Information processing apparatus, information processing method, and program

Abstract

To inspect a plurality of objects in a short processing time while suppressing variations in inspection accuracy for the plurality of objects.SOLUTION: The information processing apparatus specifies a condition under which the relative positional relationship among the object, the imaging unit, and the light source matches among the plurality of objects, and inspects each of the plurality of objects based on an image obtained by imaging the plurality of objects under the specified condition.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to techniques for inspecting objects. [Background technology]

[0002] Conventionally, there is a method for visually inspecting a product by using an image captured by imaging using multiple lighting fixtures to detect defects such as scratches on the product surface. Patent Document 1 discloses a technology for capturing and measuring multiple objects at once. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-200582 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, in order to make the inspection accuracy for a plurality of objects uniform, it is necessary to identify the orientation of each object by pattern matching, which poses a problem of taking a long processing time.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to inspect a plurality of objects in a short processing time while suppressing variations in inspection accuracy for the plurality of objects. [Means for solving the problem]

[0006] In order to solve the above problem, the information processing device according to the present invention is characterized by having an identification means for identifying conditions under which the relative positional relationships between the objects, the imaging means, and the light source coincide among a plurality of objects, and an inspection means for inspecting each of the plurality of objects based on images obtained by imaging the plurality of objects under the conditions. [Effects of the Invention]

[0007] According to the present invention, it is possible to inspect a plurality of objects in a short processing time while suppressing variations in inspection accuracy for the plurality of objects. [Brief explanation of the drawings]

[0008] [Figure 1] Block diagram showing the functional configuration of an information processing device [Figure 2] 1 is a flowchart showing a process executed by an information processing device; [Figure 3] FIG. 1 is a diagram showing an example of the arrangement of an imaging device, a light source, and an object. [Figure 4] 1 is a diagram showing an example of the relative position of a light source with respect to an object; [Figure 5] A diagram showing an example of a user interface [Figure 6] Block diagram showing the functional configuration of an information processing device [Figure 7] 1 is a flowchart showing a process executed by an information processing device; [Figure 8] Block diagram showing the hardware configuration of an information processing device [Figure 9] FIG. 1 is a diagram showing an example of the arrangement of an imaging device, a light source, and an object. [Figure 10] A diagram showing an example of how to select a light source [Figure 11] FIG. 1 is a diagram showing an example of the arrangement of an imaging device, a light source, and an object. [Figure 12] 1 is a flowchart showing a process executed by an information processing device; [Figure 13] FIG. 1 is a diagram showing an example of the arrangement of an imaging device, a light source, and an object. [Figure 14] A diagram showing examples of conditions for identifying the placement of objects. [Figure 15] Block diagram showing the functional configuration of an information processing device DETAILED DESCRIPTION OF THE INVENTION

[0009] Each embodiment will be described below with reference to the drawings. Note that the following embodiments do not necessarily limit the present invention. Furthermore, not all of the combinations of features described in each embodiment are necessarily essential to the solution of the present invention.

[0010] [First embodiment] In this embodiment, a method for specifying the position of a light source to be used for inspection for each object to be inspected will be described.

[0011] <Hardware configuration of information processing device> FIG. 8 is a diagram illustrating an example of the hardware configuration of the information processing device 1. The information processing device 1 includes a CPU 801, a ROM 802, and a RAM 803. The information processing device 1 also includes a VC (video card) 804, a general-purpose I / F (interface) 805, a SATA (serial ATA) I / F 806, and a NIC (network interface card) 807. The CPU 801 uses the RAM 803 as a work memory to execute an OS (operating system) and various programs stored in the ROM 802, a HDD (hard disk drive) 813, etc. The CPU 801 also controls each component via a system bus 808. Note that, in the processing according to the flowcharts described below, program codes stored in the ROM 802, the HDD 813, etc. are loaded into the RAM 803 and executed by the CPU 801. A display device 815 is connected to the VC 804. An input device 810 such as a mouse or keyboard, an imaging device 811 such as a digital camera, and an illumination device 816 having multiple light sources are connected to the general-purpose I / F 805 via a serial bus 809. An HDD 813 is connected to the SATA I / F 806 via a serial bus 812. The NIC 807 inputs and outputs information to and from external devices. The CPU 801 uses the HDD 813 as a storage location for various data. The CPU 801 displays a UI (user interface) provided by a program on the display device 815 and receives inputs such as user instructions accepted via the input device 810. The display device 815 may be a touch panel display having a touch panel function that detects the position of a touch made by a pointer such as a finger.

[0012] <Functional configuration of information processing device> Fig. 1 is a block diagram showing the functional configuration of the information processing device 1. The CPU 801 uses the RAM 803 as a work memory and reads and executes a program stored in the ROM 802 or the HDD 813, thereby functioning as the functional configuration shown in Fig. 1. It should be noted that not all of the processes described below need to be executed by the CPU 801, and the information processing device 1 may be configured so that part or all of the processes are executed by one or more processing circuits other than the CPU 801.

[0013] The information processing device 1 includes an acquisition unit 101, an imaging control unit 102, an identification unit 103, and an inspection unit 104. The acquisition unit 101 acquires information indicating imaging conditions for capturing images of objects to be inspected. The information indicating the imaging conditions in this embodiment includes imaging device information indicating the number and positions of imaging devices 811, lighting device information indicating the number and positions of light sources included in lighting devices 816, and object information indicating the number, sizes, and positions of objects to be inspected. The imaging control unit 102 controls the imaging devices 811 and the lighting devices 816 to capture images of the objects to be inspected under the imaging conditions indicated by the information acquired by the acquisition unit 101. The identification unit 103 identifies images to be used for inspecting each of the objects to be inspected from among multiple images obtained under the control of the imaging control unit 102. The inspection unit 104 inspects each of the objects to be inspected based on the images identified by the identification unit 103.

[0014] <Processing performed by the information processing device> The flow of processing executed by the information processing device 1 in this embodiment will be described using the flowchart in Fig. 2. The processing shown in the flowchart in Fig. 2 starts when a user inputs an instruction via the input device 810 and the CPU 801 accepts the input instruction. Hereinafter, each step (process) will be represented by adding an S before the reference number.

[0015] In S201, the acquiring unit 101 acquires imaging device information indicating the number and positions of imaging devices 811. In this embodiment, the acquiring unit 101 acquires the imaging device information based on a value input by a user via a UI displayed on the display device 815. Note that the method of acquiring the imaging device information is not limited to the above example, and a preset value may be acquired from a storage device such as the HDD 813. Furthermore, image recognition processing may be performed to identify the number and positions of imaging devices 811 based on an image obtained by capturing an image of the imaging device 811 with another imaging device. In this embodiment, imaging is performed in the arrangement of the imaging device 811, the light source of the lighting device 816, and the object to be inspected, as shown in FIG. 3. FIG. 3(a) is a diagram illustrating the arrangement of the imaging device 811, the light source, and the object as viewed from the side, and FIG. 3(b) is a diagram illustrating the arrangement of the imaging device 811, the light source, and the object as viewed from directly above. In the example of FIG. 3, the number of imaging device 811 is "1." The coordinate position of the imaging device 811 in a predetermined coordinate system is input. For example, since the image capture device 811 and the light source are arranged so that they are at the same height from the surface on which the object is placed, position information in the height (z) direction is not necessary. Therefore, the acquisition unit 101 in this embodiment acquires coordinate positions in the x and y directions when viewed from a direction perpendicular to the surface on which the object is placed. In FIG. 3(c), if the upper left coordinate is (0,0), the position of the image capture device 811 is (6,5).

[0016] In S202, the acquisition unit 101 acquires lighting device information indicating the number and positions of light sources included in the lighting device 816. Like the imaging device information, the lighting device information is acquired based on values ​​input by the user via a UI displayed on the display device 815. Alternatively, a preset value may be acquired from a storage device such as the HDD 813. Alternatively, image recognition processing may be performed to identify the number and positions of light sources based on an image obtained by capturing an image of the light sources. In the example of FIG. 3, the number of light sources is "16." The positions of the light sources are input as coordinate positions in the same coordinate system as the imaging device 811. In FIG. 3(c), the position of the light source in the upper left is (3,2), and the position of the light source in the lower right is (9,8).

[0017] In S203, the acquisition unit 101 acquires object information indicating the number, size, and position of the objects to be inspected. Like the imaging device information, the object information is acquired based on values ​​input by the user via a UI displayed on the display device 815. Alternatively, a preset value may be acquired from a storage device such as the HDD 813. Alternatively, image recognition processing may be performed to identify the number and position of objects based on images obtained by capturing images of the objects. In the example of FIG. 3, the number of objects is "2." For example, assuming that the interval between the dashed grid lines in FIG. 3(c) is 10 cm, the object size is approximately 20 cm in width W and approximately 20 cm in height H. The size input value is a value based on a preset unit. Specifically, if the unit is cm, W=20 and H=20 are input, and if the unit is 10 cm, W=2 and H=2 are input. The object position information may be the center position of the object or the upper left position of the object, as long as it is consistent for all objects to be inspected. In this embodiment, the center position of the object is acquired as the position information. In Fig. 3(c), the position of object A is (5,4), and the position of object B is (7,4). In this embodiment, all of the objects to be inspected are entirely included in the angle of view of the imaging device 811. Furthermore, the imaging devices 811 are all arranged so that their relative positions with respect to each object are the same.

[0018] In S204, the imaging control unit 102 controls the imaging device 811 and the lighting device 816 to capture an image of the object to be inspected under the imaging conditions indicated by the information acquired by the acquisition unit 101. The imaging control unit 102 causes the imaging device 811 to capture an image in synchronization with the timing at which each light source is turned on. This imaging process makes it possible to acquire images of an object illuminated with light from multiple angles. In this embodiment, imaging is performed by turning on all of the light sources one by one. In the example of FIG. 3, imaging is performed 16 times, and 16 captured images corresponding to different lighting conditions are obtained.

[0019] In S205, the identification unit 103 identifies the light source to be used for each object based on the information indicating the imaging conditions. First, the identification unit 103 acquires positional relationship information indicating the relative positional relationship between the object and each light source. The positional relationship information can be acquired by calculating the position coordinates of each light source when the position of the object is set to (0,0). The relative positions of the light sources with respect to each object in the example of FIG. 3 are shown in FIG. 4. FIG. 4(a) shows the relative position of the light source with respect to object A, and FIG. 4(b) shows the relative position of the light source with respect to object B. The coordinate values ​​written above each light source indicate the relative position with respect to the object. The relative position can be calculated by subtracting the coordinate values ​​of the object from the coordinate values ​​of each light source acquired by the acquisition unit 101. Specifically, the light source L located at the top left with respect to object A is calculated as follows: A The relative position of the light source L A coordinate value (L A x,L A y) = (3,2), the coordinate value of object A (W A x,W A y) = (5,4) can be calculated by subtracting the light source L for object A. A The relative position of is (-2,-2).

[0020] After calculating the relative positions of all light sources with respect to each object, the identification unit 103 selects a combination of light sources whose relative positions with respect to object A and object B match. In the example of FIG. 4, there are 12 combinations of light sources whose relative positions with respect to object A and object B match. There are no other relative positions whose coordinates match the relative positions (4,-2), (4,0), (4,2), and (4,4) with respect to object A and the relative positions (-4,-2), (-4,0), (-4,2), and (-4,4) with respect to object B. However, since (4,-2) and (-4,-2), (4,0) and (-4,0), (4,2) and (-4,2), and (4,4) and (-4,4) each show the same positional relationship with respect to the object, these combinations can also be considered as combinations of light sources whose relative positions match. 4, by using all the light sources for each object, captured images corresponding to 16 types of illumination conditions can be obtained for each of object A and object B. Therefore, the identification unit 103 identifies all 16 light sources as the light sources to be used for object A and object B, and selects 16 images as test images.

[0021] If inspection time is limited and many captured images cannot be used, the number of light sources to be used may be limited. In this case, a light source that can accurately perform inspection can be selected for each object. For example, when generating surface shape data using photometric stereo for inspection, captured images corresponding to light illumination from at least three directions are required. Therefore, three or more light sources that can illuminate the entire object should be selected. In the example of Figure 4, inspection can be performed by using four light sources (top, bottom, left, and right) for the object. Inspection can also be performed by using four light sources (top left, top right, bottom left, and bottom right) for the object. As another example, when detecting defects such as scratches based on the distribution of shading in captured images, multiple light sources are not necessarily required, so one light source whose relative position with respect to the object is (0,0) can be selected.

[0022] In this embodiment, since there is one imaging device 811, there is no need to consider the relative position between the imaging device 811 and the light source. If there are multiple imaging devices 811, the identification unit 103 also calculates the relative positional relationship between the imaging device 811 and each object, and identifies a combination of light sources that results in the same relative position with respect to the imaging device 811 and the object. The calculation method for the relative positional relationship can be the same as the method described above.

[0023] In S206, the inspection unit 104 inspects each object to be inspected based on the selected inspection image. In this embodiment, the inspection unit 104 performs inspection processing by generating shape images representing the surface shape and color images representing the color using photometric stereo. The inspection processing is performed by performing spatial filtering on the images and integrating the response values ​​to calculate the value obtained as the degree of abnormality.

[0024] As described above, the information processing device 1 identifies, based on information indicating the imaging conditions, inspection images for multiple inspection target objects in which the relative positional relationships between the objects, the imaging device 811, and the light source of the illumination device 816 match, and performs inspection processing based on the identified inspection images. This makes it possible to inspect multiple objects in a short processing time while suppressing variations in inspection accuracy for multiple objects.

[0025] <Modification> Although the information processing device 1 in this embodiment has the inspection unit 104 that performs inspection processing based on the inspection image selected by the identification unit 103, the inspection processing may be performed by another device. For example, instead of the inspection unit 104, the information processing device 1 may have an output unit that outputs the inspection image selected by the identification unit 103 to an external device, and the external device that receives the inspection image may perform the inspection processing.

[0026] Furthermore, identification information of the light source identified by the identification unit 103 may be presented to the user via the UI, allowing the user to instruct whether or not to perform inspection using an image corresponding to the identified light source. For example, if the identification unit 103 selects light sources whose relative positions with respect to each object are (0,-2), (-2,0), (2,0), and (0,2), a light source layout diagram and the ID of the selected light source are displayed as shown in FIG. 5. FIG. 5 is a diagram showing an example of the display of the light source to be used for object A. If the user checks the display and determines that the presented light source is acceptable for inspection, the user presses an OK button 501. When the OK button 501 is pressed, the inspection unit 104 performs inspection processing based on the selected inspection image. If the user determines that the light source to be used needs to be changed, the user presses a Change button 502. When the Change button 502 is pressed, the system transitions to a manual change mode, in which the user adds, removes, or changes the position of the light source to be used on the UI. When the user makes a change to one object, the identification unit 103 identifies the light source again so that the relative positional relationships of the other objects are unified, and updates the display based on the result of re-identification of the light source. When presenting the result of re-identification, the display may be updated automatically when the identification process is completed, or when the display update button 503 on the UI is pressed.

[0027] In addition, although the relative position is roughly determined using two-dimensional coordinates in this embodiment, the relative position may be determined by other methods. For example, the distance from the object to the light source may be measured using a distance measuring sensor or the like, and the light source to be used may be determined based on the measured distance.

[0028] In addition, in this embodiment, the positional relationship between the imaging device 811, the light source, and the object is unified, but since it is sufficient that the inspection accuracy for each object is similar, an allowable error range may be set depending on the inspection method.

[0029] In this embodiment, the heights of the image capturing device 811 and the light source are the same, but if the heights are different, the acquiring unit 101 also acquires position information in the height (z) direction. In this embodiment, the attitudes (directions) of the image capturing device 811 and the light source are the same, but if the attitudes are different, the acquiring unit 101 also acquires attitude information.

[0030] [Second embodiment] In the first embodiment, from images obtained by imaging with all light sources turned on, an inspection image was selected in which the relative position of the imaging device 811 to the object and the relative position of the light source of the lighting device 816 were the same for multiple inspection target objects. In this embodiment, the lighting pattern of the light source is changed depending on the number and size of the inspection target objects. Note that the hardware configuration of the information processing device 1 in this embodiment is the same as that in the first embodiment, so a description thereof will be omitted. The following mainly describes the differences between this embodiment and the first embodiment. Note that the same components as in the first embodiment will be described using the same reference numerals.

[0031] <Functional configuration of information processing device> Fig. 6 is a block diagram showing the functional configuration of the information processing device 1. The CPU 801 uses the RAM 803 as a work memory and reads and executes a program stored in the ROM 802 or the HDD 813, thereby functioning as the functional configuration shown in Fig. 6. Note that it is not necessary for all of the processes shown below to be executed by the CPU 801, and the information processing device 1 may be configured so that part or all of the processes are executed by one or more processing circuits other than the CPU 801.

[0032] The information processing device 1 has an acquisition unit 101, an identification unit 601, an imaging control unit 602, and an inspection unit 104. The identification unit 602 identifies a light source to be turned on based on information indicating imaging conditions acquired by the acquisition unit 101. The imaging control unit 602 turns on the light source identified by the identification unit 601 and captures an image of an object.

[0033] <Processing performed by the information processing device> The flow of processing executed by the information processing device 1 in this embodiment will be described with reference to the flowchart in Fig. 7. The processing shown in the flowchart in Fig. 7 starts when a user inputs an instruction via the input device 810 and the CPU 801 accepts the input instruction. Note that the processing of S201 to S203 and S206 is the same as the processing in the first embodiment, and therefore description thereof will be omitted.

[0034] In S701, the identification unit 601 identifies the light source to be used for each object based on information indicating the imaging conditions. A method for identifying the light source to be turned on will be described for the example arrangement of the imaging device 811, light sources, and objects shown in FIG. 9. In the example of FIG. 9, there is one imaging device 811, which is arranged in the center. 36 light sources are arranged at equal intervals in a ring shape surrounding the imaging device 811. FIG. 9(a) shows an example where four objects are arranged, and FIG. 9(b) shows an example where six objects are arranged. FIG. 10 shows an example of the procedure for identifying the light source for the object 901 in the upper left corner of the example of FIG. 9(a). If it is desired to irradiate the object with light from at least four directions, the light sources are classified into four groups as indicated by the dashed lines in FIG. 10(a). In this embodiment, it is desired to turn on at least one light source on each of the top, bottom, left, and right sides of the object, so the grouping is performed using the diagonal of the object. If the groups are grouped into groups 1 to 4, the identification unit 601 selects one light source for each group. Furthermore, by selecting light sources such that the lines connecting the light sources selected in adjacent groups do not pass through the object, it is possible to inspect the entire object. For example, when selecting one light source each in group 1 and group 4, if light sources are selected that are symmetrically positioned between the groups and the lines connecting the light sources do not pass through the object, the light sources shown by the white circles in Figure 10(b) are selected. If these two point selections are performed in the same way for the other three objects, eight light sources shown by the white circles in Figure 10(c) are selected.

[0035] Next, the identification unit 601 determines whether it is possible to select four of the eight selected light sources so that a line connecting two of the light sources does not pass through the object. As in the example of FIG. 10(c), if it is possible to select light sources from group 2 and group 3 so that a line connecting two light sources between adjacent groups does not pass through the object, the eight selected light sources are determined to be the light sources to be turned on. If it is not possible to select a light source that satisfies the above conditions from the eight selected light sources, a light source that satisfies the above conditions is added for all objects. As shown in FIG. 10(d), by selecting light sources using the above method, the relative positions of the light sources with respect to each object can be unified. Using a similar method, six light sources indicated by white circles are selected for the object shown in FIG. 9(b). Note that the method of identifying light sources is not limited to the above example; other methods may be used as long as they can identify light sources corresponding to the light irradiation direction required for inspection. Furthermore, since the number of light sources to be turned on and the direction and angle of light irradiation vary depending on the inspection method, the lighting pattern may be changed depending on the inspection method.

[0036] In S702, the imaging control unit 602 turns on the light source identified by the identification unit 601 and captures an image. Information about the light source identified by the identification unit 601 is transmitted as a signal to the imaging control unit 602, and the imaging control unit 602 controls the lighting device 816 to turn on the identified light source. Note that information about the light source identified by the identification unit 601 may be displayed on a UI, and the user may check the UI and input signals to the imaging device 811 and the lighting device 816 to capture an image. For example, in the example of FIG. 9( a), eight light sources are turned on, and the imaging device 811 captures images eight times in synchronization with the lighting of the light sources, thereby generating eight inspection images. In the example of FIG. 9( b), six light sources are turned on, and the imaging device 811 captures images six times in synchronization with the lighting of the light sources, thereby generating six inspection images.

[0037] As described above, the information processing device 1 identifies, based on information indicating the imaging conditions, a light source for each of a plurality of inspection target objects that matches the relative positional relationship between the object, the imaging device 811, and the light source of the lighting device 816, and then turns on the identified light source to perform imaging. This makes it possible to inspect a plurality of objects in a short processing time while suppressing variations in inspection accuracy for the plurality of objects.

[0038] <Modification> In the present embodiment, an example in which the light source pattern to be lit is changed when there is one imaging device 811 has been described. However, when there are multiple imaging devices 811, the imaging device to be used may be changed. For example, in the example of FIG. 11 , four imaging devices 811 and 25 light sources are arranged at equal intervals. Assume that light needs to be irradiated onto an object from at least four directions for inspection. In the example of FIG. 11( a), there are nine objects. If the positional relationship between the imaging devices 811 and the light sources for each object is to be unified, all four imaging devices 811 are used, but the light sources indicated by the black circles in FIG. 11( b) are not used. In the example of FIG. 11( c), there are six objects. If the positional relationship between the imaging devices 811 and the light sources for each object is to be unified, only the two imaging devices 811 on the left are used, as shown in FIG. 11( d), and the light sources indicated by the black circles are unnecessary, so the 20 light sources on the left are used.

[0039] [Third embodiment] In the second embodiment, a light source that makes the relative position of the imaging device 811 and the relative position of the light source of the lighting device 816 to the object the same is identified for a number of inspection target objects, and the identified light source is turned on to capture an image. In this embodiment, the object is positioned according to the position of the imaging device 811 and the light source. Since the hardware configuration of the information processing device 1 in this embodiment is the same as that in the first embodiment, a description thereof will be omitted. Below, differences between this embodiment and the first embodiment will be mainly described. Note that the same components as in the first embodiment will be described using the same reference numerals.

[0040] <Functional configuration of information processing device> Fig. 15 is a block diagram showing the functional configuration of the information processing device 1. The CPU 801 uses the RAM 803 as a work memory and reads and executes a program stored in the ROM 802 or the HDD 813, thereby functioning as the functional configuration shown in Fig. 15. Note that it is not necessary for all of the processes shown below to be executed by the CPU 801, and the information processing device 1 may be configured so that part or all of the processes are executed by one or more processing circuits other than the CPU 801.

[0041] The information processing device 1 has an acquisition unit 101, an identification unit 1501, an arrangement control unit 1502, an imaging control unit 1503, and an inspection unit 104. The identification unit 1501 identifies the arrangement of an object based on information indicating imaging conditions acquired by the acquisition unit 101. The arrangement control unit 1502 controls an arrangement device (not shown) to arrange the object. The imaging control unit 1503 images the arranged object.

[0042] <Processing performed by the information processing device> The flow of processing executed by the information processing device 1 in this embodiment will be described with reference to the flowchart in Fig. 12. The processing shown in the flowchart in Fig. 12 starts when a user inputs an instruction via the input device 810 and the CPU 801 accepts the input instruction. Note that the processing of S201 to S203 and S206 is the same as the processing in the first embodiment, and therefore description thereof will be omitted.

[0043] In S1201, the identification unit 1501 identifies the location of each object based on the number and positions of the image capture device 811 and light sources. In this embodiment, there is one image capture device 811, which is located at the center of the multiple light sources. The multiple light sources are aligned at equal intervals horizontally with respect to the surface on which the objects are placed. The identification unit 1501 first calculates the maximum number of objects that can be placed based on the placement conditions of the image capture device 811 and light sources and the shape and size of the objects. For example, as shown in FIG. 13(a), if the angle of view of the image capture device 811 is within the range indicated by the dashed rectangle, a maximum of four objects can be placed as long as the diameter of the object or the length of the long side of the rectangle is equal to or less than the spacing between the light sources. In this case, the positional relationship between the image capture device 811 and each object must be consistent. As long as the positional relationship between the image capture device 811 and the light sources is consistent for each object, even two or three objects can be placed in the example of FIG. 13(a). As another example, as shown in FIG. 13(b), when the long side of the object's rectangle is longer than the distance between the light sources, up to two objects can be placed.

[0044] Next, the identification unit 1501 identifies the location of the object according to the inspection method and the shape of the object. The method for identifying the location of the object will be described using the example of FIG. 13(a). The identification unit 1501 identifies the placement conditions using the table in FIG. 14. The inspection method (C01) is photometric stereo ((1)) and a method using luminance values ​​((3)). The object shape (C02) is a square ((2)). The object surface shape (C03) is a high enclosure ((2)). The minimum light irradiation direction is 4 ((1)). The light irradiation angle (C05) is directly above ((1)) and small ((2)). The identification unit 1501 identifies a combination of coordinates in which the objects can be placed using the position information of the image capture device 811 so that each object is located at the same distance from the image capture device 811. Next, the identification unit 1501 limits the combination of object coordinate values ​​to result in a placement that satisfies the above placement conditions. In the example of FIG. 13(a), inspection is performed using photometric stereo and a method using luminance values, so light irradiation from directly above and from four directions is required. Based on the conditions of this inspection method, the identification unit 1501 identifies the placement of the object in FIG. 13(a) as appropriate. Note that, although an appropriate object position is identified in this embodiment, for example, if the surface of the object is embossed with text, the orientation of the object relative to the imaging device 811 may also be consistent. As shown in the table of FIG. 14, there are multiple conditions for identifying the placement of an object. Therefore, if all conditions cannot be satisfied, the placement may be identified by prioritizing the conditions. For example, the placement may be as shown in FIG. 13(c) or 13(d).

[0045] In S1202, the placement control unit 1502 places each object on the placement surface. In placing objects in this embodiment, the placement control unit 1502 transmits object placement information as a signal to a placement device such as a robot arm, and the placement device places the object based on the signal. Note that the information processing device 1 may have a display control unit instead of the placement control unit 1502, and the display control unit may display object placement information on the display device 815, so that the user can place the object by checking the placement information. Alternatively, a projector may display the position at which the object is to be placed, and the placement device may recognize the position and perform placement. Alternatively, a printer may print the object placement on a printing medium, and the user may place the object by placing the printed material indicating the object placement on an inspection table or the like. In S1203, the imaging control unit 1503 controls the imaging device 811 to capture an image of the placed object.

[0046] As described above, based on information indicating the imaging conditions, information processing device 1 identifies the position of an object among multiple inspection target objects where the relative positional relationship between the object, the imaging device 811, and the light source of lighting device 816 matches, and places the object at the identified position to perform imaging. This makes it possible to inspect multiple objects in a short processing time while suppressing variations in inspection accuracy for multiple objects.

[0047] [Other embodiments] The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions. [Explanation of symbols]

[0048] 1. Information processing equipment 103 Specific part 104 Inspection Department 601 Specific part 1501 Specific section

Claims

1. a specifying means for specifying a condition under which the relative positional relationship between the object, the image capturing means, and the light source coincides among a plurality of objects; an inspection means for inspecting each of the plurality of objects based on images obtained by capturing images of the plurality of objects under the conditions; An information processing device comprising:

2. 2. The information processing apparatus according to claim 1, wherein the specifying unit specifies a light source arrangement that matches the relative positional relationship between the object, the image capturing unit, and the light source among a plurality of objects.

3. the specifying means selects an image from images obtained by capturing images of the plurality of objects based on the specified arrangement of the light sources; 3. The information processing apparatus according to claim 2, wherein the inspection means performs the inspection based on the selected image.

4. 3. The information processing device according to claim 2, further comprising a control means for controlling the light sources to turn on the light sources in the specified arrangement, and for controlling the imaging means to capture images of the plurality of objects illuminated by the light from the turned-on light sources.

5. 2. The information processing apparatus according to claim 1, wherein the specifying means specifies an arrangement of an object in which the relative positional relationship between the object, the image capturing means, and the light source coincides among a plurality of objects.

6. 6. The information processing apparatus according to claim 5, further comprising a control unit that controls the placement unit to place the plurality of objects in the specified placement, and that controls the imaging unit to image the plurality of placed objects.

7. 6. The information processing apparatus according to claim 5, further comprising control means for controlling display means to display the specified layout.

8. 2. The information processing apparatus according to claim 1, wherein the specifying means specifies the condition based on information indicating the number and positions of the image capturing means.

9. 2. The information processing apparatus according to claim 1, wherein the specifying unit specifies the condition based on information indicating the number and positions of the light sources.

10. 2. The information processing apparatus according to claim 1, wherein the condition is specified based on information indicating the number, size, and position of the plurality of objects.

11. 2. The information processing apparatus according to claim 1, wherein said inspection means inspects the surface shape and color of each of said plurality of objects.

12. 2. The information processing apparatus according to claim 1, wherein the specifying means specifies the condition based on a method of inspection performed by the inspection means.

13. 3. The information processing apparatus according to claim 2, wherein the specifying unit classifies each of the plurality of light sources into a plurality of groups, and specifies the arrangement of the light sources by selecting a light source from the plurality of groups.

14. A program for causing a computer to function as the information processing device according to any one of claims 1 to 13.

15. a specifying step of specifying a condition under which the relative positional relationships between the object, the image capturing means, and the light source coincide among a plurality of objects; an inspection step of inspecting each of the plurality of objects based on images obtained by capturing images of the plurality of objects under the conditions; An information processing method comprising:

Images