Information processing device, information processing method, and recording medium

Abstract

An information processing device (10) comprises: an acquisition means (110) that acquires an image including an iris region of a subject; and a determination means (120) that determines an expansion method to be used for polar coordinate expansion of the iris region on the basis of shielding object information relating to a shielding object that shields the iris region. According to such an information processing device, even when a part of the iris is hidden by the shielding object, the iris image can be appropriately subject to polar coordinate expansion. Thus, for example, a feature amount is extracted from the image subjected to polar coordinate expansion, and highly accurate iris authentication can be implemented.

Description

Information processing device, information processing method, and recording medium

[0001] The present disclosure relates to the technical fields of an information processing device, an information processing method, and a recording medium.

[0002] Known examples of this type of device include those that analyze information related to the iris. For example, Patent Document 1 discloses a technique for mapping an iris image onto a polar coordinate domain in order to calculate the feature amount of the iris image.

[0003] Special Publication No. 2008-538425

[0004] This disclosure aims to improve upon the related art discussed above.

[0005] A first aspect of the information processing device disclosed herein comprises an acquisition means for acquiring an image including an iris region of a target, and a determination means for determining an expansion method to be used for polar coordinate expansion of the iris region based on occluding object information regarding an occluding object that occludes the iris region.

[0006] A second aspect of the information processing device disclosed herein comprises an acquisition means for acquiring an image including an iris region of a target, an extraction means for extracting features of the iris region, and a learning means for training the extraction means in accordance with occluding object information relating to an occluding object that occludes the iris region.

[0007] A third aspect of the information processing device disclosed herein comprises an acquisition means for acquiring an image including an iris region of a target, a plurality of extraction means for extracting features of the iris region in a manner according to an obstruction that obstructs the iris region, and a selection means for selecting an extraction means to use from the plurality of extraction means according to obstruction information regarding the obstruction.

[0008] A first aspect of the information processing method of this disclosure involves using at least one computer to acquire an image including an iris region of a target, and determining an expansion method to be used for polar coordinate expansion of the iris region based on occluding object information regarding an occluding object that occludes the iris region.

[0009] A first aspect of the recording medium of this disclosure has recorded thereon a computer program that causes at least one computer to execute an information processing method that acquires an image including an iris region of a subject, and determines an expansion method to be used for polar coordinate expansion of the iris region based on occluding object information regarding an occluding object that occludes the iris region.

[0010] 1 is a block diagram showing a hardware configuration of a first information processing device. 2 is a block diagram showing a functional configuration of the first information processing device. 3 is a diagram showing a concept of normalization processing of an iris image. 4 is a diagram showing a specific example of an eye image. 5 is a flowchart showing an operation flow in the first information processing device. 6 is a block diagram showing a functional configuration of a second information processing device. 7 is a flowchart showing an operation flow in the second information processing device. 8 is a conceptual diagram showing an example of a development method corresponding to small eyes. 9 is a conceptual diagram showing an example of a development method corresponding to colored contact lenses. 10 is a block diagram showing a functional configuration of a third information processing device. 11 is a flowchart showing an operation flow in the third information processing device. 12 is a conceptual diagram showing an example of a development method corresponding to a state where an obstruction is present. 13 is a flowchart showing an operation flow in the fourth information processing device. 14 is a flowchart showing an operation flow in a modified example of the fourth information processing device. 15 is a flowchart showing an operation flow in a modified example of the fifth information processing device. 16 is a block diagram showing a functional configuration of a sixth information processing device. 17 is a flowchart showing an operation flow in the sixth information processing device. 18 is a block diagram showing a functional configuration of a modified example of the sixth information processing device. 19 is a flowchart showing an operation flow in a modified example of the sixth information processing device. 20 is a block diagram showing a functional configuration of a seventh information processing device. 21 is a flowchart showing an operation flow in the seventh information processing device. 22 is a block diagram showing a functional configuration of a modified example of the seventh information processing device. 23 is a flowchart showing an operation flow in a modified example of the seventh information processing device. 24 is a block diagram showing a functional configuration of an eighth information processing device. 10 is a flowchart showing the flow of operations in an eighth information processing device. 11 is a block diagram showing the functional configuration of a ninth information processing device. 12 is a flowchart showing the flow of operations in the ninth information processing device. 13 is a block diagram showing the functional configuration of a tenth information processing device. 14 is a block diagram showing the functional configuration related to learning of the tenth information processing device. 15 is a flowchart showing the flow of learning operations in the tenth information processing device. 16 is a block diagram showing the functional configuration of an eleventh information processing device. 17 is a flowchart showing the flow of operations in the eleventh information processing device.It is a block diagram showing the functional configuration of a twelfth information processing apparatus. It is a block diagram showing the functional configuration of a thirteenth information processing apparatus. It is a flowchart showing the flow of operations in the thirteenth information processing apparatus.

[0011] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0012] First Embodiment A first embodiment will be described with reference to FIGS. 1 to 3. FIG.

[0013] (Hardware Configuration) First, the hardware configuration of the first information processing apparatus will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the first information processing apparatus.

[0014] 1, a first information processing device 10 includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. The information processing device 10 may further include an input device 15 and an output device 16. The processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected to each other via a data bus 17.

[0015] The processor 11 loads a computer program. For example, the processor 11 is configured to load a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. Alternatively, the processor 11 may load a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown). The processor 11 may acquire (i.e., load) the computer program from a device (not shown) located outside the information processing device 10 via a network interface. The processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the loaded computer program. In particular, in this embodiment, when the processor 11 executes the loaded computer program, a functional block that executes processing related to polar coordinate expansion of the iris is realized within the processor 11. In other words, the processor 11 may function as a controller that executes each control in the information processing device 10.

[0016] The processor 11 may be configured as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or a quantum processor. The processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.

[0017] The RAM 12 temporarily stores computer programs executed by the processor 11. The RAM 12 temporarily stores data that the processor 11 temporarily uses while it is executing the computer programs. The RAM 12 may be, for example, a dynamic random access memory (D-RAM) or a static random access memory (SRAM). Alternatively, other types of volatile memory may be used instead of the RAM 12.

[0018] The ROM 13 stores computer programs executed by the processor 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a programmable read-only memory (PROM) or an erasable read-only memory (EPROM). Alternatively, other types of non-volatile memory may be used instead of the ROM 13.

[0019] The storage device 14 stores data that is to be saved long-term by the information processing device 10. The storage device 14 may operate as a temporary storage device for the processor 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

[0020] The input device 15 is a device that receives input instructions from a user of the information processing device 10. The input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel. The input device 15 may be configured as a mobile terminal such as a smartphone or a tablet. The input device 15 may also be, for example, a device that includes a microphone and is capable of voice input.

[0021] The output device 16 is a device that outputs information related to the information processing device 10 to the outside. For example, the output device 16 may be a display device (e.g., a display) that can display information related to the information processing device 10. The output device 16 may also be a speaker or the like that can output information related to the information processing device 10 as audio. The output device 16 may be configured as a mobile terminal such as a smartphone or a tablet.

[0022] 1 shows an example of an information processing device 10 including multiple devices, but all or some of the functions may be realized by a single device. Such an information processing device may be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., the storage device 14, input device 15, output device 16, etc.) may be provided by an external device connected to the information processing device 10. Furthermore, some of the calculation functions of the information processing device 10 may be realized by an external device (e.g., an external server, a cloud, etc.).

[0023] (Functional Configuration) Next, the functional configuration of the first information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the first information processing device.

[0024] 2, the first information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110 and an unfolding method determination unit 120. Each of the iris acquisition unit 110 and the unfolding method determination unit 120 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0025] The iris acquisition unit 110 is configured to be able to acquire an iris image including the target iris region. The iris acquisition unit 110 may acquire data directly from a camera, for example, or may read out an iris image that has been captured in advance and stored in storage (for example, the storage device 14). The iris image acquired by the iris acquisition unit 110 is configured to be output to the unfolding method determination unit 120.

[0026] An iris image will be further described with reference to FIG. 3 . The iris acquisition unit 110 may acquire an image of the subject's eye (see, for example, FIG. 3( a)). The iris acquisition unit 110 may detect the pupil 52, for example, by extracting pixels with a brightness lower than a predetermined value from the image of the eye. The iris acquisition unit 110 may identify the position of the detected pupil 52. Note that the shape of the pupil 52 can be approximated as a circle. Therefore, the position of the pupil 52 may be expressed, for example, by the center coordinates and radius of the pupil 52.

[0027] The iris acquisition unit 110 may detect the iris 51 from the image of the eye. The iris acquisition unit 110 may identify the position of the detected iris 51. As shown in FIG. 3A , the iris 51 includes the pupil 52, and therefore the shape of the iris 51 is a ring shape. Therefore, the position of the iris 51 may be expressed by the center coordinates of the iris 51, and the outer and inner radii of the iris 51. As shown in FIG. 3A , the inner edge of the iris 51 corresponds to the outer edge of the pupil 52, and therefore the inner radius of the iris 51 corresponds to the radius of the pupil 52. The iris acquisition unit 110 may detect the outer radius of the iris 51 by detecting the outer edge of the iris 51 based on a change in brightness at the boundary between the outer edge of the iris 51 and the sclera (the so-called white of the eye), for example.

[0028] The iris acquisition unit 110 may acquire the iris image 510 shown in Fig. 3(b) by extracting an iris region 51a, which is a region corresponding to the iris 51, from the image of the eye based on the position of the iris 51 identified as described above. Note that the process of extracting the iris region from the image of the eye may be performed by a processing block different from the iris acquisition unit 110 or by a device different from the first information processing device 10. The method of extracting the iris region from the image of the eye is not limited to the above-described method, and other methods may also be used.

[0029] The unfolding method determination unit 120 is configured to be able to determine the unfolding method to be used for unfolding the iris region in polar coordinates, based on information about an occluding object (hereinafter referred to as "occluding object information") in the iris image (e.g., iris image 510 shown in FIG. 3(b)) acquired by the iris acquisition unit 110. Here, an "occluding object" refers to an object that at least partially obstructs the iris of a subject in the iris image. Specific examples of an occluding object include eyelids (particularly eyelids when the eyes are narrowed) and colored contact lenses (hereinafter referred to as "colored contacts"). The unfolding method determination unit 120 may have a function to acquire the occluding object information by analyzing the iris image.

[0030] Polar coordinate expansion is a process of expanding the iris region, for example, around the center of the pupil circle as an axis. Specifically, as shown in FIG. 3C, it is a process of converting a circular iris region 51a included in an iris image 510 into a rectangular image 520. This process may be performed, for example, by coordinate-transforming the iris region 51a from an xy plane coordinate system to an rθ polar coordinate system. Normalizing the polar coordinate expansion results in an expanded image of the iris region.

[0031] The bottom edge of the image 520 shown in FIG. 3C corresponds to the inner edge of the iris 51. The top edge of the image 520 corresponds to the outer edge of the iris 51. The inner edge of the iris 51 may also be referred to as the pupil circle. The outer edge of the iris 51 may also be referred to as the iris circle. As described above, the inner radius of the iris 51 corresponds to the radius of the pupil 52. The radius of the pupil 52 may change due to, for example, the brightness of the lighting. Therefore, the inner radius of the iris 51 may change due to, for example, the brightness of the lighting. Furthermore, the size of the iris region 51a in the image of the subject's eye (e.g., distance d in FIG. 3C) may change due to the distance between the camera capturing the subject and the subject. In other words, the size of the iris region included in the iris image acquired by the iris acquisition unit 110 (e.g., the iris region 51a included in the iris image 510) is not constant.

[0032] In order to correct the deviation in size of iris region 51a that occurs when photographing the subject, for example, by setting the value of the bottom side of image 520 to "0" and the value of the top side of image 520 to "1," and changing the value of the vertical axis of image 520 so that the value of the vertical axis of image 520 is between 0 and 1, this is an example of "normalizing the polar coordinate expansion" described above.

[0033] In order to correct a size discrepancy in the iris region 51a that occurs when photographing a subject, the inner radius of the iris image 510 (i.e., the inner radius of the iris 51) and the outer radius of the iris image 510 (i.e., the outer radius of the iris 51) may each be changed to a predetermined value, and then the iris region 51a may be subjected to polar coordinate expansion to obtain a normalized expanded image of the iris region. In practice, for example, polar coordinate expansion and normalization may be performed simultaneously by including a variable for normalization in a coordinate transformation matrix for polar coordinate expansion of the iris region. An image in which the iris region has been expanded in polar coordinates (e.g., image 520) may be referred to as a rubber sheet image. For this reason, polar coordinate expansion of the iris region may also be referred to as rubber sheet expansion.

[0034] Specific examples of images of a target eye will be described with reference to Fig. 4. Fig. 4(a) is an image of an eye in which the iris 51 is reflected. Fig. 4(b) is an image of an eye in which part of the iris 51 is obscured by the eyelid. Fig. 4(c) is an image of an eye in which part of the iris 51 (particularly the outer periphery of the iris 51) is obscured by the pattern of colored contact lenses. Note that the part indicated by the symbol "CCL" in Fig. 4 corresponds to the colored contact lens.

[0035] As described above, iris images are often acquired from eye images on the assumption that the shape of the iris 51 is circular. For this reason, the iris images acquired from the eye images shown in Figures 4(b) and 4(c) include the pattern of the eyelids or colored contact lenses in addition to the iris 51.

[0036] For example, an image (e.g., image 520 shown in FIG. 3C) obtained by polar coordinate expansion of an iris image acquired from the eye image shown in FIG. 4A includes an iris pattern, and therefore, feature quantities related to the iris 51 can be calculated from the image.

[0037] In contrast, when the iris images acquired from the eye images shown in each of Figures 4(b) and 4(c) are expanded into polar coordinates in the same way as the iris image acquired from the eye image shown in Figure 4(a), the images obtained by expanding the iris images acquired from the eye images shown in each of Figures 4(b) and 4(c) into polar coordinates include portions of the iris pattern that are shielded (in other words, covered) by the eyelid or the pattern of the colored contact lenses. The portions of the iris pattern that are shielded by the eyelid or the pattern of the colored contact lenses cannot be used in calculating the feature amounts related to the iris 51.

[0038] In iris authentication, feature amounts related to the iris 51 of a subject are compared with feature amounts of a pre-registered comparison subject (e.g., a registered individual). If the iris pattern is not obscured by the eyelids or the pattern of colored contact lenses (e.g., see FIG. 4A), and the subject and comparison subject are identical, the matching score (i.e., the score of the degree of match of the feature amounts) will be greater than a predetermined threshold. On the other hand, if the iris pattern is obscured by the eyelids or the pattern of colored contact lenses, the matching score may not exceed the predetermined threshold even if the subject and comparison subject are identical. In other words, if the iris region of the subject is obscured by an obstruction such as an eyelid, the authentication performance of iris authentication may be reduced.

[0039] Therefore, the expansion method determination unit 120 determines the expansion method to be used when performing this polar coordinate expansion based on the occluding object information. The expansion method determination unit 120 may be configured to select an expansion method according to the occluding object from, for example, a plurality of expansion methods prepared in advance. For example, the plurality of expansion methods may include a method of performing polar coordinate expansion on the entire iris image, and a method of performing polar coordinate expansion on only a portion of the iris image in which the iris pattern is not obstructed by an obstructing object such as an eyelid. Note that determining the expansion method based on the occluding object information may include determining or changing parameters related to the polar coordinate expansion based on the occluding object information. More specific expansion methods for polar coordinate expansion will be described in other embodiments below.

[0040] (Flow of Operation) Next, the flow of operation of the first information processing device 10 will be described with reference to Fig. 5. Fig. 3 is a flowchart showing the flow of operation in the first information processing device.

[0041] 5, when the operation of the first information processing device 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the unfolding method determination unit 120 determines the unfolding method to be used for unfolding the iris image into polar coordinates based on the obstructing object information in the iris image (step S102).

[0042] The unfolding method determination unit 120 may output information related to the unfolding method determined. In this case, the information processing device 10 may execute a process of unfolding the iris image into polar coordinates using the unfolding method determined by the unfolding method determination unit 120. The unfolded image obtained by polar coordinate unfolding may be used for iris authentication, for example. Iris authentication using an unfolded image will be described in detail in another embodiment described later.

[0043] (Technical Effects) Next, technical effects obtained by the first information processing device 10 will be described.

[0044] As described with reference to Figures 1 to 5, in the first information processing device 10, the expansion method to be used for polar coordinate expansion is determined based on the obstruction information in the iris image. In this way, it is possible to more appropriately expand the iris image into polar coordinates. For example, by using different expansion methods when an obstruction is present and when no obstruction is present, more appropriate polar coordinate expansion can be performed. Alternatively, by using different expansion methods depending on the type of obstruction, etc., more appropriate polar coordinate expansion can be performed.

[0045] As described above, if the iris pattern is obscured by an obstruction such as an eyelid, the authentication performance of iris authentication may be degraded unless some countermeasure is taken. In response to this, the first information processing device 10 determines the expansion method based on the obstruction information, thereby enabling the iris image to be appropriately expanded into polar coordinates. As a result, even in a situation where the iris region is obscured, it is possible to prevent a decrease in the authentication performance of iris authentication.

[0046] Second Embodiment A second embodiment will be described with reference to Figures 6 to 9. The second embodiment differs from the first embodiment described above only in some configurations and operations, and other parts may be the same as the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit a description of other overlapping parts as appropriate.

[0047] (Functional Configuration) First, the functional configuration of the second information processing device 10 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing the functional configuration of the second information processing device. Note that in Fig. 6, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0048] 6, the second information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, a deployment method determination unit 120, an obstructing object presence / absence determination unit 130, and an obstructing object type determination unit 140. That is, the second information processing device 10 further includes, in addition to the configuration described in the first embodiment (see FIG. 2), the obstructing object presence / absence determination unit 130 and the obstructing object type determination unit 140. The obstructing object presence / absence determination unit 130 and the obstructing object type determination unit 140 may be processing blocks realized by, for example, the above-described processor 11 (see FIG. 1).

[0049] The obstruction presence / absence determination unit 130 is configured to be able to determine whether an obstruction exists in the iris region included in the iris image (e.g., iris image 510). For example, the obstruction presence / absence determination unit 130 may determine that an obstruction exists when the subject's eyes are narrowed (i.e., the eyes are not wide open, in other words, part of the iris region is obstructed by the eyelids). Alternatively, the obstruction presence / absence determination unit 130 may determine that an obstruction exists when the subject is wearing colored contact lenses (i.e., part of the iris region is obstructed by the pattern of the colored contact lenses). Furthermore, the obstruction presence / absence determination unit 130 may determine that no obstruction exists when the subject's eyes are wide open and the subject is not wearing colored contact lenses.

[0050] For example, the obstructing object presence / absence determination unit 130 may detect the edges of the upper eyelid and the lower eyelid from an iris image (e.g., iris image 510). The obstructing object presence / absence determination unit 130 may determine that the eyes are squinting when the distance between the edges of the upper eyelid and the lower eyelid is less than a predetermined distance.

[0051] The obstruction presence / absence determination unit 130 may determine the presence or absence of an obstruction by performing image processing on the iris image. The obstruction presence / absence determination unit 130 may determine the presence or absence of an obstruction using a model that outputs information indicating the presence or absence of an obstruction when an iris image is input. An example of such a model is a model using a neural network (e.g., a convolutional neural network (CNN)). The model may be, for example, a model that has been trained to be able to determine the presence or absence of an obstruction using multiple images with an obstruction and multiple images without an obstruction. The method for determining the presence or absence of an obstruction is not limited to the above-described method, and other methods may also be used.

[0052] The information indicating the determination result by the obstruction presence / absence determining unit 130 (for example, information indicating the presence or absence of an obstruction) corresponds to an example of the obstruction information described above.

[0053] The obstructing object type determination unit 140 is configured to be able to determine the type of obstructing object when the obstructing object presence determination unit 130 determines that an obstructing object is present. The type of obstructing object may include, for example, at least one of an eyelid and colored contact lenses. For example, the obstructing object type determination unit 140 may be configured to be able to determine whether the obstructing object is an eyelid or colored contact lenses.

[0054] The obstructing object type determination unit 140 may determine the type of obstructing object by performing image processing on the iris image. The obstructing object type determination unit 140 may determine the type of obstructing object using a model that outputs information indicating the type of obstructing object when an iris image is input. An example of such a model is a model using a neural network (e.g., a CNN). For example, the model may be trained to determine the type of obstructing object using multiple iris images that include at least one of an eyelid and colored contact lenses. In this case, the model may have outputs equal to the number of obstructing object types (e.g., the output layer of the neural network may include nodes corresponding to the number of obstructing object types). The obstructing object type determination unit 140 may determine the type of obstructing object corresponding to the maximum output among multiple outputs of the model as the type of obstructing object.

[0055] If the model has as many outputs as there are types of obstructing objects, the model outputs may be expressed as likelihoods. In this case, the obstructing object type determination unit 140 may determine, as the type of obstructing object, the type of obstructing object corresponding to the output having the largest likelihood among the multiple outputs of the model, which has a likelihood equal to or greater than a certain value. On the other hand, the obstructing object type determination unit 140 may determine that there is no obstructing object if all of the multiple likelihoods as the multiple outputs of the model are less than a certain value. In this case, the obstructing object type determination unit 140 can determine the presence or absence of an obstructing object. Therefore, the obstructing object type determination unit 140 may include the obstructing object presence / absence determination unit 130 (i.e., the obstructing object type determination unit 140 may include the functionality related to the obstructing object presence / absence determination unit 130). The method for determining the type of other obstructing objects is not limited to the above-described method, and other methods may also be used.

[0056] The information indicating the determination result by the obstructing object type determination unit 140 (for example, information indicating the type of obstructing object) corresponds to another example of the obstructing object information described above.

[0057] (Operation Flow) Next, the operation flow of the second information processing device 10 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the operation flow in the second information processing device. Note that in Fig. 7, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0058] 7 , when the operation of the second information processing device 10 starts, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction determination unit 130 determines whether or not an obstruction is present in the iris image (step S201). If it is determined that no obstruction is present (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction is present (step S202).

[0059] As described above, the information indicating the determination result by the obstruction presence / absence determination unit 130 corresponds to an example of obstruction information. Therefore, in the process of step S202, the unfolding method determination unit 120 determines the unfolding method based on the obstruction information. An example of an unfolding method that corresponds to a state in which there is no obstruction is a method in which the entire annular iris region 51 a included in the iris image 510 is unfolded into polar coordinates, as shown in FIG. 3( c).

[0060] On the other hand, if it is determined that a shielding object is present (step S201: YES), the shielding object type determination unit 140 determines the type of the shielding object (step S203). Then, the deployment method determination unit 120 determines a deployment method based on the determined type of shielding object (step S204). As described above, information indicating the determination result by the shielding object type determination unit 140 corresponds to an example of shielding object information. Therefore, in the processing of step S204, the deployment method determination unit 120 determines a deployment method based on the shielding object information.

[0061] For example, if the obstructing object type determination unit 140 determines that the type of obstructing object is an eyelid (in other words, if the eye is narrowed), the unfolding method determination unit 120 may determine an unfolding method suitable for narrow eyes. Here, an example of an unfolding method suitable for narrow eyes will be described with reference to Fig. 8. Fig. 8 is a conceptual diagram showing an example of an unfolding method suitable for narrow eyes.

[0062] When a portion of the iris region is obscured by the eyelid, for example, as shown in FIG. 3C , if the entire annular iris region 51a included in the iris image 510 is polar coordinate expanded (in other words, if all angles of the iris region 51a are polar coordinate expanded), as shown in the expanded image 530 of FIG. 8 , there will be a region where the iris pattern is visible even when the subject squints, and other regions (i.e., a region where the iris pattern is obscured by the eyelid when the subject squints). Therefore, when the subject squints, the region from which information about the iris pattern can be obtained from the expanded image 530 will be narrowed. The bottom edge of the expanded image 530 corresponds to the outer edge of the iris (in other words, the iris circle). The top edge of the expanded image 530 corresponds to the inner edge of the iris (in other words, the pupil circle).

[0063] On the other hand, in the development method suitable for narrow eyes according to this embodiment, polar coordinate development is performed to develop only the periphery of the area that is visible even when the eyes are narrowed. Specifically, in the development method suitable for narrow eyes, polar coordinate development may be performed to extract partial areas of the iris region at predetermined angles (e.g., partial areas Ar1 and Ar2 shown in FIG. 8). For example, the partial areas of the predetermined angles may be the partial areas of [-30 degrees, 30 degrees] or [150 degrees, 210 degrees]. In other words, the partial areas of the predetermined angles may include the partial area from 0 degrees to 30 degrees, the partial area from 150 degrees to 210 degrees, and the partial area from 330 degrees to 360 degrees.

[0064] The unfolded image 540 according to the unfolding method mentioned in the details may be an image in which a plurality of images, in which partial regions of the iris region at a predetermined angle are unfolded using polar coordinates, are combined in the angular direction (i.e., the horizontal direction of the unfolded image 540). In this way, if the size of the unfolded image 540 is normalized to the same size as the unfolded image 530 according to the comparative example in which the entire region is unfolded using polar coordinates, an image with high resolution in the visible iris region can be obtained.

[0065] For example, if the obstructing object type determination unit 140 determines that the obstructing object is a colored contact lens, the unfolding method determination unit 120 may determine a unfolding method suitable for the colored contact lens. An example of a unfolding method suitable for the colored contact lens will now be described with reference to Fig. 9. Fig. 9 is a conceptual diagram showing an example of a unfolding method suitable for the colored contact lens.

[0066] When a portion of the iris region is obscured by the pattern of colored contact lenses, for example, as shown in FIG. 3C , if the entire annular iris region 51a included in the iris image 510 is subjected to polar coordinate expansion (in other words, if the entire radius from the inner radius to the outer radius of the iris 51 is subjected to polar coordinate expansion), as shown in the expanded image 550 of FIG. 9 , there will be an area where the iris pattern is visible even when the subject is wearing colored contact lenses, and other areas (i.e., areas where the iris pattern is obscured by the pattern of the colored contact lenses). Therefore, if the subject is wearing colored contact lenses, the area from which information about the iris pattern can be obtained from the expanded image 550 will be narrowed. The bottom edge of the expanded image 550 corresponds to the outer edge of the iris (in other words, the iris circle). The top edge of the expanded image 550 corresponds to the inner edge of the iris (in other words, the pupil circle).

[0067] On the other hand, in the development method suitable for colored contact lenses according to this embodiment, polar coordinate development is performed so as to develop only the periphery of the area where the iris pattern is visible even when the subject is wearing colored contact lenses. Specifically, in the development method suitable for colored contact lenses, polar coordinate development may be performed so as to extract the area around the pupil circle (for example, area Ar3 shown in FIG. 9).

[0068] Note that, because the size of the pupil circle changes depending on the lighting environment in which the subject is located, the area around the pupil circle may be determined by the ratio of the radii of the pupil circle to the radii of the iris circle. For example, the area around the pupil circle may be an area where the ratio of the radii of the pupil circle to the radii of the iris circle is r:1-r (0<r<1). The ratio of the radii of the pupil circle to the radii of the iris circle is not limited to this, and any ratio may be used.

[0069] The unfolded image 560 according to the unfolding method suitable for color contact lenses may be an image obtained by unfolding the area of ​​the iris region around the pupil circle (for example, area Ar3 shown in FIG. 9 ) using polar coordinates. In this way, if the size of the unfolded image 560 is normalized to the same size as the unfolded image 550 according to the comparative example, an image with high resolution in the visible part of the iris region can be obtained.

[0070] (Technical Effects) Next, technical effects obtained by the second information processing device 10 will be described.

[0071] 6 to 9, in the second information processing device 10, the expansion method used for expanding the iris region into polar coordinates is determined depending on whether or not an obstruction is present. In addition, if an obstruction is present, the expansion method used for expanding the iris region into polar coordinates is further determined depending on the type of obstruction. In this way, different expansion methods are used depending on whether or not an obstruction is present and the type of obstruction, making it possible to expand the iris image into polar coordinates more appropriately.

[0072] Third Embodiment A third embodiment will be described with reference to Figures 10 to 12. The third embodiment differs from the second embodiment described above only in some configurations and operations, and other parts may be similar to the first and second embodiments. Therefore, the following will describe in detail the parts that differ from the first and second embodiments, and will omit a description of other overlapping parts as appropriate.

[0073] (Functional Configuration) First, the functional configuration of the third information processing device 10 will be described with reference to Fig. 10. Fig. 10 is a block diagram showing the functional configuration of the third information processing device. Note that in Fig. 10, the same elements as those shown in Fig. 6 are denoted by the same reference numerals.

[0074] 10, the third information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, a deployment method determination unit 120, and an obstruction presence / absence determination unit 130. That is, compared to the second information processing device 10 (see FIG. 6) described in the second embodiment, the third information processing device 10 does not include the obstruction type determination unit 140.

[0075] (Operation Flow) Next, the operation flow of the third information processing device 10 will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the operation flow in the third information processing device. Note that in Fig. 11, the same processes as those shown in Fig. 7 are denoted by the same reference numerals.

[0076] 11 , when the operation of the third information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction determination unit 130 determines whether or not an obstruction is present in the iris image (step S201). If it is determined that no obstruction is present (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction is present (step S202).

[0077] If it is determined that an obstruction is present (step S201: YES), the unfolding method determination unit 120 determines an unfolding method corresponding to the presence of an obstruction (step S301). For example, an unfolding method corresponding to the presence of an obstruction may be a polar coordinate unfolding method for extracting partial regions Ar4 and Ar5 of the iris region, as shown in FIG. 12 . Here, partial regions Ar4 and Ar5 may be regions of the iris region that are unlikely to be obscured by the eyelids or the pattern of colored contact lenses. In other words, partial regions Ar4 and Ar5 may be regions in which the iris pattern is visible even when the subject is squinting or wearing colored contact lenses.

[0078] 12 may be an image obtained by angularly combining a plurality of images obtained by polar coordinate expansion of partial regions Ar4 and Ar5 of the iris region. In this way, if the size of exfoliated image 570 is normalized to the same size as an exfoliated image obtained by polar coordinate expansion of the entire iris region, an image with high resolution in the visible iris region can be obtained.

[0079] In the process of step S301, the unfolding method determination unit 120 may select at least one of the unfolding methods suitable for fine eyes and the unfolding method suitable for colored contact lenses as the unfolding method for the state where an obstruction is present.

[0080] (Technical Effects) Next, technical effects obtained by the third information processing apparatus 10 will be described.

[0081] 10 to 12, in the third information processing device 10, the expansion method to be used for polar coordinate expansion is determined depending on whether or not there is an obstruction. In this way, different expansion methods are used when there is an obstruction and when there is no obstruction, making it possible to expand the iris image into polar coordinates more appropriately.

[0082] <Fourth Embodiment> A fourth embodiment will be described with reference to Figures 13 and 14. Note that the fourth embodiment differs from the second embodiment described above only in some of its operations, and other parts may be similar to the first to third embodiments. Therefore, the following will describe in detail only the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0083] (Operation Flow) First, the operation flow of the fourth information processing device 10 will be described with reference to FIG. 13. Here, the functional configuration of the fourth information processing device 10 is the same as the functional configuration of the second information processing device 10 shown in FIG. 6. However, the obstructing object type determination unit 140 of the fourth information processing device 10 may determine whether the type of obstructing object is an eyelid. In other words, the obstructing object type determination unit 140 may determine whether the object is a narrowed eye. FIG. 13 is a flowchart showing the operation flow of the fourth information processing device. Note that in FIG. 13, the same processes as those shown in FIG. 7 are denoted by the same reference numerals.

[0084] 13 , when the operation of the fourth information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction determination unit 130 determines whether or not an obstruction is present in the iris image (step S201). If it is determined that no obstruction is present (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction is present (step S202).

[0085] On the other hand, if it is determined that an obstruction is present (step S201: YES), the obstruction type determination unit 140 determines whether the type of obstruction is an eyelid (step S401). If the determined obstruction is an eyelid (step S401: YES), the unfolding method determination unit 120 determines a unfolding method suitable for narrow eyes (step S402). On the other hand, if the determined obstruction is not an eyelid (step S401: NO), the unfolding method determination unit 120 determines a unfolding method suitable for obstructions other than narrow eyes (step S403). An unfolding method suitable for obstructions other than narrow eyes may be, for example, a unfolding method suitable for colored contact lenses.

[0086] (Modification) Next, the flow of operations in a modification of the fourth information processing device 10 will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the flow of operations in the modification of the fourth information processing device. Note that in Fig. 14, the same processes as those shown in Fig. 13 are denoted by the same reference numerals.

[0087] 14 , when the operation of the fourth information processing device 10 according to the modified example is started, the iris acquisition unit 110 first acquires an iris image including the iris region of the target (step S101). Then, the unfolding method determination unit 120 determines whether the target in the iris image has narrowed eyes (step S451). That is, in this modified example, a determination as to whether an obstruction is present or absent is not made, but a binary determination as to whether the target has narrowed eyes or not is made. Therefore, the information processing device 10 according to the modified example does not need to include the obstruction presence / absence determination unit 130 and the obstruction type determination unit 140.

[0088] Then, when the subject is in a narrowed eye state (step S451: YES), the expansion method determination unit 120 determines a expansion method suitable for narrowed eyes (step S402). On the other hand, when the subject is not in a narrowed eye state (step S451: NO), the expansion method determination unit 120 determines a expansion method suitable for eyes other than narrowed eyes (step S452). The expansion method suitable for eyes other than narrowed eyes may be, for example, a expansion method that corresponds to no obstruction or a expansion method suitable for colored contact lenses.

[0089] (Technical Effects) Next, technical effects obtained by the fourth information processing apparatus 10 will be described.

[0090] 13 and 14, in the fourth information processing device 10, when it is determined that the obstructing object is an eyelid, a development method suitable for the squinting state is determined. In this way, even when the subject has squinted eyes, it is possible to appropriately obtain information about the iris region by polar coordinate development.

[0091] Fifth Embodiment The fifth embodiment will be described with reference to Figures 15 and 16. Note that the fifth embodiment differs from the second embodiment described above only in some of its operations, and other parts may be similar to the first to fourth embodiments. Therefore, the following will describe in detail only the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0092] (Operation Flow) First, the operation flow of the fifth information processing device 10 will be described with reference to Fig. 15. Here, the functional configuration of the fourth information processing device 10 is the same as the functional configuration of the second information processing device 10 shown in Fig. 6. However, the shielding object type determination unit 140 of the fifth information processing device 10 may determine whether the type of shielding object is colored contact lenses. Fig. 15 is a flowchart showing the operation flow of the fifth information processing device. Note that in Fig. 15, the same processes as those shown in Fig. 7 are denoted by the same reference numerals.

[0093] 15 , when the operation of the fifth information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction determination unit 130 determines whether or not an obstruction exists in the iris image (step S201). If it is determined that no obstruction exists (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction exists (step S202).

[0094] On the other hand, if it is determined that an obstructing object is present (step S201: YES), the obstructing object type determination unit 140 determines whether the obstructing object is colored contact lenses (step S501). If the obstructing object is determined to be colored contact lenses (step S501: YES), the unfolding method determination unit 120 determines a unfolding method suitable for colored contact lenses (step S502). On the other hand, if the obstructing object is determined not to be colored contact lenses (step S501: NO), the unfolding method determination unit 120 determines a unfolding method suitable for obstructing objects other than colored contact lenses (step S503). An unfolding method suitable for obstructing objects other than colored contact lenses may be, for example, a unfolding method suitable for narrow eyes.

[0095] (Modification) Next, the flow of operations in a modification of the fifth information processing device 10 will be described with reference to Fig. 16. Fig. 16 is a flowchart showing the flow of operations in the modification of the fifth information processing device. Note that in Fig. 16, the same processes as those shown in Fig. 15 are denoted by the same reference numerals.

[0096] 16 , when the operation of the fifth information processing device 10 according to the modified example is started, the iris acquisition unit 110 first acquires an iris image including the iris region of the subject (step S101). Then, the unfolding method determination unit 120 determines whether the subject in the iris image is wearing colored contact lenses (step S551). That is, in this modified example, a determination as to whether or not an obstruction is present is not made, but a binary determination as to whether or not the subject is wearing colored contact lenses is made. Therefore, the information processing device 10 according to the modified example does not need to include the obstruction presence / absence determination unit 130 and the obstruction type determination unit 140.

[0097] Then, if the subject is wearing colored contacts (step S551: YES), the deployment method determination unit 120 determines a deployment method suitable for colored contacts (step S502). On the other hand, if the subject is not wearing colored contacts (step S551: NO), the deployment method determination unit 120 determines a deployment method suitable for something other than colored contacts (step S552). The deployment method suitable for something other than colored contacts may be, for example, a deployment method that corresponds to no obstruction or a deployment method suitable for narrow eyes.

[0098] (Technical Effects) Next, technical effects obtained by the fifth information processing apparatus 10 will be described.

[0099] 15 and 16, when the fifth information processing device 10 determines that the obstructing object is colored contact lenses, it determines a development method suitable for colored contact lenses. In this way, even if the subject is wearing colored contact lenses, it is possible to appropriately obtain information about the iris region by polar coordinate development.

[0100] Sixth Embodiment A sixth embodiment will be described with reference to Figures 17 to 20. Note that the sixth embodiment differs from the first to fifth embodiments described above only in part of the configuration and operation, and other parts may be similar to the first to fifth embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0101] (Functional Configuration) First, the functional configuration of the sixth information processing device 10 will be described with reference to Fig. 17. Fig. 17 is a block diagram showing the functional configuration of the sixth information processing device. Note that in Fig. 17, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0102] 17, the sixth information processing apparatus 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an unfolding method determination unit 120, and an occlusion amount estimation unit 150. That is, the sixth information processing apparatus 10 further includes, in addition to the configuration described in the first embodiment (see FIG. 2), an occlusion amount estimation unit 150. The occlusion amount estimation unit 150 may be a processing block realized by, for example, the above-described processor 11 (see FIG. 1).

[0103] The occlusion amount estimation unit 150 is configured to be able to estimate the occlusion amount of the iris region. Here, the "occlusion amount" is a value indicating the size of an area in the iris region where the iris pattern is occluded by an occluding object. The occlusion amount is a value estimated as occluding object information. The occlusion amount estimation unit 150 may estimate the occlusion amount by performing image processing on the iris image. The occlusion amount estimation unit 150 may estimate the occlusion amount using a model that outputs the occlusion amount when an iris image is input. An example of such a model is a model using a neural network (e.g., a CNN). Alternatively, the occlusion amount estimation unit 150 may estimate the occlusion amount using a model that outputs the iris region and an occlusion area where the iris pattern is occluded by the occluding object when an iris image is input. Such a model may be a model that has been trained to be able to estimate the area occluded by an occluding object and the iris area using training data consisting of, for example, a certain iris image, the iris area corresponding to that image, and correct data on the occluded area thereof. The occlusion amount estimation unit 150 may estimate the occlusion amount of the iris area using the areas of the occluded area and the iris area estimated by the model. The method for estimating the occlusion amount is not limited to the above-described method, and other methods may also be used.

[0104] (Operation Flow) Next, the operation flow of the sixth information processing device 10 will be described with reference to Fig. 18. Fig. 18 is a flowchart showing the operation flow in the sixth information processing device. Note that in Fig. 18, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0105] 18 , when the operation of the sixth information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Thereafter, the occlusion amount estimation unit 150 estimates the occlusion amount of the iris region from the iris image (step S601).

[0106] Next, the expansion method determination unit 120 determines the expansion method to be used for polar coordinate expansion of the iris image based on the occlusion amount estimated by the occlusion amount estimation unit 150 (step S602). For example, the expansion method determination unit 120 may select different expansion methods depending on whether the occlusion amount is equal to or greater than a predetermined threshold or less than the predetermined threshold. Note that a case where the occlusion amount is equal to or greater than the predetermined threshold may correspond to a case where the occlusion amount is determined by the occlusion object presence / absence determination unit 130 as described above. A case where the occlusion amount is less than the predetermined threshold may correspond to a case where the occlusion amount is determined by the occlusion object presence / absence determination unit 130 as described above. Alternatively, the expansion method determination unit 120 may determine parameters related to polar coordinate expansion (e.g., an expansion angle for an expansion method suitable for narrow eyes, an expansion radius for an expansion method suitable for colored contact lenses, etc.) depending on the occlusion amount.

[0107] The amount of shielding estimated by the shielding amount estimation unit 150 corresponds to another example of the above-mentioned shielding object information. Therefore, in the process of step S602, the deployment method determination unit 120 can be said to determine the deployment method based on the shielding object information.

[0108] (Configuration of Modified Example) Next, a functional configuration of a modified example of the sixth information processing device 10 will be described with reference to Fig. 19. Fig. 19 is a block diagram showing the functional configuration of a modified example of the sixth information processing device. Note that in Fig. 19, the same elements as those shown in Figs. 6 and 17 are denoted by the same reference numerals.

[0109] 19 , the sixth modified example of the information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, a deployment method determination unit 120, an obstructing object presence / absence determination unit 130, an obstructing object type determination unit 140, and an obstructing amount estimation unit 150. That is, the sixth modified example of the information processing device 10 further includes, in addition to the configuration of the sixth information processing device described above (see FIG. 17 ), the obstructing object presence / absence determination unit 130 and the obstructing object type determination unit 140. Each of the obstructing object presence / absence determination unit 130 and the obstructing object type determination unit 140 may be the same elements as those described in the second embodiment (see FIG. 6 ).

[0110] (Operation of Modified Example) Next, the flow of operations in a modified example of the sixth information processing device 10 will be described with reference to Fig. 20. Fig. 20 is a flowchart showing the flow of operations in a modified example of the sixth information processing device. Note that in Fig. 20, the same processes as those shown in Fig. 7 and Fig. 18 are denoted by the same reference numerals.

[0111] 20 , when the operation of the sixth modified example of the information processing device 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction presence / absence determination unit 130 determines whether an obstruction is present in the iris image (step S201). If it is determined that no obstruction is present (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction is present, as in the second embodiment described above (step S202).

[0112] On the other hand, if it is determined that an obstructing object is present (step S201: YES), the obstructing object type determination unit 140 determines the type of obstructing object (step S203). Then, the obstruction amount estimation unit 150 estimates the obstruction amount of the iris area caused by the determined obstructing object (step S651). If it is determined that the obstructing object is an eyelid, it can be estimated that the smaller the degree of eye opening, the greater the obstruction amount. Furthermore, if it is determined that the obstructing object is colored contact lenses, it can be estimated that the larger the patterned portion of the colored contact lenses, the greater the obstruction amount, and / or the greater the degree of overlap between the patterned portion of the colored contact lenses and the iris.

[0113] Next, the expansion method determination unit 120 determines the expansion method to be used for expanding the iris image into polar coordinates based on the type of the obstructing object estimated by the obstructing object type estimation unit 130 and the amount of obstruction estimated by the obstructing amount estimation unit 150 (step S652). The expansion method determination unit 120 may, for example, first select the expansion method according to the type of obstructing object, and then determine the parameters of the selected polar coordinate expansion according to the amount of obstruction.

[0114] (Technical Effects) Next, technical effects obtained by the sixth information processing apparatus 10 will be described.

[0115] 17 to 20, in the sixth information processing apparatus 10, the expansion method to be used for polar coordinate expansion is determined based on the amount of occlusion of the iris region by an occluding object. In this way, it is possible to more appropriately expand the iris image into polar coordinates using an expansion method according to the amount of occlusion (i.e., the size of the region hidden by the occluding object).

[0116] Seventh Embodiment The seventh embodiment will be described with reference to Figures 21 to 24. Note that the seventh embodiment differs from the first to sixth embodiments described above only in part of the configuration and operation, and other parts may be similar to the first to sixth embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0117] (Functional Configuration) First, the functional configuration of the seventh information processing device 10 will be described with reference to Fig. 21. Fig. 21 is a block diagram showing the functional configuration of the seventh information processing device. Note that in Fig. 21, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0118] 21 , the seventh information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an unfolding method determination unit 120, and an eye opening degree estimation unit 160. That is, the seventh information processing device 10 further includes, in addition to the configuration described in the first embodiment (see FIG. 2 ), an eye opening degree estimation unit 160. The eye opening degree estimation unit 160 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1 ).

[0119] The eye opening degree estimation unit 160 is configured to estimate the degree of eye opening of the subject's eye. Here, the "eye opening degree" is a value indicating the degree to which the subject's eye is open in the iris image. The eye opening degree is a value estimated as obstruction information. The eye opening degree estimation unit 160 may estimate the eye opening degree by performing image processing on the iris image. The eye opening degree estimation unit 160 may estimate the eye opening degree using a model that outputs the eye opening degree when an iris image is input. An example of such a model is a model using a neural network (e.g., a CNN). The eye opening degree estimation unit 160 may estimate points on the upper eyelid, points on the lower eyelid, and the iris diameter for the iris image using a regression model, and calculate the eye opening degree as the ratio of the distance between the coordinates of the estimated points on the upper eyelid and the lower eyelid divided by the iris diameter. In this case, the regression model may be a neural network trained using training data consisting of iris images, corresponding points on the upper eyelid, points on the lower eyelid, and iris diameter. Other methods for estimating the degree of eye opening are not limited to the above-described methods, and other methods may also be used.

[0120] (Operation Flow) Next, the operation flow of the seventh information processing device 10 will be described with reference to Fig. 22. Fig. 22 is a flowchart showing the operation flow in the seventh information processing device. Note that in Fig. 22, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0121] 22, when the operation of the seventh information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including the iris region of the target (step S101). Thereafter, the eye opening degree estimation unit 160 estimates the eye opening degree of the target from the iris image (step S701).

[0122] Next, the unfolding method determination unit 120 determines the unfolding method to be used for unfolding the iris image into polar coordinates based on the eye opening degree estimated by the eye opening degree estimation unit 160 (step S702). For example, the unfolding method determination unit 120 may select different unfolding methods when the eye opening degree is equal to or greater than a predetermined threshold and when it is less than the predetermined threshold. Note that the case where the eye opening degree is equal to or greater than the predetermined threshold may correspond to the case where the above-mentioned obstruction presence determination unit 130 determines that there is no obstruction. The case where the eye opening degree is less than the predetermined threshold may correspond to the case where the above-mentioned obstruction presence determination unit 130 determines that there is an obstruction. Alternatively, the unfolding method determination unit 120 may determine parameters related to the polar coordinate unfolding (e.g., unfolding angles related to unfolding methods suitable for narrow eyes) according to the eye opening degree.

[0123] The eye opening degree estimated by the eye opening degree estimation unit 160 corresponds to another example of the above-mentioned obstructing object information. Therefore, in the process of step S702, the deployment method determination unit 120 can be said to determine the deployment method based on the obstructing object information.

[0124] (Configuration of Modified Example) Next, a functional configuration of a modified example of the seventh information processing device 10 will be described with reference to Fig. 23. Fig. 23 is a block diagram showing the functional configuration of a modified example of the seventh information processing device. Note that in Fig. 23, the same elements as those shown in Figs. 6 and 21 are denoted by the same reference numerals.

[0125] 23 , the seventh modified information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, a deployment method determination unit 120, an obstruction presence / absence determination unit 130, an obstruction type determination unit 140, and an eye opening degree estimation unit 160. That is, the seventh modified information processing device 10 further includes, in addition to the configuration of the seventh information processing device described above (see FIG. 21 ), an obstruction presence / absence determination unit 130 and an obstruction type determination unit 140. Each of the obstruction presence / absence determination unit 130 and the obstruction type determination unit 140 may be the same elements as those described in the second embodiment (see FIG. 6 ).

[0126] (Operation of Modified Example) Next, the flow of operations in a modified example of the seventh information processing device 10 will be described with reference to Fig. 24. Fig. 24 is a flowchart showing the flow of operations in a modified example of the seventh information processing device. Note that in Fig. 24, the same processes as those shown in Fig. 7 and Fig. 22 are denoted by the same reference numerals.

[0127] 24 , when the operation of the seventh modified example of the information processing device 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the obstruction presence / absence determination unit 130 determines whether or not an obstruction is present in the iris image (step S201). If it is determined that no obstruction is present (step S201: NO), the unfolding method determination unit 120 determines an unfolding method corresponding to a state in which no obstruction is present, as in the second embodiment described above (step S202).

[0128] On the other hand, if it is determined that an obstruction is present (step S201: YES), the obstruction type determination unit 140 determines the type of obstruction (step S203). Then, the eye opening degree estimation unit 160 estimates the eye opening degree of the subject in the iris image (step S751). If it is determined that the obstruction is an eyelid, the degree of eye narrowing can be estimated from the eye opening degree. Furthermore, if it is determined that the obstruction is colored contact lenses, in addition to the influence of the colored contact lenses, the influence of the eyelids can also be estimated from the eye opening degree.

[0129] Next, the expansion method determination unit 120 determines the expansion method to be used for expanding the iris image into polar coordinates based on the type of obstruction estimated by the obstruction type estimation unit 130 and the eye opening degree estimated by the obstruction amount estimation unit 150 (step S752). The expansion method determination unit 120 may, for example, first select the expansion method according to the type of obstruction, and then determine the parameters of the selected polar coordinate expansion according to the eye opening degree.

[0130] (Technical Effects) Next, technical effects obtained by the seventh information processing apparatus 10 will be described.

[0131] 21 to 24, in the seventh information processing device 10, the expansion method to be used for polar coordinate expansion is determined based on the degree of eye opening of the subject in the iris image. In this way, it is possible to more appropriately expand the iris image into polar coordinates using an expansion method according to the degree of eye opening (i.e., the size of the area hidden by the eyelid).

[0132] Eighth Embodiment An eighth embodiment will be described with reference to Figures 25 and 26. Note that the eighth embodiment differs from the first to seventh embodiments described above only in part of the configuration and operation, and other parts may be similar to the first and seventh embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0133] (Functional Configuration) First, the functional configuration of the eighth information processing device 10 will be described with reference to Fig. 25. Fig. 25 is a block diagram showing the functional configuration of the eighth information processing device. Note that in Fig. 25, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0134] 25, the eighth information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an expansion method determination unit 120, an expansion unit 170, and an authentication unit 180. That is, the eighth information processing device 10 further includes, in addition to the configuration described in the first embodiment (see FIG. 2), an expansion unit 170 and an authentication unit 180. Each of the expansion unit 170 and the authentication unit 180 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0135] The unfolding unit 170 is configured to be able to unfold the iris region into polar coordinates using the unfolding method determined by the unfolding method determination unit 120. The unfolding unit 170 may have a function of normalizing the unfolded image obtained by polar coordinate unfolding.

[0136] The authentication unit 180 is configured to perform iris authentication using the expanded image obtained by the expanding unit 170 in polar coordinates. For example, the authentication unit 180 is configured with an iris feature extraction model implemented by a neural network. The iris feature extraction model is trained by metric learning using training data consisting of iris images and individual identification labels. In addition to the iris image, the training data may also include iris region information for masking non-iris regions during feature extraction. In this case, the input to the feature extraction model is the iris image with the non-iris region masked. The trained feature extraction model trained by metric learning can extract features from iris images that allow for similarity comparison. For example, when registering an iris image, registered features extracted from the registered iris image using the trained feature extraction model are stored in a dictionary in advance. During authentication, features extracted from the authentication image using the trained feature extraction model are compared with the registered features to calculate the similarity between the iris features. For example, if a high similarity indicates similarity and a low similarity indicates dissimilarity, a certain threshold can be set, and authentication results can be classified as follows: if the similarity is greater than this threshold, it is the actual person, and if the similarity is less than this threshold, it is a different person. The magnitude of the similarity value varies depending on the type of similarity. For example, if the similarity is Euclidean distance, a value closer to 0 is similar, and a value farther from 0 is dissimilar. If the similarity is cosine similarity, a value closer to 1 is similar, and a value closer to -1 is dissimilar. Furthermore, the authentication unit 180 may have a function to perform various subsequent processes depending on the result of iris authentication. For example, the authentication unit 180 may allow the target to pass through the gate if identity verification is successful through iris authentication, and may perform a process to prohibit the target from passing through the gate if identity verification is not successful through iris authentication.

[0137] (Operational Flow) Next, the operational flow of the eighth information processing device 10 will be described with reference to Fig. 26. Fig. 26 is a flowchart showing the operational flow in the eighth information processing device. Note that in Fig. 26, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0138] 26 , when the operation of the eighth information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the unfolding method determination unit 120 determines the unfolding method to be used for unfolding the iris image into polar coordinates based on the obstructing object information in the iris image (step S102).

[0139] Next, the unfolding unit 170 unfolds the iris region into polar coordinates using the unfolding method determined by the unfolding method determination unit 120 (step S801). After that, the authentication unit 180 performs iris authentication using the unfolded image unfolded into polar coordinates by the unfolding unit 170 (step S802).

[0140] (Technical Effects) Next, technical effects obtained by the eighth information processing apparatus 10 will be described.

[0141] 25 and 26 , in the eighth information processing device 10, polar coordinate expansion is performed using the determined expansion method, and iris authentication is performed using the expanded image. The expanded image used for this iris authentication is expanded using the expansion method determined based on the obstructing object information. Therefore, it is possible to perform iris authentication with higher accuracy than when polar coordinate expansion is always performed using the same expansion method.

[0142] Ninth Embodiment A ninth embodiment will be described with reference to Figures 27 and 28. Note that the ninth embodiment differs from the first to eighth embodiments described above only in part of the configuration and operation, and other parts may be similar to the first to eighth embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0143] (Functional Configuration) First, the functional configuration of the ninth information processing device 10 will be described with reference to Fig. 27. Fig. 27 is a block diagram showing the functional configuration of the ninth information processing device. Note that in Fig. 27, the same elements as those shown in Fig. 25 are denoted by the same reference numerals.

[0144] As shown in Fig. 27, the ninth information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an unfolding method determination unit 120, an unfolding unit 170, an authentication unit 180, an extraction unit 190, and a registered image storage unit 200. That is, the ninth information processing device 10 further includes the extraction unit 190 and the registered image storage unit 200 in addition to the components described in the eighth embodiment (see Fig. 25). The extraction unit 190 may be a processing block realized by, for example, the above-mentioned processor 11 (see Fig. 1). The registered image storage unit 200 may be configured by, for example, the above-mentioned storage device 14.

[0145] The extraction unit 190 is configured to extract iris feature quantities from the expanded image expanded in polar coordinates by the expansion unit 170. The extraction unit 190 is also configured to extract iris feature quantities from a pre-registered image. The authentication unit 180 according to this embodiment compares these feature quantities to calculate a similarity, and if the similarity exceeds a certain threshold, authenticates that the registered person and the photographed person are the same person. The extraction unit 190 may be configured by a machine learning model including, for example, a neural network. The learning of the extraction unit 190 will be described in detail in another embodiment described later.

[0146] The registered image storage unit 200 is configured to be able to store iris images of registered users. The registered images stored in the registered image storage unit 200 are read out as needed by the extraction unit 190, and feature amounts are extracted.

[0147] (Operational Flow) Next, the operational flow of the ninth information processing device 10 will be described with reference to Fig. 28. Fig. 28 is a flowchart showing the operational flow in the ninth information processing device. Note that in Fig. 28, the same processes as those shown in Fig. 26 are denoted by the same reference numerals.

[0148] 28 , when the operation of the ninth information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the unfolding method determination unit 120 determines the unfolding method to be used for unfolding the iris image into polar coordinates based on the obstructing object information in the iris image (step S102).

[0149] Next, the unfolding unit 170 unfolds the iris region into polar coordinates using the unfolding method determined by the unfolding method determination unit 120 (step S801). Thereafter, the extraction unit 190 extracts iris-related features from the unfolded image (step S901). The extraction unit 190 also extracts iris-related features from the registered image (step S902). At this time, the extraction unit 190 extracts features according to the unfolding method determined by the unfolding method determination unit 120. For example, if the unfolding method determination unit 120 determines a unfolding method suitable for narrow eyes, the extraction unit 190 extracts features from the registered image using a method corresponding to the unfolding method suitable for narrow eyes. Similarly, if the unfolding method determination unit 120 determines a unfolding method suitable for colored contact lenses, the extraction unit 190 extracts features from the registered image using a method corresponding to the unfolding method suitable for colored contact lenses.

[0150] Next, the authentication unit 180 compares the feature values ​​extracted from the unfolded image with the feature values ​​extracted from the registered image (step S903). Note that the registered image storage unit 200 may store the extracted feature values ​​instead of the registered image. In this case, the registered image storage unit 200 may store a plurality of feature values ​​corresponding to a plurality of unfolding methods. Then, when performing iris authentication, the feature value corresponding to the selected unfolding method may be read out from the plurality of feature values.

[0151] (Technical Effects) Next, technical effects obtained by the ninth information processing apparatus 10 will be described.

[0152] 27 and 28, in the ninth information processing apparatus 10, features are extracted from a registered image using a feature extraction method corresponding to the determined unfolding method. In this way, features suitable for authentication are extracted from the registered image according to the unfolding method, which makes it possible to improve authentication accuracy.

[0153] Tenth Embodiment A tenth embodiment will be described with reference to Figures 29 to 31. The tenth embodiment differs from the first to ninth embodiments described above only in part of the configuration and operation, and other parts may be similar to the first to ninth embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0154] (Functional Configuration) First, the functional configuration of the tenth information processing device 10 will be described with reference to Fig. 29. Fig. 29 is a block diagram showing the functional configuration of the tenth information processing device. Note that in Fig. 29, the same elements as those shown in Fig. 2 and Fig. 27 are denoted by the same reference numerals.

[0155] As shown in Fig. 29 , the tenth information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an unfolding method determination unit 120, an unfolding unit 170, an extraction unit 190, and a learning object 210. That is, the tenth information processing device 10 further includes, in addition to the configuration described in the first embodiment (see Fig. 2 ), the unfolding unit 170, the extraction unit 190, and the learning unit 210. Each of the unfolding unit 170 and the extraction unit 190 may be the same elements as those described in the ninth embodiment (see Fig. 27 ). The learning unit 210 may be a processing block realized by, for example, the above-mentioned processor 11 (see Fig. 1 ).

[0156] The learning unit 210 is configured to be able to learn the extraction unit 190, which is a machine learning model, by inputting training data and executing a learning operation. The learning unit 210 particularly learns the extraction unit 190 by taking into account occluding object information in the iris region. The configuration of the learning unit 210 will be specifically described below with reference to FIG. 30. FIG. 30 is a block diagram showing a functional configuration related to learning of the tenth information processing device. FIG. 30 illustrates excerpts of the components shown in FIG. 29 that are related to learning.

[0157] As shown in FIG. 30 , the learning unit 210 in the tenth information processing device 10 includes, as components for realizing its functions, a loss function calculation unit 211, a gradient calculation unit 212, and a parameter update unit 213.

[0158] The loss function calculation unit 211 is configured to be able to calculate a loss function using the extraction result by the extraction unit 180 and correct answer information (i.e., information indicating the correct answer of the extraction result, which is linked to the input image as training data). The loss function calculated by the loss function calculation unit 211 is configured to be output to the gradient calculation unit 212.

[0159] The gradient calculation unit 212 is configured to be able to calculate a gradient for each parameter of the extraction unit 190 by backpropagation using the loss function calculated by the loss function calculation unit 211. The gradient calculated by the gradient calculation unit 212 is configured to be output to the parameter update unit 213.

[0160] The parameter update unit 213 is configured to be able to update the model parameters of the extraction unit 190, which is a machine learning model, based on the gradient calculated by the gradient calculation unit 212. The parameter update unit 213 may update the model parameters based on a preset learning rate.

[0161] (Flow of Operation) Next, the learning operation of the tenth information processing device 10 (i.e., the operation of the learning unit 210) will be described with reference to Fig. 31. Fig. 31 is a flowchart showing the flow of the learning operation in the tenth information processing device.

[0162] 31 , when the learning operation by the tenth information processing device 10 is started, the information processing device 10 first acquires a training data set to be used for learning (step S1001). An iris image included in the training data is acquired by the iris acquisition unit 110 and unfolded using a unfolding method according to the obstruction.

[0163] Next, the extraction unit 190 randomly acquires mini-batches of training data from the training dataset (step S1002). For example, the extraction unit 190 acquires 128 iris images (unfolded images) as a batch size. Note that the batch size is a preset value, but may be any positive integer value.

[0164] Next, the extraction unit 190 estimates iris information from the iris image (unfolded image) (step S1003). Specifically, the extraction unit 190 extracts a feature vector representing iris characteristics from the iris image. Note that, at the beginning of learning, random values ​​are extracted from this feature vector, but as learning progresses, values ​​with high cosine similarity with the weight vector corresponding to the correct label in the final layer are extracted. Note that, in learning by the extraction unit 190, training data including unfolded images unfolded by a single unfolding method may be used. Alternatively, training data including unfolded images unfolded by multiple types of unfolding methods may be used. In this case, the correct label may be created to have a single ID for the combination of one eye and unfolding method of an individual.

[0165] Next, the loss function calculation unit 211 calculates a loss function based on the extraction result of the extraction unit 180 and the correct answer information (step S1004). Then, the gradient calculation unit 212 calculates a gradient using the loss function (step S1005). Then, the parameter update unit 213 updates the model parameters of the extraction unit based on the gradient (step S1006).

[0166] Next, the learning unit 210 determines whether to terminate learning (step S1007). The learning unit 210 may determine whether to terminate learning based on, for example, whether a predetermined number of iterations has been reached. Alternatively, the learning unit 210 may determine to terminate learning early if the loss value calculated midway stops changing.

[0167] If it is determined not to end the learning (step S1007: NO), the process is repeated from step S1002. In the learning operation, this series of processes is repeated to optimize the model parameters of the extraction unit 190. If it is determined to end the learning (step S1007: YES), the learning unit 210 saves the model parameters of the extraction unit 190 (step S1008).

[0168] (Technical Effects) Next, technical effects obtained by the tenth information processing device 10 will be described.

[0169] 29 to 31 , in the tenth information processing device 10, the extraction unit 190 is trained using images unfolded by an unfolding method according to the obstruction. In this way, it is possible to train the extraction unit 190 so that it can extract appropriate feature amounts according to the obstruction.

[0170] Eleventh Embodiment An eleventh embodiment will be described with reference to Figures 32 and 33. Note that the eleventh embodiment differs from the first to tenth embodiments described above only in part of the configuration and operation, and other parts may be similar to the first to tenth embodiments. Therefore, hereinafter, only the parts that differ from the embodiments already described will be described in detail, and descriptions of other overlapping parts will be omitted as appropriate.

[0171] (Functional Configuration) First, the functional configuration of the eleventh information processing device 10 will be described with reference to Fig. 32. Fig. 32 is a block diagram showing the functional configuration of the eleventh information processing device. Note that in Fig. 32, the same elements as those shown in Fig. 2 and Fig. 27 are denoted by the same reference numerals.

[0172] As shown in Fig. 32 , the eleventh information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an unfolding method determination unit 120, an unfolding unit 170, a plurality of extraction units 190, and a selection unit 220. That is, the eleventh information processing device 10 further includes, in addition to the configuration described in the first embodiment (see Fig. 2 ), an unfolding unit 170, a plurality of extraction units 190, and a selection unit 220. Each of the unfolding unit 170 and the plurality of extraction units 190 may be the same elements as those described in the ninth embodiment (see Fig. 27 ). The selection unit 220 may be a processing block realized by, for example, the above-mentioned processor 11 (see Fig. 1 ).

[0173] The multiple extraction units 190 are configured to be able to extract feature amounts of the iris region in a manner corresponding to the type of obstruction. Each of the multiple extraction units 190 is trained as a model capable of appropriately extracting feature amounts according to, for example, the type of obstruction. For example, the multiple extraction units 190 may include an extraction unit suitable for when there is no obstruction, an extraction unit suitable for fine eyes, and an extraction unit suitable for colored contact lenses. Each of the multiple extraction units 190 may be trained by, for example, the tenth information processing device described above.

[0174] The selection unit 220 is configured to be able to select the extraction unit 190 to actually use from among the multiple extraction units 190. The selection unit 220 selects the extraction unit 190 to use depending on the obstructing object information. For example, the selection unit 220 may select the extraction unit 190 to use depending on the type of obstructing object. Specifically, if the obstructing object is an eyelid with the eyes squinted, the selection unit 220 may select an extraction unit suitable for the squinted eyes. If the obstructing object is colored contact lenses, the selection unit 220 may select an extraction unit suitable for the colored contact lenses.

[0175] (Operational Flow) Next, the operational flow of the eleventh information processing device 10 will be described with reference to Fig. 33. Fig. 33 is a flowchart showing the operational flow in the eleventh information processing device. Note that in Fig. 33, the same processes as those shown in Fig. 26 are denoted by the same reference numerals.

[0176] 33 , when the operation of the eleventh information processing apparatus 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the unfolding method determination unit 120 determines the unfolding method to be used for unfolding the iris image into polar coordinates based on the obstructing object information in the iris image (step S102).

[0177] Next, the unfolding unit 170 unfolds the iris region into polar coordinates using the unfolding method determined by the unfolding method determination unit 120 (step S801). After that, the selection unit 220 selects an extraction unit 190 based on the obstructing object information (step S1101). Then, the extraction unit 190 selected by the selection unit 220 extracts iris-related features from the unfolded image (step S1102).

[0178] (Technical Effects) Next, technical effects obtained by the eleventh information processing device 10 will be described.

[0179] 32 and 33 , in the eleventh information processing apparatus 10, the extraction unit 190 to be used is selected based on the obstructing object information. In this way, a feature amount can be extracted using a more appropriate extraction unit 190 depending on the obstructing object. Therefore, it is possible to improve the accuracy of iris authentication using the extracted feature amount, for example.

[0180] <Twelfth Embodiment> A twelfth embodiment will be described with reference to Fig. 34. Note that the twelfth embodiment differs from the above-described tenth embodiment only in some configurations, and other portions may be similar to the tenth embodiment. Therefore, the following will describe in detail the portions that differ from the embodiments already described, and will omit descriptions of other overlapping portions as appropriate.

[0181] (Functional Configuration) First, the functional configuration of the twelfth information processing device 10 will be described with reference to Fig. 34. Fig. 34 is a block diagram showing the functional configuration of the twelfth information processing device. Note that in Fig. 34, the same elements as those shown in Fig. 29 are denoted by the same reference numerals.

[0182] 34, the twelfth information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, an extraction unit 190, and a learning unit 210. Each of the iris acquisition unit 110, the extraction unit 190, and the learning unit 210 may be the same elements as those described in the tenth embodiment (see FIG. 29).

[0183] The iris acquisition unit 110 in the twelfth information processing device 10 is configured to be able to acquire training data to be used for learning. The extraction unit 190 is configured to be able to extract iris-related features from the training data acquired by the iris acquisition unit 110. The learning unit 210 is configured to be able to execute learning of the extraction unit 190 using the extraction results of the extraction unit 190. Specifically, the learning unit 210 trains the extraction unit 190 so that it can extract features suitable for the obstructing object information. For example, the learning unit 210 trains the extraction unit 190 so that it can extract features specialized for each type of obstructing object.

[0184] The specific processing of the learning operation by the learning unit 210 is the same as that in the tenth embodiment (see FIG. 31) already described, and therefore a detailed description thereof will be omitted here.

[0185] (Technical Effects) Next, technical effects obtained by the twelfth information processing device 10 will be described.

[0186] 34, in the twelfth information processing device 10, the extraction unit 190 is trained based on the obstructing object information. In this way, it is possible to train the extraction unit 190 so that it can extract appropriate feature amounts depending on the obstructing object.

[0187] 13th Embodiment A 13th embodiment will be described with reference to Figures 35 and 36. Note that the 13th embodiment differs from the above-described 11th embodiment only in some configurations and operations, and other parts may be similar to the 11th embodiment. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0188] (Functional Configuration) First, the functional configuration of the thirteenth information processing device 10 will be described with reference to Fig. 35. Fig. 35 is a block diagram showing the functional configuration of the thirteenth information processing device. Note that in Fig. 35, the same elements as those shown in Fig. 32 are denoted by the same reference numerals.

[0189] 35, the thirteenth information processing device 10 is configured to include, as components for realizing its functions, an iris acquisition unit 110, a plurality of extraction units 190, and a selection unit 220. Each of the iris acquisition unit 110, the plurality of extraction units 190, and the selection unit 220 may be the same elements as those described in the eleventh embodiment (see FIG. 32).

[0190] The iris acquisition unit 110 in the thirteenth information processing device 10 is configured to be able to acquire an iris image including the iris of a target. The plurality of extraction units 190 are trained to be able to extract iris feature amounts according to obstructions. The selection unit 220 is configured to be able to select an extraction unit 190 to use from the plurality of extraction units 190 based on obstruction information in the iris image.

[0191] (Operational Flow) Next, the operational flow of the thirteenth information processing device 10 will be described with reference to Fig. 36. Fig. 36 is a flowchart showing the operational flow in the thirteenth information processing device. Note that in Fig. 36, the same processes as those shown in Fig. 33 are denoted by the same reference numerals.

[0192] 36 , when the operation of the thirteenth information processing device 10 is started, the iris acquisition unit 110 first acquires an iris image including a target iris region (step S101). Then, the selection unit 220 selects an extraction unit 190 to be used from the plurality of extraction units 190 based on the obstructing object information (step S1101).

[0193] Next, the extraction unit 190 selected by the selection unit 220 extracts iris-related feature amounts from the iris image (step S1102).

[0194] (Technical Effects) Next, technical effects obtained by the thirteenth information processing device 10 will be described.

[0195] 35 and 36 , in the thirteenth information processing apparatus 10, the extraction unit 190 to be used is selected based on the obstructing object information. In this way, a feature amount can be extracted using a more appropriate extraction unit 190 depending on the obstructing object. Therefore, it is possible to improve the accuracy of iris authentication using the extracted feature amount, for example.

[0196] The scope of each embodiment also includes a processing method in which a program that operates the configuration of each embodiment to realize the functions of the above-described embodiments is recorded on a recording medium, the program recorded on the recording medium is read as code, and the program is executed on a computer. In other words, a computer-readable recording medium is also included in the scope of each embodiment. Furthermore, each embodiment includes not only a recording medium on which the above-described program is recorded, but also the program itself.

[0197] Examples of recording media that can be used include floppy disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, magnetic tapes, non-volatile memory cards, and ROMs. Furthermore, the scope of each embodiment is not limited to programs that execute processes by themselves, but also includes programs that execute processes by operating on an OS in conjunction with other software or expansion board functions. Furthermore, the program itself may be stored on a server, and part or all of the program may be downloadable from the server to a user terminal. The program may be provided to the user in, for example, a SaaS (Software as a Service) format.

[0198] <Supplementary Notes> The above-described embodiment may be further described as in the following supplementary notes, but is not limited to the following.

[0199] (Supplementary Note 1) The information processing device described in Supplementary Note 1 is an information processing device that includes an acquisition means that acquires an image including an iris region of a target, and a determination means that determines an expansion method to be used for polar coordinate expansion of the iris region based on obstruction information regarding an obstruction that obstructs the iris region.

[0200] (Supplementary Note 2) The information processing device described in Supplementary Note 2 is the information processing device described in Supplementary Note 1, further comprising a presence / absence determination means for determining the presence or absence of the obstruction, and the determination means determines the expansion method to be used for polar coordinate expansion of the iris region based on the presence or absence of the obstruction as the obstruction information.

[0201] (Supplementary Note 3) The information processing device described in Supplementary Note 3 is the information processing device described in Supplementary Note 2, further comprising a type determination means for determining the type of the obstructing object when it is determined that the obstructing object is present, and the determination means determines an expansion method to be used for expanding the iris region into polar coordinates based on the type of the obstructing object as the obstructing object information.

[0202] (Supplementary Note 4) The information processing device described in Supplementary Note 4 is the information processing device described in any one of Supplements 1 to 3, wherein the determining means determines a method of using polar coordinate expansion of the iris region so as to cut out a partial region of the iris region having a predetermined angle that is not hidden by the eyelid when the obstructing object is an eyelid.

[0203] (Supplementary Note 5) The information processing device described in Supplementary Note 5 is the information processing device described in any one of Supplements 1 to 4, wherein the determining means determines a method of using a polar coordinate expansion of the iris region so as to extract the portion of the iris region around the pupil circle that is not hidden by the color contact lens when the occluding object is a color contact lens.

[0204] (Supplementary Note 6) The information processing device described in Supplementary Note 6 is the information processing device described in any one of Supplements 1 to 5, further including an occlusion amount estimation means for estimating an amount of occlusion by the occluding object in the iris region, and the determination means determines an expansion method to be used for polar coordinate expansion of the iris region based on the occlusion amount as the occlusion object information.

[0205] (Appendix 7) The information processing device described in Appendix 7 is the information processing device described in any one of Appendices 1 to 6, further comprising an eye opening degree estimation means for estimating an eye opening degree indicating the degree of opening of the subject's eyes, and the determination means determines an unfolding method to be used for polar coordinate unfolding of the iris region based on the eye opening degree as the obstruction information.

[0206] (Appendix 8) The information processing device described in Appendix 8 is the information processing device described in any one of Appendices 1 to 7, further comprising: an expansion means that performs polar coordinate expansion of the iris area using the expansion method determined by the determination means and generates an expanded image of the iris area; and an authentication means that performs iris authentication of the target using the expanded image.

[0207] (Appendix 9) The information processing device described in Appendix 9 is the information processing device described in Appendix 8, further comprising an extraction means for extracting features of the iris region, and the authentication means performs iris authentication of the target by comparing the features extracted from the unfolded image with features extracted from a pre-registered image according to the unfolding method determined by the determination means.

[0208] (Supplementary Note 10) The information processing device described in Supplementary Note 10 is the information processing device described in any one of Supplementary Notes 1 to 9, further including an extraction means for extracting features of the iris region, and a learning means for learning the extraction means in accordance with the obstructing object information.

[0209] (Supplementary Note 11) The information processing device described in Supplementary Note 11 is the information processing device described in any one of Supplements 1 to 10, further including a plurality of extraction means for extracting features of the iris region in a manner according to the obstructing object, and a selection means for selecting an extraction means to use from the plurality of extraction means according to the obstructing object information.

[0210] (Supplementary Note 12) The information processing device described in Supplementary Note 12 is an information processing device that includes an acquisition means that acquires an image including an iris region of a target, an extraction means that extracts features of the iris region, and a learning means that learns the extraction means in accordance with obstructing object information regarding an obstructing object that obstructs the iris region.

[0211] (Supplementary Note 13) The information processing device described in Supplementary Note 13 is an information processing device that includes an acquisition means that acquires an image including an iris region of a target, a plurality of extraction means that extract features of the iris region in a manner according to an obstruction that obstructs the iris region, and a selection means that selects an extraction means to be used from the plurality of extraction means according to obstruction information regarding the obstruction.

[0212] (Supplementary Note 14) The information processing method described in Supplementary Note 14 is an information processing method in which an image including an iris region of a target is acquired by at least one computer, and an expansion method to be used for expanding the iris region into polar coordinates is determined based on occluding object information regarding an occluding object that occludes the iris region.

[0213] (Supplementary Note 15) The recording medium described in Supplementary Note 15 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method for acquiring an image including an iris region of a target, and determining an unfolding method to be used for unfolding the iris region in polar coordinates based on obstruction information regarding an obstruction that obstructs the iris region.

[0214] (Supplementary Note 16) The computer program described in Supplementary Note 16 is a computer program that causes at least one computer to execute an information processing method that acquires an image including an iris region of a target, and determines an unfolding method to be used for unfolding the iris region in polar coordinates based on occlusion information regarding an object that occludes the iris region.

[0215] (Supplementary Note 17) The information processing method described in Supplementary Note 17 is an information processing method that, by at least one computer, acquires an image including an iris region of a target, extracts features of the iris region, and trains the extraction means according to obstructing object information regarding an obstructing object that obstructs the iris region.

[0216] (Supplementary Note 18) The recording medium described in Supplementary Note 15 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring an image including an iris region of a target, extracting features of the iris region, and training the extraction means in accordance with obstructing object information relating to an obstructing object that obstructs the iris region.

[0217] (Supplementary Note 19) The computer program described in Supplementary Note 16 is a computer program that causes at least one computer to execute an information processing method, which acquires an image including an iris region of a target, extracts features of the iris region, and trains the extraction means according to obstructing object information regarding an obstructing object that obstructs the iris region.

[0218] (Supplementary Note 20) The information processing method described in Supplementary Note 21 is an information processing method that acquires an image including an iris region of a target by at least one computer, extracts features of the iris region using a plurality of extraction means in a manner according to an obstructing object that obstructs the iris region, and selects an extraction means to be used from the plurality of extraction means according to obstructing object information related to the obstructing object.

[0219] (Supplementary Note 21) The recording medium described in Supplementary Note 21 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring an image including an iris region of a target, extracting features of the iris region using a plurality of extraction means in a manner according to an obstructing object that obstructs the iris region, and selecting an extraction means to be used from the plurality of extraction means according to obstructing object information related to the obstructing object.

[0220] (Supplementary Note 22) The computer program described in Supplementary Note 22 is a computer program that causes at least one computer to execute an information processing method, which acquires an image including an iris region of a target, extracts features of the iris region using a plurality of extraction means in a manner according to an obstructing object that obstructs the iris region, and selects an extraction means to be used from the plurality of extraction means according to obstructing object information related to the obstructing object.

[0221] This disclosure may be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0222] REFERENCE SIGNS LIST 10 Information processing device 11 Processor 51 Iris 52 Pupil 110 Iris acquisition unit 120 Expansion method determination unit 130 Obstruction presence / absence determination unit 140 Obstruction type determination unit 150 Obstruction amount estimation unit 160 Eye opening degree estimation unit 170 Expansion unit 180 Authentication unit 190 Extraction unit 200 Registered image storage unit 210 Learning unit 211 Loss function calculation unit 212 Gradient calculation unit 213 Parameter update unit 220 Selection unit

Claims

1. An information processing device comprising: an acquisition means for acquiring an image including an iris region of a target; and a determination means for determining a development method to be used for polar coordinate development of the iris region based on obstruction information regarding an obstruction that obstructs the iris region.

2. The information processing device according to claim 1, further comprising a presence / absence determination means for determining the presence or absence of the obstruction, wherein the determination means determines a development method to be used for the polar coordinate development of the iris region based on the presence or absence of the obstruction as the obstruction information.

3. The information processing device according to claim 2, further comprising a type determination means for determining the type of the obstructing object when it is determined that the obstructing object is present, and the determination means determines the expansion method to be used for expanding the iris region into polar coordinates based on the type of the obstructing object as the obstructing object information.

4. An information processing device as described in claim 1 or 3, wherein the determination means determines a method of using polar coordinate expansion of the iris region so as to extract a partial region of the iris region having a specified angle that is not hidden by the eyelid when the obstructing object is an eyelid.

5. An information processing device as described in claim 1 or 3, wherein the determination means determines a method of using a polar coordinate expansion of the iris region so as to extract the portion of the iris region surrounding the pupil circle that is not hidden by the color contact lens when the occluding object is a color contact lens.

6. The information processing device according to claim 1, further comprising an occlusion amount estimation means for estimating an amount of occlusion by the obstructing object in the iris region, wherein the determination means determines a development method to be used for polar coordinate development of the iris region based on the amount of occlusion as the obstructing object information.

7. The information processing device of claim 1, further comprising an eye opening degree estimation means for estimating an eye opening degree indicating the degree to which the subject's eyes are open, wherein the determination means determines a development method to be used for polar coordinate development of the iris area based on the eye opening degree as the obstruction information.

8. The information processing device according to claim 1, further comprising: an expansion means for performing polar coordinate expansion of the iris area using the expansion method determined by the determination means, and generating an expanded image of the iris area; and an authentication means for performing iris authentication of the subject using the expanded image.

9. An information processing device as described in claim 8, further comprising an extraction means for extracting features of the iris area, wherein the authentication means performs iris authentication of the target by comparing the features extracted from the unfolded image with features extracted from a pre-registered image according to the unfolding method determined by the determination means.

10. The information processing device according to claim 1, further comprising: an extraction means for extracting features of the iris region; and a learning means for learning the extraction means in accordance with the obstructing object information.

11. The information processing device according to claim 1, further comprising: a plurality of extraction means for extracting features of the iris region in a manner according to the obstruction; and a selection means for selecting an extraction means to be used from the plurality of extraction means according to the obstruction information.

12. An information processing device comprising: an acquisition means for acquiring an image including an iris region of a target; an extraction means for extracting features of the iris region; and a learning means for learning the extraction means in accordance with obstruction information regarding an obstruction that obstructs the iris region.

13. An information processing device comprising: an acquisition means for acquiring an image including an iris region of a target; a plurality of extraction means for extracting features of the iris region in a manner according to an obstruction that obstructs the iris region; and a selection means for selecting an extraction means to be used from the plurality of extraction means according to obstruction information relating to the obstruction.

14. An information processing method, comprising: acquiring an image including an iris region of a target by at least one computer; and determining an expansion method to be used for expanding the iris region into polar coordinates based on occluding object information regarding an occluding object that occludes the iris region.

15. A recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which comprises acquiring an image including an iris region of a target, and determining a development method to be used for polar coordinate development of the iris region based on occluding object information regarding an object that occludes the iris region.

Images