, such as Figure 5 As shown in (a) and (b), the analysis terminal 26 obtains multiple image data containing trace-like features by taking pictures of multiple workpieces 4 (workpieces 4-1 to 4-N) respectively. Figure 5 The coordinate data of points (shown as black triangles in (a) and (b)) are overlapped to sample multiple image data. The sampling result is used to form the distribution of the locations of the trace-like features by overlapping the features contained in each of the multiple image data.

[0078] Therefore, the terminal 26 calculates the position of the feature corresponding to the trace in the relative coordinate system (an example of the second coordinate system). Here, the relative coordinate system refers to the image 32 captured by the camera 20 (reference). Figure 4 The coordinate system is defined with the position of workpiece 4 (i.e., the outline of workpiece 4) recorded in the ) as the reference. The terminal 26 is used to calculate the magnitude (variance) of the distribution of the position of the feature corresponding to the trace in the relative coordinate system, i.e., the relative coordinate system distribution (an example of the second distribution), and the center coordinates of the relative coordinate system distribution (S1046).

[0079] Furthermore, in a relative coordinate system, if the shape of workpiece 4 is a symmetrical shape such as a circle or a square, a vertical coordinate system (described later) can be set to be the same as the absolute coordinate system, with the origin set as the center point of the symmetrical shape. Alternatively, in a polar coordinate system, the radial axis can be defined based on printing information on the surface of workpiece 4.

[0080] Regarding the calculation of the magnitude of the distribution of terminal 26 in analytical processing, a Gaussian Mixture Model (GMM) can be used, for example. A Gaussian Mixture Model approximates a given probability distribution by a linear combination of Gaussian functions. In this Gaussian Mixture Model, considering a two-dimensional scenario, the k-th Gaussian function (a normal distribution) with the mean μx_k of X, the mean μy_k of Y, the variance ∑x_k of X, the variance ∑y_k of Y, and the covariance ∑xy_k of XY is combined with weights πk. The magnitude of each distribution can be simply treated as ∑y_k + ∑x_k.

[0081] Furthermore, regarding the number of local distributions, which is a hyperparameter in the Gaussian mixture model, the Gaussian mixture model can be analyzed while changing the number of local distributions. For example, by using a process that minimizes the number of local distributions using Akaike's Information Criterion (AIC) or Bayesian Information Criterion (BIC), features that are locally concentrated within the image, equivalent to traces, can be automatically analyzed without considering various preconditions.

[0082] Back Figure 3 The flowchart shows that after step S1046, the terminal 26 calculates the position of the feature corresponding to the trace in the absolute coordinate system (an example of the first coordinate system). Here, the so-called absolute coordinate system is based on the image 32 captured by the camera 20 (reference). Figure 4 The coordinate system is defined with the field of view (i.e., the overall outline of image 32) as the reference. The parsing terminal 26 calculates the magnitude (variance) of the distribution of the location of the feature corresponding to the trace in the absolute coordinate system (i.e., an example of the first distribution) and the center coordinates of the absolute coordinate system distribution by using the magnitude of the relative coordinate system distribution and the calculation results of the center coordinates in step S1046 (S1047).

[0083] Specifically, for the coordinate group that is determined to belong to the k-th Gaussian function based on the application of the Gaussian mixture model for relative coordinate systems, the average value μx_k of X, the average value μy_k of Y, the variance ∑x_k of X, the variance ∑y_k of Y, and the covariance ∑xy_k of XY in the absolute coordinates are calculated by simply summing them.

[0084] Furthermore, if Gaussian mixture models are applied individually to different absolute and relative coordinate systems for the local concentration of features equivalent to traces, the calculated distribution information (size and center coordinates) may lack uniformity, making comparison difficult. Therefore, it is preferable to first calculate the distribution information using a Gaussian mixture model for one of the absolute and relative coordinate systems, and then, using this calculated distribution information, calculate the distribution information related to the other of the absolute and relative coordinate systems without applying a Gaussian mixture model.

[0085] Furthermore, in a relative coordinate system, although the transformation error from the absolute coordinate system to the relative coordinate system introduces coordinate deviations, the traces generated under the reference of the workpiece 4 (the object) tend to be concentrated, making the application of a Gaussian mixture model (GMM) relatively easy. On the other hand, in an absolute coordinate system, the transport deviation of workpiece 4 introduces coordinate deviations, making the application of a GMM less convenient. Therefore, in this embodiment, after calculating the distribution information using a GMM for the relative coordinate system, the distribution information for the absolute coordinate system (without a GMM) is calculated based on the distribution information related to the relative coordinate system. This allows for comparison between the distribution information related to the absolute coordinate system and the distribution information related to the relative coordinate system. Alternatively, based on the relative relationship between the transport deviation of workpiece 4 and the transformation deviation from the absolute coordinate system to the relative coordinate system, the distribution information can also be calculated using a GMM for the absolute coordinate system (without a GMM) after calculating the distribution information for the absolute coordinate system, conversely, by using a GMM to calculate the distribution information for the relative coordinate system (without a GMM) based on the distribution information related to the absolute coordinate system.

[0086] like Figure 5 As shown in (c), the distribution of the locations corresponding to the features of the trace (distributions 1-3) is displayed in an elliptical shape. This elliptical shape is a contour line obtained by adding k Gaussian distributions calculated based on a Gaussian mixture model to obtain the mixture Gaussian density, and then connecting the mixture Gaussian densities of a given density. The given density is mostly adopted using equally spaced densities on a logarithmic scale, for example, by using 10 0.333 10 0.663 10 1.000 Connecting the Gaussian mixture densities of a given density makes the Gaussian mixture distribution easily and intuitively understood. The magnitude of the distribution is calculated by taking values ​​of... Figure 5 The standard deviations σx_k and σy_k obtained by taking the positive square roots of the variances ∑x_k and ∑y_k of the k-th Gaussian functions with corresponding elliptical shapes as shown in (c) are used as (σx_k) 2 +σy_k 2 ) 0.5The approximate size of the distribution is determined by a threshold of several hundred μm. Distributions smaller than the threshold are defined as "dense," and those larger than the threshold are defined as "sparse." The size of the distribution in the absolute coordinate system and the size of the distribution in the relative coordinate system are compared, as described later.

[0087] Back Figure 3 The flowchart shows that after step S1047, the parsing terminal 26 determines whether the difference between the magnitude of the absolute coordinate system distribution (absolute coordinate system variance) calculated in step S1047 and the magnitude of the relative coordinate system distribution (relative coordinate system variance) calculated in step S1046 exceeds the first given value (e.g., "0") (S1048).

[0088] If the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution exceeds the first given value (S1048 "Yes"), the analytical terminal 26 further determines whether the size of the relative coordinate system distribution is less than the third given value (e.g., several hundred μm) (S1049). If the size of the relative coordinate system distribution is less than the third given value (S1049 "Yes"), the analytical terminal 26 determines that the feature equivalent to a mark is a mark formed on the top surface 4a of the workpiece 4 during the machining process (S1050).

[0089] Returning to step S1048, if the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution is less than or equal to the first given value (S1048 "No"), the parsing terminal 26 determines that the feature equivalent to the trace is a false detection of the trace in the inspection process (S1051).

[0090] Since the position of the camera 20 in the inspection device 17 is fixed, when the camera 20 takes a picture of the workpiece 4 that exists in the fixed shooting area, the position of the workpiece 4 will deviate within the fixed angle of the camera 20 due to the transport deviation of the workpiece 4.

[0091] Furthermore, when the trace is formed on the top surface 4a of the workpiece 4, the trace is concentrated at a specific location on the top surface 4a of the workpiece 4. On the other hand, when the foreign object is attached to a specific location in the lens of the camera 20, the trace is concentrated at a specific location within a fixed angle of the camera 20.

[0092] That is, such as Figure 6As shown in (a), when the distribution of the positions corresponding to the trace in the absolute coordinate system (reference to camera 20) is "sparse," the probability that a foreign object is attached to a specific location in the lens of camera 20 is low. Conversely, when the distribution of the positions corresponding to the trace in the relative coordinate system (reference to workpiece 4) is "dense," the probability that the trace is formed at a specific location on the top surface 4a of workpiece 4 is high. This is because, assuming that the trace is formed at a specific location on the top surface 4a of workpiece 4, in the event of a transport deviation of workpiece 4, the distribution in the absolute coordinate system becomes "sparse," and the distribution in the relative coordinate system becomes "dense."

[0093] Therefore, when the absolute coordinate system distribution is "sparse" and the relative coordinate system distribution is "dense", in other words, when the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution exceeds the first given value and the size of the relative coordinate system distribution is less than the third given value, the feature that the analytical terminal 26 determines to be equivalent to a trace is a trace formed on the top surface 4a of the workpiece 4 during the processing step.

[0094] On the other hand, such as Figure 6 As shown in (b), when the distribution of the positions corresponding to the trace in the absolute coordinate system (reference to camera 20) is "dense," it is highly likely that the foreign object is attached to a specific location in the lens of camera 20. Conversely, when the distribution of the positions corresponding to the trace in the relative coordinate system (reference to workpiece 4) is "sparse," it is less likely that the trace is formed at a specific location on the top surface 4a of workpiece 4. This is because, assuming that the foreign object is attached to a specific location in the lens of camera 20, in the event of a transport deviation in workpiece 4, the distribution in the absolute coordinate system becomes "dense," and the distribution in the relative coordinate system becomes "sparse."

[0095] Therefore, when the absolute coordinate system distribution is "dense" and the relative coordinate system distribution is "sparse," in other words, when the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution is less than the first given value, the feature that the analytical terminal 26 determines as equivalent to a trace is a false detection of a trace in the inspection process.

[0096] Back Figure 3In the flowchart below, after step S1050, the parsing terminal 26 compares the center coordinates of the relative coordinate system distribution (i.e., the position of the feature corresponding to the mark) with the position coordinates of the chucks 16 of the first processing equipment 6, the chucks of the second processing equipment 8, and the chucks of the third processing equipment 10 in the relative coordinate system (i.e., the gripping position of each chuck on the workpiece 4 in the relative coordinate system) by referring to the position coordinate information stored in the database 24. Specifically, the parsing terminal 26 determines whether the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chucks is less than or equal to a second given value (e.g., 1 mm) (S1052). If the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chucks is less than or equal to the second given value (S1052 "Yes"), the parsing terminal 26 determines the processing equipment that is the cause of the mark formed on the top surface 4a of the workpiece 4 based on the above comparison result (S1053).

[0097] Here, the location coordinate information is, for example, Figure 7 A data table as shown. In Figure 7 In the example shown, the first row of the position coordinate information stores the position coordinates (X, Y) of the chuck 16 of the first machining device 6 in the relative coordinate system as (10, 10). The second row of the position coordinate information stores the position coordinates (X, Y) of the chuck of the second machining device 8 in the relative coordinate system as (100, 100). The third row of the position coordinate information stores the position coordinates (X, Y) of the chuck of the third machining device 10 in the relative coordinate system as (150, 150).

[0098] For example, when the center coordinates of the relative coordinate system distribution are (X, Y) = (10, 10), the analytical terminal 26 calculates the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chuck 16 of the first machining device 6 in the relative coordinate system, which is the first difference (ΔX1, ΔY1). Furthermore, the analytical terminal 26 calculates the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chuck of the second machining device 8 in the relative coordinate system, which is the second difference (ΔX2, ΔY2). Additionally, the analytical terminal 26 calculates the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chuck of the third machining device 10 in the relative coordinate system, which is the third difference (ΔX3, ΔY3).

[0099] The analysis terminal 26 determines the smallest first difference among the calculated first, second, and third differences. For example, in the example above, the first difference is (0, 0). The second difference is (90, 90). The third difference is (140, 140). The first difference is smaller than the second difference. Moreover, the first difference is smaller than the third difference. When the determined first difference (ΔX1 and ΔY1 each) is less than or equal to the second given value, the analysis terminal 26 determines the first processing equipment 6 as the processing equipment that causes the mark, and determines that the cause of the mark is the gripping of the workpiece 4 by the first processing equipment 6.

[0100] Back Figure 3 The flowchart shows that after step S1053, the analysis results from the analysis terminal 26 are displayed on the analysis result display 28 (S1054). Thus, the analysis result display 28 displays information indicating that a mark was formed on the top surface 4a of the workpiece 4 due to the gripping of the chuck 16 of the first processing equipment 6.

[0101] Returning to step S1052, if the difference between the center coordinates of the relative coordinate system distribution and the position coordinates of the chuck exceeds the second given value (S1052 "No"), the analysis terminal 26 determines that the cause of the feature corresponding to the mark is unknown (concentrated on workpiece 4) (S1055). Then, information indicating that the cause of the feature corresponding to the mark is unknown is displayed on the analysis result display 28 as the analysis result from the analysis terminal 26 (S1054).

[0102] Returning to step S1048, if proceeding from step S1048 to step S1051, similarly as described above, the parsing result from the parsing terminal 26 is displayed on the parsing result display display 28 (S1054). Thus, information indicating that a false detection of a trace occurred due to a foreign object attached to the lens of the camera 20 is displayed on the parsing result display display 28.

[0103] Returning to step S1048, if the difference between the magnitude of the absolute coordinate system distribution and the magnitude of the relative coordinate system distribution exceeds a first given value (S1048 "Yes") and the magnitude of the relative coordinate system distribution is greater than a third given value (S1049 "No"), the analysis terminal 26 determines that the cause of the feature corresponding to the mark is unknown (not concentrated on workpiece 4) (S1056). This is because, when the magnitude of the relative coordinate system distribution is greater than a third given value (i.e., the relative coordinate system distribution is "sparse"), there is a possibility that the evaluation in the Gaussian mixture model is inappropriate, and the cause of the feature corresponding to the mark cannot be properly determined. Then, information indicating that the cause of the feature corresponding to the mark is unknown is displayed on the analysis result display 28 as the analysis result from the analysis terminal 26 (S1054).

[0104] [4. Effect]

[0105] As described above, in this embodiment, if the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution exceeds a first given value, the analytical terminal 26 determines that the characteristic equivalent to a mark is a mark formed on the top surface 4a of the workpiece 4 during the machining process. On the other hand, if the difference between the size of the absolute coordinate system distribution and the size of the relative coordinate system distribution is less than or equal to the first given value, the analytical terminal 26 determines that the characteristic equivalent to a mark is a false detection of a mark during the inspection process.

[0106] This allows for a clear distinction between false detections of traces generated during the processing and those generated during the inspection process. Consequently, it improves the accuracy of the visual inspection of workpiece 4 during the inspection process.

[0107] (Other variations)

[0108] The above description illustrates one or more information processing methods and apparatuses based on the aforementioned embodiments, but this disclosure is not limited to the above embodiments. Various modifications conceived by those skilled in the art to the embodiments, and forms constructed by combining constituent elements from different embodiments, can also be included within the scope of one or more embodiments, provided they do not depart from the spirit of this disclosure.

[0109] The above embodiments illustrate the case where workpiece 4 is a capacitor, but it is not limited to this. For example, it can also be various electronic components such as resistors or inductors, or metal products such as automotive parts.

[0110] Furthermore, in the above embodiments, each component can be constructed by dedicated hardware, or it can be implemented by executing software programs suitable for each component. Each component can also be implemented by a program execution unit such as a CPU or processor reading and executing software programs recorded on a recording medium such as a hard disk or semiconductor memory.

[0111] Alternatively, some or all of the functions of the information processing device described in the above embodiments can be implemented by a processor such as a CPU executing a program.

[0112] Some or all of the constituent elements of the above-described devices can be composed of IC cards or individual modules that can be detached and installed in each device. The IC card or module is a computer system composed of a microprocessor, ROM, RAM, etc. The IC card or module may contain the aforementioned multi-functional LSI.

[0113] The IC card or module achieves this function by operating under a computer program via a microprocessor. The IC card or module may also be tamper-proof.

[0114] This disclosure can be implemented as the method described above. Alternatively, these methods can be implemented as a computer program implemented by a computer, or as a digital signal composed of the computer program. Furthermore, this disclosure can be implemented by recording the computer program or the digital signal on a computer-readable recording medium such as a floppy disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray Disc), semiconductor memory, etc. Alternatively, it can be implemented as the digital signal recorded on these recording media. Furthermore, this disclosure can be implemented by transmitting the computer program or the digital signal via electrical communication lines, wireless or wired communication lines, networks such as the Internet, data broadcasting, etc. Additionally, this disclosure can be a computer system equipped with a microprocessor and a memory, the memory storing the aforementioned computer program, and the microprocessor operating according to the computer program. Alternatively, it can be implemented by a separate computer system by recording the program or the digital signal on the recording medium and transferring it, or by transferring the program or the digital signal via the network, etc.

[0115] Industrial availability

[0116] The information processing method disclosed herein can be applied, for example, to an inspection process in which the appearance of a workpiece is inspected by photographing the workpiece.

Claims

1. An information processing method for detecting traces formed on the surface of a workpiece during an inspection process included in a manufacturing line for producing a workpiece, wherein, The inspection process involves photographing the workpiece after it has undergone processing to inspect its appearance. The information processing method includes the following steps: (a) If the image captured during the inspection process contains a feature equivalent to the mark, calculate the position of the feature equivalent to the mark in a first coordinate system defined with the field of view of the image for each workpiece; (b) If the image contains a feature corresponding to the trace, calculate the position of the feature corresponding to the trace in a second coordinate system defined with reference to the position of the workpiece recorded in the image for each workpiece; (c) Calculate the magnitude of the first distribution of the positions corresponding to the features of the trace in the first coordinate system, and the magnitude of the second distribution of the positions corresponding to the features of the trace in the second coordinate system; and (d) If the difference between the size of the first distribution and the size of the second distribution exceeds a first given value, output information indicating that the feature of the trace is the trace formed on the surface of the workpiece during the processing step; if the difference between the size of the first distribution and the size of the second distribution is less than the first given value, output information indicating that the feature of the trace is the trace falsely detected during the inspection step.

2. The information processing method according to claim 1, wherein, In the aforementioned processing step, a first processing device is used to perform the first processing on the workpiece while it is gripping the workpiece. The information processing method further includes the following steps: (e) Calculate the difference between the position of the feature corresponding to the mark in the second coordinate system and the gripping position of the first processing device on the workpiece in the second coordinate system, i.e., the first difference. In step (d), if the difference between the size of the first distribution and the size of the second distribution exceeds the first given value and the first difference is less than the second given value, information indicating that the cause of the mark is the gripping of the workpiece by the first processing equipment is output.

3. The information processing method according to claim 2, wherein, In the aforementioned processing step, a second processing device is also used to perform a second processing on the workpiece while it is being gripped. The information processing method further includes the following steps: (f) Calculate the difference between the position of the feature corresponding to the mark in the second coordinate system and the gripping position of the second processing equipment on the workpiece in the second coordinate system, i.e., the second difference. In step (d), if the difference between the size of the first distribution and the size of the second distribution exceeds the first given value, and the first difference is smaller than the second difference, and the first difference is less than the second given value, information indicating that the cause of the mark is the gripping of the workpiece by the first processing equipment is output.

4. The information processing method according to any one of claims 1 to 3, wherein, In step (c), after calculating the size of the second distribution, the size of the first distribution is calculated using the result of calculating the size of the second distribution.

5. An information processing apparatus for detecting traces formed on the surface of a workpiece during an inspection process included in a manufacturing line for producing a workpiece, wherein, The inspection process involves photographing the workpiece after it has undergone the processing steps to inspect its appearance. The information processing device includes: processor; and A memory that stores programs that can be executed by the processor. The processor uses the program stored in the memory to execute: If the image captured during the inspection process contains a feature corresponding to the mark, the position of the feature corresponding to the mark in a first coordinate system defined with the field of view of the image is calculated for each workpiece. If the image contains a location corresponding to the mark, calculate the location of the feature corresponding to the mark in a second coordinate system defined with the position of the workpiece recorded in the image as a reference. Calculate the magnitude of the first distribution of the positions corresponding to the features of the trace in the first coordinate system, and the magnitude of the second distribution of the positions corresponding to the features of the trace in the second coordinate system. If the difference between the size of the first distribution and the size of the second distribution exceeds a given value, output information indicating that the feature corresponding to the mark is the mark formed on the surface of the workpiece during the processing step. If the difference between the size of the first distribution and the size of the second distribution is below the given value, information is output indicating that the characteristic of the trace is a false detection of the trace in the inspection process.

Images