Information processing device, information processing method, and information processing program

Abstract

To perform appropriate mosaic processing according to the size of each face area of ​​a plurality of people included in an image. [Solution] The information processing device of the present application comprises a detection unit that detects each of a plurality of facial regions including the faces of a plurality of persons from an image; a judgment unit that judges whether the size of a first reduced facial image, which is an image of the facial region reduced at a predetermined reduction rate, is equal to or greater than a lower limit size and equal to or less than an upper limit size; and a generation unit that, if the judgment unit judges that the size of the first reduced facial image is below the lower limit size, resizes the size of the first reduced facial image to the lower limit size; if the judgment unit judges that the size of the first reduced facial image is above the upper limit size, resizes the size of the first reduced facial image to the upper limit size, and generates a first enlarged facial image by enlarging the resized first reduced facial image to the size of the original image of the facial region.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known techniques for deleting personal information that appears in an image, such as a technique for detecting a person area, which is an area in an image captured by a camera device where a person is captured, and performing privacy processing on the person area with varying strength depending on a depth associated with the coordinates of the person area or a predetermined index related to the depth. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-114821 Summary of the Invention [Means for solving the problem]

[0004] The information processing device of the present application includes a detection unit that detects each of a plurality of facial regions including the faces of a plurality of persons from an image; a determination unit that determines whether a size of a first reduced facial image, which is an image of the facial region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size; and a generation unit that, if the determination unit determines that the size of the first reduced facial image is below the lower limit size, resizes the size of the first reduced facial image to the lower limit size, if the determination unit determines that the size of the first reduced facial image is above the upper limit size, resizes the size of the first reduced facial image to the upper limit size, and generates a first enlarged facial image by enlarging the resized first reduced facial image to the size of the original image of the facial region.

[0005] In addition, the information processing device of the present application includes a detection unit that detects each of a plurality of facial regions including the faces of each of a plurality of persons from an image; a generation unit that generates a plurality of enlarged facial images by enlarging each of a plurality of reduced facial images, which are images of the facial regions reduced to each of a plurality of predetermined sizes, to the size of the original image of the facial region; a determination unit that determines whether the similarity between the image features of each of the plurality of enlarged facial images and the image features of the original image of the facial region exceeds a predetermined similarity; and an acquisition unit that, when the determination unit determines that the similarity exceeds the predetermined similarity, acquires the enlarged facial image corresponding to the predetermined size whose similarity is determined to exceed the predetermined similarity as a mosaic image. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing an image on which mosaic processing according to the first comparative technique has been performed. [Figure 2] FIG. 2 is a diagram showing an image on which mosaic processing according to the second comparative technique has been performed. [Figure 3] FIG. 3 is a diagram showing an image on which the mosaic process according to the first embodiment has been performed. [Figure 4] FIG. 4 is a diagram for explaining an overview of the mosaic processing. [Figure 5] FIG. 5 is a diagram for explaining the reduction process (pattern 1) of the mosaic process. [Figure 6] FIG. 6 is a diagram for explaining the reduction process (pattern 2) of the mosaic process. [Figure 7] FIG. 7 is a diagram for explaining a case where a lower limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of the mosaic process. [Figure 8] FIG. 8 is a diagram for explaining the setting of the lower limit value of the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment. [Figure 9] FIG. 9 is a diagram for explaining a case where an upper limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of the mosaic process. [Figure 10] FIG. 10 is a diagram for explaining setting of the upper limit value of the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of the configuration of an information processing system according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of the configuration of an information processing device according to the first embodiment. [Figure 13] FIG. 13 is a flowchart illustrating an example of a processing procedure of the information processing device according to the first embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of the configuration of an information processing device according to the second embodiment. [Figure 15] FIG. 15 is a diagram illustrating an outline of the processing of the information processing device according to the second embodiment. [Figure 16] FIG. 16 is a diagram illustrating an outline of the processing of the information processing device according to the second embodiment. [Figure 17] FIG. 17 is a flowchart illustrating an example of a processing procedure of the information processing device according to the second embodiment. [Figure 18] FIG. 18 is a flowchart illustrating an example of a processing procedure of the information processing device according to the second embodiment. [Figure 19] FIG. 19 is a diagram illustrating an example of the configuration of an information processing device according to the third embodiment. [Figure 20] FIG. 20 is a flowchart illustrating an example of a processing procedure of the information processing device according to the third embodiment. [Figure 21] FIG. 21 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0008] 1. Introduction First, the background that led the inventors to create the first embodiment will be described with reference to FIGS.

[0009] Generally, when mosaicing an image containing a person, it is desirable to perform mosaicing with an appropriate strength so that the person in the image cannot be identified as a specific person, and the face of the person in the image can be recognized as a human face. On the other hand, if mosaicing is performed with a uniform mosaicing strength on an image containing multiple people, the mosaicing strength may be too strong, causing the face to be blurred, or the mosaicing strength may be too weak, making it impossible to remove personal information. This point will be explained using Figures 1 to 3.

[0010] 1 to 3 show images G11 to G13 that show three people U1 to U3. In FIGS. 1 to 3, person U1 is located at the forefront of the space shown in the image. In other words, person U1 appears at the forefront of the image. Also, person U3 is located at the back of the space shown in the image. In other words, person U3 appears at the back of the image. Also, person U2 is located in the space between person U1 and person U3. In other words, person U2 appears behind person U1 (in front of person U3).

[0011] FIG. 1 illustrates an image on which mosaicing according to the first comparative technique has been performed. FIG. 1 shows an image G11 on which strong mosaicing has been performed uniformly to remove personal information of person U1, who appears in the foreground of the image. In FIG. 1, the facial region of person U1, who appears in the foreground of the image, has been subjected to mosaicing with an appropriate strength according to the size of the facial region. Therefore, in FIG. 1, person U1's face can be recognized as a human face, and the personal information of person U1 has been successfully removed so that person U1's face is not recognized as the face of a specific person. However, in FIG. 1, facial regions M12 and M13 of persons U2 and U3, who appear in the background of the image, have been subjected to strong (i.e., coarse) mosaicing that is inappropriate for the size of facial regions M12 and M13, respectively. Therefore, in FIG. 1, the faces of persons U2 and U3, who appear in the background of the image, are blurred. In other words, in FIG. 1, the faces of persons U2 and U3, who appear in the background of the image, cannot be recognized as human faces.

[0012] FIG. 2 shows an image on which mosaicing according to the second comparative technique has been performed. FIG. 2 shows an image G12 on which a uniformly weak mosaicing process has been performed on the image so that the faces of persons U2 and U3 in the background of the image can be recognized as human faces, but the faces of persons U2 and U3 are not recognized as the faces of a specific person. In FIG. 2, the facial regions of persons U2 and U3 in the background of the image have been subjected to mosaicing with an appropriate strength according to the size of the facial regions. Therefore, in FIG. 2, the faces of persons U2 and U3 can be recognized as human faces, and personal information of persons U2 and U3 has been successfully removed so that the faces of persons U2 and U3 are not recognized as the faces of a specific person. However, in FIG. 2, the facial region M21 of person U1 in the foreground of the image has been subjected to a weak (i.e., smooth) mosaicing process that is inappropriate for the size of the facial region M21. Therefore, in FIG. 2, the face of person U1 in the foreground of the image can be recognized as the face of a specific person. In other words, in FIG. 2, the personal information of the person U1 in the foreground cannot be deleted.

[0013] FIG. 3 is a diagram showing an image obtained by performing mosaic processing according to the first embodiment. The mosaic processing according to the first embodiment is performed by the information processing device 100 according to the first embodiment. FIG. 3 shows an image G13 obtained by performing mosaic processing by the information processing device 100 with appropriate strengths according to the sizes of the facial regions M31 to M33 of the persons U1 to U3. In FIG. 3, the information processing device 100 performs strong mosaic processing on the facial region M31 of the person U1, who appears in the foreground of the image. As a result, the information processing device 100 is able to recognize the face of the person U1 in the foreground as a human face and successfully deletes the personal information of the person U1. Furthermore, the information processing device 100 performs weaker mosaic processing on the facial regions M32 and M33 of the persons U2 and U3, who appear in the background of the image, than on the facial region M31 of the person U1. As a result, the information processing device 100 is able to recognize the faces of the persons U2 and U3 in the background of the image as human faces and successfully deletes the personal information of the persons U2 and U3.

[0014] FIG. 4 is a diagram for explaining an overview of mosaic processing. FIG. 4 explains an overview of general mosaic processing for a face region of a person detected from an image. Generally, mosaic processing for a face region of a person is performed by reducing the image of the face region (Step 1) and enlarging the reduced image to the size of the image of the original face region (Step 2). For example, the information processing device 100 acquires an image G21 of a face region of a person included in an image. Next, the information processing device 100 generates a reduced face image G22 by reducing the image G21 of the face region of the person (Step 1: reduction processing). Next, the information processing device 100 generates an enlarged face image G23 by enlarging the reduced face image G22 to the size of the image G21 of the original face region (Step 2: enlargement processing). In this way, the information processing device 100 acquires the enlarged face image G23 as an image obtained by performing mosaic processing on the image G21 of the face region (hereinafter referred to as a mosaic image).

[0015] FIG. 5 is a diagram illustrating the reduction process (pattern 1) of the mosaic process. FIG. 5 illustrates an example of the reduction process of the mosaic process described in FIG. 4. In FIG. 5, the information processing device 100 reduces the image G31 of the person's face region to a predetermined size. Note that, hereinafter, the original image of the person's face region may be referred to as an input face image. In other words, the information processing device 100 generates a reduced face image G32 by reducing the image G31 of the person's face region to a predetermined size. In other words, the information processing device 100 generates a reduced face image G32 by reducing the image G31 of the person's face region to a predetermined width and height. For example, the information processing device 100 generates a reduced face image G32 by reducing the image G31 of the person's face region to a predetermined width and height of 30 pixels by 40 pixels in height. Note that 30 pixels in width and 40 pixels in height are an example of the predetermined width and height, and the predetermined width and height are not limited to 30 pixels in width and 40 pixels in height. For example, the predetermined width and height may be greater than 30 pixels wide by 40 pixels high, or may be less than 30 pixels wide by 40 pixels high.

[0016] FIG. 6 is a diagram illustrating a reduction process (pattern 2) of mosaic processing. FIG. 6 illustrates an example of the reduction process of mosaic processing described in FIG. 4 that is different from FIG. 5. In FIG. 6, the information processing device 100 reduces the image G33 of the person's face region at a fixed reduction rate relative to the size of the input face image. In other words, the information processing device 100 generates a reduced face image G34 by reducing the image G33 of the person's face region at a fixed reduction rate relative to the size of the input face image. For example, the information processing device 100 reduces the image G33 of the person's face region, which is 260 pixels wide and 300 pixels high, by 0.5 times to generate a reduced face image G34 of 130 pixels wide and 150 pixels high. Note that 0.5 times is an example of a fixed reduction rate, and the fixed reduction rate is not limited to 0.5 times. For example, the fixed reduction rate may be greater than 0.5 times or less than 0.5 times.

[0017] As described with reference to FIGS. 5 and 6, there are two types of reduction processes in mosaic processing: a reduction process (pattern 1) that reduces an input face image to a predetermined size, and a reduction process (pattern 2) that reduces the input face image at a fixed reduction rate. Here, in the case of reduction process using pattern 1, if the size of the input face image is large, the size of the reduced face image reduced to the size of the input face image becomes significantly smaller relative to the size of the input face image. Therefore, when the reduced face image reduced using reduction process using pattern 1 is enlarged to the size of the input face image, the reduced face image is significantly stretched relative to the size of the reduced face image. Furthermore, if an enlarged face image is generated in which the reduced face image is significantly stretched relative to the size of the reduced face image, a strong (i.e., coarse) mosaic process that is not suitable for the size of the input face image is performed. Therefore, in the case of reduction process using pattern 1, depending on the size of the input face image, a strong (i.e., coarse) mosaic process that is not suitable for the size of the input face image is performed. In contrast, in the case of reduction processing of pattern 2, since the input face image is reduced at a constant reduction rate relative to its size, it is difficult to perform strong (i.e., coarse) mosaic processing that is not suitable for the size of the input face image, compared to reduction processing of pattern 1. For this reason, the mosaic processing according to the first embodiment is based on logic of reduction processing (pattern 2) that reduces the input face image at a constant reduction rate relative to its size.

[0018] As described above, the mosaic processing according to the first embodiment is based on a logic of a reduction process (pattern 2) that reduces the input face image at a fixed reduction rate. However, in the reduction process (pattern 2) that reduces the input face image at a fixed reduction rate, if no lower limit is set for the size of the reduced face image obtained by reducing the input face image, a strong (i.e., coarse) mosaic processing that is not suitable for the size of the input face image may be performed. Furthermore, as a result of a strong (i.e., coarse) mosaic processing that is not suitable for the size of the input face image, it may become impossible to recognize the face in the face image (enlarged face image) that has undergone the mosaic processing as a human face.

[0019] Using Fig. 7, a case where a lower limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of mosaic processing will be described. Fig. 7 is a diagram for explaining a case where a lower limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of mosaic processing. Fig. 7 shows an input face image G41 having a width of 138 pixels and a height of 153 pixels. Also shown is a reduced face image G42 having a width of 4 pixels and a height of 4 pixels obtained by reducing the input face image G41 at a fixed reduction ratio of 0.03. Also shown is an enlarged face image G43 obtained by enlarging the reduced face image G42 to the size of the input face image G41 having a width of 138 pixels and a height of 153 pixels.

[0020] In FIG. 7, since no lower limit is set for the size of the reduced face image, the size of the reduced face image G42 is relatively small (for example, less than 10 pixels in width or less than 10 pixels in height). Therefore, when the reduced face image G42 is enlarged to the size of the input face image G41, an enlarged face image G43 is generated in which the reduced face image G42 is greatly enlarged. Furthermore, when the enlarged face image G43 is generated in which the reduced face image G42 is greatly enlarged, a strong (i.e., coarse) mosaic process that is not suitable for the size of the input face image is executed. For this reason, in the reduction process (pattern 2) in which the input face image is reduced at a fixed reduction rate, it is desirable to set a lower limit for the size of the reduced face image obtained by reducing the input face image.

[0021] Setting of a lower limit value for the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment will be described with reference to FIG. 8. FIG. 8 is a diagram for describing setting of a lower limit value for the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment. In FIG. 8, the information processing device 100 acquires an input face image G51 having a width of 138 pixels and a height of 153 pixels. The information processing device 100 also determines whether the size of a reduced face image obtained by reducing the input face image G51 at a fixed reduction ratio of 0.03 is equal to or greater than the lower limit size. In FIG. 8, the lower limit size is 20 pixels in width and 20 pixels in height. Note that 20 pixels in width and 20 pixels in height are an example of the lower limit size, and the lower limit size is not limited to 20 pixels in width and 20 pixels in height. For example, the lower limit size may be larger or smaller than 20 pixels in width and 20 pixels in height.

[0022] In FIG. 8, the information processing device 100 determines that the size of a reduced face image obtained by reducing the input face image G51 by a fixed reduction ratio of 0.03 times is below the lower limit size. Furthermore, when the information processing device 100 determines that the size of the reduced face image is below the lower limit size, it resizes the size of the reduced face image to the lower limit size. Specifically, when the information processing device 100 determines that the size of the reduced face image is below the lower limit size, it reduces the size of the input face image G51 to the lower limit size. In other words, the information processing device 100 generates a reduced face image G52 by reducing the size of the input face image G51 to the lower limit size. Subsequently, the information processing device 100 generates an enlarged face image G53 by enlarging the reduced face image G52 to the size of the input face image G51.

[0023] 8, the information processing device 100 sets a lower limit on the size of the reduced face image, thereby preventing the size of the reduced face image G52 from becoming relatively very small (for example, less than 10 pixels in width or less than 10 pixels in height). In other words, the information processing device 100 sets a lower limit on the size of the reduced face image, thereby enabling the size of the reduced face image G52, which has been reduced relative to the size of the input face image G51, to be reduced to an appropriate size (for example, 10 pixels in width or more and 10 pixels in height or more). Therefore, when the information processing device 100 enlarges the reduced face image G52 to the size of the input face image G51, it can prevent the generation of an enlarged face image G53 in which the reduced face image G52 is greatly enlarged relative to the size of the reduced face image G52. In other words, the information processing device 100 can generate an enlarged face image G53 in which the reduced face image G52 is enlarged to a size appropriate relative to the size of the reduced face image G52. Furthermore, the information processing device 100 can prevent the generation of an enlarged face image G53 in which the reduced face image G52 is enlarged significantly relative to the size of the reduced face image G52, and therefore can prevent the execution of a mosaic process with a high intensity (i.e., a coarse intensity) that is inappropriate for the size of the input face image. In other words, the information processing device 100 can generate an enlarged face image G53 in which the reduced face image G52 is enlarged to a size appropriate for the size of the reduced face image G52, and therefore can execute a mosaic process with an appropriate intensity that is appropriate for the size of the input face image.

[0024] As described above, the mosaic processing according to the first embodiment is based on a logic of reduction processing (pattern 2) that reduces the size of an input face image at a fixed reduction rate. As described above, the mosaic processing according to the first embodiment sets a lower limit for the size of the reduced face image. However, unless an upper limit is set for the size of the reduced face image obtained by reducing the input face image, a weak (i.e., smooth) mosaic processing that is not suitable for the size of the input face image is executed. Furthermore, as a result of executing a weak (i.e., smooth) mosaic processing that is not suitable for the size of the input face image, the face in the face image (enlarged face image) that has undergone mosaic processing may be recognized as the face of a specific person (i.e., personal information cannot be deleted).

[0025] Using Fig. 9, a case will be described in which an upper limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of mosaic processing. Fig. 9 is a diagram for explaining a case in which an upper limit value for the size of a reduced face image is not set in the reduction process (pattern 2) of mosaic processing. Fig. 9 shows an input face image G61 having a width of 2295 pixels and a height of 3236 pixels. Fig. 9 also shows a reduced face image G62 having a width of 69 pixels and a height of 97 pixels obtained by reducing the input face image G61 at a fixed reduction ratio of 0.03. Fig. 9 also shows an enlarged face image G63 obtained by enlarging the reduced face image G62 to the size of the input face image G61, which is 2295 pixels in width and 3236 pixels in height.

[0026] In FIG. 9, since no upper limit is set for the size of the reduced face image, the size of the reduced face image G62 is relatively large (for example, 50 pixels or more in width or 50 pixels or more in height). Therefore, when the reduced face image G62 is enlarged to the size of the input face image G61, an enlarged face image G63 is generated by smoothly enlarging the reduced face image G62. Furthermore, when the enlarged face image G63 is generated by smoothly enlarging the reduced face image G62, a weak (i.e., smooth) mosaic process that is not suitable for the size of the input face image is executed. For this reason, in the reduction process (pattern 2) that reduces the input face image at a fixed reduction rate, it is desirable to set an upper limit for the size of the reduced face image obtained by reducing the input face image.

[0027] Setting of an upper limit value for the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment will be described with reference to FIG. 10 . FIG. 10 is a diagram for describing setting of an upper limit value for the size of a reduced face image in the reduction process (pattern 2) of the mosaic process according to the first embodiment. In FIG. 10 , the information processing device 100 acquires an input face image G71 having a width of 2295 pixels and a height of 3236 pixels. The information processing device 100 also determines whether the size of a reduced face image obtained by reducing the input face image G71 at a fixed reduction ratio of 0.03 is equal to or smaller than the upper limit size. In FIG. 10 , the upper limit size is 30 pixels in width and 30 pixels in height. Note that 30 pixels in width and 30 pixels in height are an example of the upper limit size, and the upper limit size is not limited to 30 pixels in width and 30 pixels in height. For example, the upper limit size may be larger or smaller than 30 pixels in width and 30 pixels in height.

[0028] In FIG. 10, the information processing device 100 determines that the size of a reduced face image obtained by reducing the input face image G71 at a fixed reduction rate of 0.03 exceeds the upper limit size. Furthermore, when the information processing device 100 determines that the size of the reduced face image exceeds the upper limit size, it resizes the size of the reduced face image to the upper limit size. Specifically, when the information processing device 100 determines that the size of the reduced face image exceeds the upper limit size, it reduces the size of the input face image G71 to the upper limit size. In other words, the information processing device 100 generates a reduced face image G72 by reducing the size of the input face image G71 to the upper limit size. Subsequently, the information processing device 100 generates an enlarged face image G73 by enlarging the reduced face image G72 to the size of the input face image G71.

[0029] 10, the information processing device 100 has an upper limit on the size of the reduced face image, so it can prevent the size of the reduced face image G72 from becoming relatively large (for example, 50 pixels or more in width or 50 pixels or more in height). In other words, the information processing device 100 has an upper limit on the size of the reduced face image, so it can reduce the size of the reduced face image G72, which has been reduced relative to the size of the input face image G71, to an appropriate size (for example, less than 50 pixels in width and less than 50 pixels in height). Therefore, when the information processing device 100 enlarges the reduced face image G72 to the size of the input face image G71, it can prevent the generation of an enlarged face image G73 in which the reduced face image G72 is smoothly enlarged relative to the size of the reduced face image G72. In other words, the information processing device 100 can generate an enlarged face image G73 in which the reduced face image G72 is enlarged to a size appropriate relative to the size of the reduced face image G72. Furthermore, the information processing device 100 can prevent the generation of an enlarged face image G73 in which the reduced face image G72 is smoothly enlarged relative to the size of the reduced face image G72, and therefore can prevent the execution of weak (i.e., smooth) mosaic processing that is not suitable for the size of the input face image. In other words, the information processing device 100 can generate an enlarged face image G73 in which the reduced face image G72 is enlarged to a size that is appropriate relative to the size of the reduced face image G72, and therefore can execute mosaic processing of appropriate strength that is suitable for the size of the input face image.

[0030] 2. First Embodiment [2-1. Information Processing System Configuration] An example of the configuration of the information processing system 1 according to the first embodiment will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the configuration of the information processing system 1 according to the first embodiment. As shown in Fig. 11, the information processing system 1 includes a user terminal 10 and an information processing device 100. The user terminal 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication.

[0031] The user terminal 10 is an information processing device used by a user. For example, the user terminal 10 is an information processing device such as a desktop PC (Personal Computer) or a notebook PC. The user terminal 10 may also be a smart device such as a smartphone or a tablet.

[0032] The information processing device 100 is a device that executes information processing according to the first embodiment. The information processing device 100 executes an information processing method according to the first embodiment by executing an information processing program according to the first embodiment. Specifically, the information processing device 100 detects each of a plurality of face regions including the faces of a plurality of people from an image. The information processing device 100 also determines whether the size of a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size. If the information processing device 100 determines that the size of the first reduced face image is below the lower limit size, it resizes the first reduced face image to the lower limit size. If the information processing device 100 determines that the size of the first reduced face image is above the upper limit size, it resizes the first reduced face image to the upper limit size. The information processing device 100 also generates a first enlarged face image by enlarging the resized first reduced face image to the size of the original image of the face region.

[0033] 2-2. Configuration of information processing device An example of the configuration of the information processing device 100 according to the first embodiment will be described with reference to Fig. 12. Fig. 12 is a diagram showing an example of the configuration of the information processing device according to the first embodiment. The information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0034] (Communication unit 110) The communication unit 110 is realized by a NIC (Network Interface Card), an antenna, etc. The communication unit 110 is connected to various networks by wire or wirelessly, and transmits and receives information to and from the user terminal 10, for example.

[0035] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. Specifically, the storage unit 120 stores the information processing program according to the first embodiment.

[0036] (control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0037] The control unit 130 has a detection unit 131, a determination unit 132, and a generation unit 133 as functional units, and may realize or execute the information processing actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 12, and may have other configurations as long as they perform the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130, and does not necessarily have to be physically distinct.

[0038] (Detection unit 131) The detection unit 131 acquires an image. For example, the detection unit 131 acquires an image from the user terminal 10.

[0039] Furthermore, the detection unit 131 detects each of a plurality of face regions including each of the faces of a plurality of people from the image. For example, when an image is input, the detection unit 131 detects each of the plurality of face regions including each of the faces of a plurality of people from the image using a face detection model, which is a machine learning model trained to output each of the plurality of face regions including each of the faces of a plurality of people included in the image. For example, the detection unit 131 inputs the acquired image to the face detection model and detects each of the plurality of face regions including each of the faces of the plurality of people from the image. The detection unit 131 acquires each of the plurality of face regions by detecting each of the plurality of face regions.

[0040] (Judgment unit 132) The determination unit 132 generates a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate. For example, the determination unit 132 generates a first reduced face image in which the width and height of the original face region image are each reduced at a predetermined reduction rate. Here, the predetermined reduction rate may be, for example, 0.5x or 0.03x. Note that 0.5x or 0.03x is an example of the predetermined reduction rate, and the predetermined reduction rate is not limited to 0.5x or 0.03x. For example, the predetermined reduction rate may be smaller than 0.03x or larger than 0.03x. Furthermore, the predetermined reduction rate may be smaller than 0.5x or larger than 0.5x.

[0041] Furthermore, the determination unit 132 determines whether the size of the first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than the lower limit size and equal to or smaller than the upper limit size. For example, the determination unit 132 determines whether the size of the first reduced face image is equal to or larger than the lower limit size. For example, the determination unit 132 determines whether the width and height of the first reduced face image are equal to or larger than the width and height corresponding to the lower limit size. For example, if the determination unit 132 determines that the width and height of the first reduced face image are equal to or larger than the width and height corresponding to the lower limit size, the determination unit 132 determines that the size of the first reduced face image is equal to or larger than the lower limit size. On the other hand, if the determination unit 132 determines that either the width or the height of the first reduced face image is smaller than either the width or the height corresponding to the lower limit size, the determination unit 132 determines that the size of the first reduced face image is not equal to or larger than the lower limit size (is below the lower limit size). If the determining unit 132 determines that the size of the first reduced face image is not equal to or larger than the lower limit size (is smaller than the lower limit size), it determines that the size of the first reduced face image is not equal to or larger than the lower limit size and not equal to or smaller than the upper limit size.

[0042] Furthermore, the determination unit 132 determines whether the size of the first reduced face image is equal to or smaller than the upper limit size. For example, the determination unit 132 determines whether the width and height of the first reduced face image are equal to or smaller than the width and height corresponding to the upper limit size. For example, when the determination unit 132 determines that the width and height of the first reduced face image are equal to or smaller than the width and height corresponding to the upper limit size, the determination unit 132 determines that the size of the first reduced face image is equal to or smaller than the upper limit size. On the other hand, when the determination unit 132 determines that either the width or the height of the first reduced face image exceeds either the width or the height corresponding to the upper limit size, the determination unit 132 determines that the size of the first reduced face image is not equal to or smaller than the upper limit size (exceeds the upper limit size). Note that when the determination unit 132 determines that the size of the first reduced face image is not equal to or smaller than the upper limit size (exceeds the upper limit size), the determination unit 132 determines that the size of the first reduced face image is equal to or larger than the lower limit size and not equal to or smaller than the upper limit size.

[0043] (Generation unit 133) When the determination unit 132 determines that the size of the first reduced face image is not equal to or larger than the lower limit size nor equal to or smaller than the upper limit size, the generation unit 133 resizes the size of the first reduced face image to the lower limit size or the upper limit size. Specifically, when the determination unit 132 determines that the size of the first reduced face image is below the lower limit size, the generation unit 133 resizes the size of the first reduced face image to the lower limit size and generates a first enlarged face image by enlarging the resized first reduced face image to the size of the image of the original face region. More specifically, when the determination unit 132 determines that the size of the first reduced face image is below the lower limit size, the generation unit 133 reduces the size of the image of the original face region to the lower limit size. In other words, the generation unit 133 generates a second reduced face image by reducing the size of the image of the original face region to the lower limit size. Subsequently, the generation unit 133 generates a first enlarged face image by enlarging the second reduced face image to the size of the image of the original face region.

[0044] Furthermore, when the determination unit 132 determines that the size of the first reduced face image exceeds the upper limit size, the generation unit 133 resizes the size of the first reduced face image to the upper limit size and generates a first enlarged face image by enlarging the resized first reduced face image to the size of the image of the original face region. More specifically, when the determination unit 132 determines that the size of the first reduced face image exceeds the upper limit size, the generation unit 133 reduces the size of the image of the original face region to the upper limit size. In other words, the generation unit 133 generates a third reduced face image by reducing the size of the image of the original face region to the upper limit size. Subsequently, the generation unit 133 generates a first enlarged face image by enlarging the third reduced face image to the size of the image of the original face region.

[0045] In addition, when the determination unit 132 determines that the size of the first reduced face image is equal to or larger than the lower limit size and equal to or smaller than the upper limit size, the generation unit 133 generates a second enlarged face image by enlarging the first reduced face image to the size of the image of the original face area.

[0046] [2-3. Processing Procedure] An example of a processing procedure of the information processing device 100 according to the first embodiment will be described with reference to FIG. 13. FIG. 13 is a flowchart showing an example of a processing procedure of the information processing device according to the first embodiment. In FIG. 13, the detection unit 131 acquires an image (step S101). Subsequently, the detection unit 131 detects a face area from the image (step S102). For example, the detection unit 131 detects each of a plurality of face areas including the faces of a plurality of people from the image. The detection unit 131 acquires each of the plurality of face areas by detecting each of the plurality of face areas.

[0047] The determination unit 132 also generates a first reduced face image, which is an image of the face region reduced at a predetermined reduction ratio (step S103). Subsequently, the determination unit 132 determines whether the size of the first reduced face image is equal to or larger than a lower limit size and equal to or smaller than an upper limit size (step S104).

[0048] If the determination unit 132 determines that the size of the first reduced face image is not equal to or larger than the lower limit size nor equal to or smaller than the upper limit size (step S104; No), the generation unit 133 resizes the size of the first reduced face image to the lower limit size or the upper limit size (step S105). For example, if the determination unit 132 determines that the size of the first reduced face image is smaller than the lower limit size, the generation unit 133 resizes the size of the first reduced face image to the lower limit size, and generates a first enlarged face image by enlarging the resized first reduced face image to the size of the image of the original face region. Also, if the determination unit 132 determines that the size of the first reduced face image is larger than the upper limit size, the generation unit 133 resizes the size of the first reduced face image to the upper limit size, and generates a first enlarged face image by enlarging the resized first reduced face image to the size of the image of the original face region. Next, the generating unit 133 generates a first enlarged face image by enlarging the resized first reduced face image to the size of the image of the original face region (step S106).

[0049] On the other hand, if the judgment unit 132 judges that the size of the first reduced face image is equal to or larger than the lower limit size and equal to or smaller than the upper limit size (step S104; Yes), the generation unit 133 generates a second enlarged face image by enlarging the first reduced face image to the size of the image of the original face area (step S107).

[0050] [2-4. Effects] As described above, the information processing device 100 according to the first embodiment includes the detection unit 131, the determination unit 132, and the generation unit 133. The detection unit 131 detects each of a plurality of face regions including the faces of a plurality of people from an image. The determination unit 132 determines whether the size of a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size. If the determination unit 132 determines that the size of the first reduced face image is below the lower limit size, the generation unit 133 resizes the first reduced face image to the lower limit size. If the determination unit 132 determines that the size of the first reduced face image is above the upper limit size, the generation unit 133 resizes the first reduced face image to the upper limit size and generates a first enlarged face image by enlarging the resized first reduced face image to the size of the original image of the face region.

[0051] This allows the information processing device 100 to perform appropriate mosaic processing according to the size of the facial area of ​​each of multiple people included in the image. Furthermore, since the information processing device 100 can perform appropriate mosaic processing according to the size of the facial area of ​​each of multiple people included in the image, it can contribute to achieving Goal 9 of the Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0052] In addition, when the determination unit 132 determines that the size of the first reduced face image is equal to or larger than the lower limit size and equal to or smaller than the upper limit size, the generation unit 133 generates a second enlarged face image by enlarging the first reduced face image to the size of the image of the original face area.

[0053] This allows the information processing device 100 to perform appropriate mosaic processing according to the size of the face area of ​​each of the multiple people included in the image.

[0054] 3. Second Embodiment In the second embodiment, a method for automatically determining appropriate values ​​for the predetermined reduction ratio, lower limit size, and upper limit size according to the first embodiment will be described.

[0055] [3-1. Information Processing System Configuration] An example configuration of an information processing system 1A according to the second embodiment will be described with reference to FIG. 11. In this embodiment, the configuration of the information processing system 1A is the same as that of the first embodiment, so reference may be made to FIG. 11 showing an example configuration of the information processing system 1 according to the first embodiment. In the second embodiment, the information processing device 100 shown in FIG. 11 is replaced with an information processing device 100A according to the second embodiment. In addition, the user terminal 10 is the same as that of the first embodiment, so description of the user terminal 10 will be omitted here.

[0056] The information processing device 100A is a device that executes information processing according to the second embodiment. The information processing device 100A executes an information processing method according to the second embodiment by executing an information processing program according to the second embodiment. Specifically, the information processing device 100A determines a predetermined reduction ratio based on a reference reduction ratio and the size of the original image of the face region. The information processing device 100A also determines a lower limit size based on the inference result of face detection. The information processing device 100A also determines an upper limit size based on the similarity of image features extracted from the image of the face region.

[0057] 3-2. Configuration of information processing device An example of the configuration of an information processing device 100A according to the second embodiment will be described with reference to Fig. 14. Fig. 14 is a diagram showing an example of the configuration of the information processing device 100A according to the second embodiment. The information processing device 100A has a communication unit 110, a storage unit 120, and a control unit 130A. Note that, since the functional units other than the control unit 130A are common to the functional units included in the information processing device 100 according to the first embodiment, only the control unit 130A that is not common to the first embodiment will be described here, and a description of the other functional units will be omitted.

[0058] (control unit 130A) The control unit 130A is a controller, and is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device inside the information processing device 100A using a RAM as a work area. The control unit 130A is also a controller, and is realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0059] The control unit 130A may have a detection unit 131, a determination unit 132, a generation unit 133, and a decision unit 134 as functional units, and may realize or execute the information processing operations described below. Note that the internal configuration of the control unit 130A is not limited to the configuration shown in FIG. 14, and may be any other configuration that performs the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130A, and does not necessarily have to be physically distinct.

[0060] Each element of the control unit 130A will be explained below in order, but since elements other than the determination unit 134 are the same as those in the first embodiment, explanations thereof will be omitted here.

[0061] (Decision unit 134) The determination unit 134 determines a predetermined reduction ratio based on a reference reduction ratio serving as a reference and the size of the image of the original face region. Specifically, the determination unit 134 determines the predetermined reduction ratio based on the size of the reference image serving as a reference, the reference reduction ratio, and the size of the image of the original face region. More specifically, the determination unit 134 determines the predetermined reduction ratio using the following formula (1). In the following formula (1), the reduction ratio基準 corresponds to the reference reduction ratio. In addition, in the following equation (1), the input image corresponds to the image of the original face region.

[0062]

number

[0063] An overview of the processing of the information processing device 100A according to the second embodiment will be described with reference to FIG. 15. FIG. 15 is a diagram for explaining an overview of the processing of the information processing device 100A according to the second embodiment. In FIG. 15, the determination unit 134 generates a plurality of reduced face images by reducing the image of the original face region to each of a plurality of predetermined sizes through a reduction process (pattern 1) that reduces the input face image to a predetermined size. For example, the determination unit 134 generates a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes that gradually increase from a size smaller than the size of the image of the original face region. Furthermore, the determination unit 134 generates a plurality of enlarged face images by enlarging each of the plurality of reduced face images reduced to each of the plurality of predetermined sizes to the size of the original face image.

[0064] FIG. 15 shows a plurality of enlarged face images G81 to G84 arranged from top to bottom in ascending order of the predetermined size (reduced size) for the reduction process. Here, a small predetermined size for the reduction process corresponds to a strong intensity of the mosaic process. Furthermore, a large predetermined size for the reduction process corresponds to a weak intensity of the mosaic process. For example, the determination unit 134 performs face detection on each of the plurality of enlarged face images G81 to G84 and determines whether a face can be detected from each of the plurality of enlarged face images G81 to G84. Here, determining that a face can be detected from an enlarged face image corresponds to determining that a face that can be recognized as a human face can be detected from a mosaic-processed face image. On the other hand, determining that a face cannot be detected from an enlarged face image corresponds to determining that a face that can be recognized as a human face cannot be detected from a mosaic-processed face image. Furthermore, the determination unit 134 determines, as the lower limit size, a size larger than the predetermined size corresponding to an enlarged face image for which it is determined that a face cannot be detected. That is, the determining unit 134 determines, as the lower limit size, a size larger than the predetermined size corresponding to the enlarged face image in which it is determined that a face that can be recognized as a human face cannot be detected.

[0065] In FIG. 15 , the determination unit 134 determines that a face cannot be detected in the enlarged facial images G81 and G82. On the other hand, the determination unit 134 determines that a face can be detected in the enlarged facial images G83 and G84. For example, the determination unit 134 performs face detection on each of the enlarged facial images G81 to G84 in ascending order of predetermined size, determines whether a face can be detected in each enlarged facial image G82 in which a face cannot be detected, and determines a size larger than the predetermined size corresponding to the enlarged facial image G82 in which a face cannot be detected as the lower limit size. For example, the determination unit 134 determines whether a face can be detected in each enlarged facial image G82 in ascending order of predetermined size, and if a face is detected a predetermined number of times consecutively, determines the smallest predetermined size included in the predetermined number of times as the lower limit size. Here, because the face detection model may output erroneous detection results, a single detection result alone may not necessarily indicate a high probability that a face that can be recognized as a human face is included. Therefore, if a face is detected a predetermined number of times consecutively, it can be said that there is a higher probability that a face that can be recognized as a human face is included.

[0066] As described above, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the image of the original face region. Furthermore, the determination unit 134 performs face detection on each of the plurality of third enlarged face images, determines whether or not a face can be detected from each of the plurality of third enlarged face images, and determines, as the lower limit size, a size larger than the predetermined size corresponding to a third enlarged face image in which it is determined that a face cannot be detected.

[0067] The determination unit 134 also generates a plurality of third enlarged face images by enlarging a plurality of second reduced face images, which are images of a face region reduced to a plurality of predetermined sizes that gradually increase from a size smaller than the size of the image of the original face region, to the size of the image of the original face region. The determination unit 134 also performs face detection on each of the plurality of third enlarged face images in order from the smallest predetermined size, determines whether a face can be detected in order from the smallest predetermined size, and, if a face is detected a predetermined number of times consecutively, determines the smallest predetermined size included in the predetermined number of times as the lower limit size. For example, the predetermined number of times may be any number of times as long as it is two or more.

[0068] An overview of the processing of the information processing device 100A according to the second embodiment will be described with reference to FIG. 16. FIG. 16 is a diagram for explaining an overview of the processing of the information processing device according to the second embodiment. The determination unit 134 generates a plurality of reduced face images by reducing the image of the original face region to each of a plurality of predetermined sizes through a reduction process (pattern 1) that reduces the input face image to a predetermined size. For example, the determination unit 134 generates a plurality of reduced face images that are images of the face region reduced to each of a plurality of predetermined sizes that are gradually smaller than the size of the image of the original face region. Furthermore, the determination unit 134 generates a plurality of enlarged face images by enlarging each of the plurality of reduced face images reduced to each of the plurality of predetermined sizes to the size of the original face image.

[0069] FIG. 16 shows a plurality of enlarged facial images G91-G93 arranged from top to bottom in descending order of the predetermined size (reduced size) used in the reduction process. Here, a larger predetermined size used in the reduction process corresponds to a weaker intensity of the mosaic process. A smaller predetermined size used in the reduction process corresponds to a stronger intensity of the mosaic process. For example, the determination unit 134 extracts image feature quantities F91-F93 from each of the enlarged facial images G91-G93. For example, the determination unit 134 extracts image feature quantities F91-F93 from each of the enlarged facial images G91-G93 using a feature quantity extraction model, which is a machine learning model trained to output image feature quantities indicating the characteristics of an image when an image is input. For example, the image feature quantities may be vectors. For example, the determination unit 134 inputs each of the multiple enlarged face images G91 to G93 into a feature extraction model and extracts image feature amounts F91 to F93 from each of the multiple enlarged face images G91 to G93. The determination unit 134 also extracts an image feature amount F9 of the original face region image G9 from the original face region image G9. For example, the determination unit 134 uses the feature extraction model to extract the image feature amount F9 of the original face region image G9 from the original face region image G9. For example, the determination unit 134 inputs the original face region image G9 into the feature extraction model and extracts the image feature amount F9 of the original face region image G9.

[0070] The determination unit 134 also calculates the similarity between the image feature values ​​F91-F93 of each of the enlarged facial images G91-G93 and the image feature value F9 of the original facial region image G9. A high degree of similarity between the image feature values ​​of an enlarged facial image and the image feature values ​​of the original facial region image corresponds to a high probability that the enlarged facial image contains a face that can be recognized as the face of a specific individual. A low degree of similarity between the image feature values ​​of an enlarged facial image and the image feature values ​​of the original facial region image corresponds to a low probability that the enlarged facial image contains a face that can be recognized as the face of a specific individual. For example, the determination unit 134 calculates cosine similarity as an example of similarity. The determination unit 134 also determines whether the similarity is equal to or less than a predetermined similarity, and determines, as the upper limit size, a size smaller than the predetermined size corresponding to an enlarged facial image whose similarity is determined to be equal to or less than the predetermined similarity. In FIG. 16, the determination unit 134 determines that the cosine similarity between the image feature value F91 and the image feature value F9 exceeds the predetermined cosine similarity. On the other hand, the determination unit 134 determines that the cosine similarity between each of the image features F92 to F93 and the image feature F9 is equal to or less than a predetermined cosine similarity. For example, the determination unit 134 calculates the cosine similarities in descending order of the predetermined size, determines whether the cosine similarities in descending order of the predetermined size are equal to or less than the predetermined cosine similarity, and determines, as the upper limit size, a size smaller than the predetermined size corresponding to the enlarged facial image G92 whose cosine similarity is determined to be equal to or less than the predetermined cosine similarity. For example, the determination unit 134 determines, as the upper limit size, the largest predetermined size that is equal to or less than the predetermined cosine similarity. For example, the determination unit 134 determines, as the upper limit size, the predetermined size of the enlarged facial image G92 that corresponds to the largest predetermined size among the enlarged facial images G92 and G93 that are equal to or less than the predetermined cosine similarity.

[0071] As described above, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes, to the size of the image of the original face area, calculates the similarity between the image features of each of the plurality of third enlarged face images and the image features of the image of the original face area, determines whether the similarity is equal to or less than the predetermined similarity, and determines, as the upper limit size, a size smaller than the predetermined size corresponding to the third enlarged face image whose similarity is determined to be equal to or less than the predetermined similarity.

[0072] In addition, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes that gradually become smaller from the size of the image of the original face area, to the size of the image of the original face area, calculates the similarity in order from the largest predetermined size, determines whether the similarity in order from the largest predetermined size is equal to or less than the predetermined similarity, and if it is determined that the similarity is equal to or less than the predetermined similarity, determines the largest predetermined size that is equal to or less than the predetermined similarity as the upper limit size.

[0073] [3-3. Processing Procedure] An example of a processing procedure of the information processing device 100A according to the second embodiment will be described with reference to FIG. 17. FIG. 17 is a flowchart showing an example of a processing procedure of the information processing device 100A according to the second embodiment. In FIG. 17, the detection unit 131 acquires an image of a face region (step S201). For example, the detection unit 131 acquires an image. Next, the detection unit 131 detects a face region from the image to acquire the image of the face region. For example, the detection unit 131 detects each of a plurality of face regions including the faces of a plurality of people from the image to acquire each of the plurality of face regions.

[0074] The determination unit 134 also generates a plurality of second reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes (step S202). Subsequently, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of the plurality of second reduced face images to the size of the original image of the face region (step S203). Subsequently, the determination unit 134 performs face detection on each of the plurality of third enlarged face images (step S204). For example, the determination unit 134 performs face detection on each of the plurality of third enlarged face images in order from the smallest to the largest predetermined size.

[0075] Furthermore, the determining unit 134 determines whether a face can be detected from each of the plurality of third enlarged face images. For example, the determining unit 134 determines whether a face can be detected in order from the smallest to the largest predetermined size. Next, the determining unit 134 determines whether a face has been detected a predetermined number of times in succession (step S205).

[0076] If the determining unit 134 determines that a face has not been detected a predetermined number of times in succession (step S205; No), it performs face detection on each of the plurality of third enlarged face images (step S204).On the other hand, if the determining unit 134 determines that a face has been detected a predetermined number of times in succession (step S205; Yes), it determines the smallest predetermined size included in the predetermined number of times as the lower limit size (step S206).

[0077] An example of a processing procedure of the information processing device 100A according to the second embodiment will be described with reference to FIG. 18. FIG. 18 is a flowchart showing an example of a processing procedure of the information processing device 100A according to the second embodiment. In FIG. 18, the detection unit 131 acquires an image of a face region (step S301). For example, the detection unit 131 acquires an image. Next, the detection unit 131 detects a face region from the image to acquire the image of the face region. For example, the detection unit 131 detects each of a plurality of face regions including the faces of a plurality of people from the image to acquire each of the plurality of face regions.

[0078] The determination unit 134 also generates a plurality of second reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes (step S302). Subsequently, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of the plurality of second reduced face images to the size of the image of the original face region (step S303). Subsequently, the determination unit 134 calculates the similarity between the image feature amount of each of the plurality of third enlarged face images and the image feature amount of the image of the original face region (step S304). The determination unit 134 determines whether the similarity is equal to or less than a predetermined similarity (step S305). For example, the determination unit 134 determines whether the similarity is equal to or less than the predetermined similarity in order from the largest predetermined size.

[0079] If the determination unit 134 determines that the similarity is not equal to or less than the predetermined similarity (step S305; No), it determines whether the similarity is equal to or less than the predetermined similarity (step S305). For example, the determination unit 134 determines whether the similarity is equal to or less than the predetermined similarity, starting from the largest predetermined size. On the other hand, if the determination unit 134 determines that the similarity is equal to or less than the predetermined similarity (step S305; Yes), it determines the largest predetermined size that is equal to or less than the predetermined threshold as the upper limit size (step S306).

[0080] [3-4. Effects] As described above, the information processing device 100A according to the second embodiment includes the determination unit 134. The determination unit 134 determines a predetermined reduction ratio based on a reference reduction ratio and the size of the original image of the face region.

[0081] This allows the information processing device 100A to automatically determine an appropriate value for the predetermined reduction ratio.

[0082] In addition, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes, to the size of the original image of the face area, performs face detection on each of the plurality of third enlarged face images, determines whether or not a face can be detected from each of the plurality of third enlarged face images, and determines, as the lower limit size, a size larger than the predetermined size corresponding to the third enlarged face image in which it is determined that a face cannot be detected.

[0083] This allows the information processing device 100A to determine, as the lower limit size, a size larger than the predetermined size corresponding to the enlarged face image in which it is determined that a face that can be recognized as a human face cannot be detected. Therefore, the information processing device 100A can automatically determine an appropriate value for the lower limit size.

[0084] Furthermore, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes that gradually increase from a size smaller than the size of the image of the original face area, to the size of the image of the original face area, performs face detection on each of the plurality of third enlarged face images in order from the smallest predetermined size, determines whether or not a face can be detected in order from the smallest predetermined size, and if a face is detected a predetermined number of times consecutively, determines the smallest predetermined size included in the predetermined number of times as the lower limit size.

[0085] This allows the information processing device 100A to determine the smallest size among the predetermined sizes corresponding to enlarged face images that are more likely to include a face that can be recognized as a human face as the lower limit size. Therefore, the information processing device 100A can automatically determine an appropriate value for the lower limit size.

[0086] In addition, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes, to the size of the image of the original face area, calculates the similarity between the image features of each of the plurality of third enlarged face images and the image features of the image of the original face area, determines whether the similarity is equal to or less than the predetermined similarity, and determines, as the upper limit size, a size smaller than the predetermined size corresponding to the third enlarged face image whose similarity is determined to be equal to or less than the predetermined similarity.

[0087] This allows the information processing device 100A to determine, as the upper limit size, a size smaller than the predetermined size corresponding to an enlarged face image that is unlikely to include a face that can be recognized as the face of a specific individual. Therefore, the information processing device 100A can automatically determine an appropriate value for the upper limit size.

[0088] In addition, the determination unit 134 generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face area reduced to each of a plurality of predetermined sizes that gradually become smaller from the size of the image of the original face area, to the size of the image of the original face area, calculates the similarity in order from the largest predetermined size, determines whether the similarity in order from the largest predetermined size is equal to or less than the predetermined similarity, and if it is determined that the similarity is equal to or less than the predetermined similarity, determines the largest predetermined size that is equal to or less than the predetermined similarity as the upper limit size.

[0089] This allows the information processing device 100A to determine the largest size among sizes smaller than the predetermined size corresponding to the enlarged face image that is unlikely to include a face that can be recognized as the face of a specific individual as the upper limit size. Therefore, the information processing device 100A can automatically determine an appropriate value for the upper limit size.

[0090] 4. Third Embodiment In the third embodiment, a method for performing mosaic processing with an appropriate strength without using the predetermined reduction ratio, lower limit size, and upper limit size according to the first embodiment will be described.

[0091] [4-1. Information Processing System Configuration] An example configuration of an information processing system 1B according to the third embodiment will be described with reference to FIG. 11. In this embodiment, the configuration of the information processing system 1B is the same as that of the first embodiment, and therefore, reference may be made to FIG. 11 showing an example configuration of the information processing system 1 according to the first embodiment. In the third embodiment, the information processing device 100 shown in FIG. 11 is replaced with an information processing device 100B according to the third embodiment. In addition, the user terminal 10 is the same as that of the first embodiment, and therefore, description of the user terminal 10 will be omitted here.

[0092] The information processing device 100B is a device that executes information processing according to the third embodiment. The information processing device 100B executes an information processing method according to the third embodiment by executing an information processing program according to the third embodiment. Specifically, the information processing device 100B detects each of a plurality of face regions including the faces of a plurality of persons from an image. The information processing device 100B also generates a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of face regions reduced to a plurality of predetermined sizes, to the size of the image of the original face region. The information processing device 100B also determines whether the similarity between the image feature amounts of each of the plurality of enlarged face images and the image feature amounts of the image of the original face region exceeds a predetermined similarity. If it is determined that the similarity exceeds the predetermined similarity, the information processing device 100B acquires the enlarged face image corresponding to the predetermined size for which the similarity is determined to exceed the predetermined similarity as a mosaic image.

[0093] 4-2. Configuration of information processing device An example of the configuration of an information processing device 100B according to the third embodiment will be described with reference to Fig. 19. Fig. 19 is a diagram showing an example of the configuration of the information processing device 100B according to the third embodiment. The information processing device 100B has a communication unit 110, a storage unit 120, and a control unit 130B. Note that, since the functional units other than the control unit 130B are common to the functional units included in the information processing device 100 according to the first embodiment, only the control unit 130B that is not common to the first embodiment will be described here, and a description of the other functional units will be omitted.

[0094] (control unit 130B) The control unit 130B is a controller, and is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device inside the information processing device 100B using RAM as a work area. The control unit 130B is also a controller, and is realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0095] The control unit 130B has a detection unit 131, a generation unit 132B, a determination unit 133B, and an acquisition unit 134B as functional units, and may realize or execute the information processing operations described below. Note that the internal configuration of the control unit 130B is not limited to the configuration shown in FIG. 19, and other configurations may be used as long as they perform the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130B, and does not necessarily have to be physically distinct.

[0096] Each element of the control unit 130B will be explained below in order, but the detection unit 131 is the same as in the first embodiment, so the explanation will be omitted here.

[0097] (Generation unit 132B) The generation unit 132B generates a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of a face region reduced to each of a plurality of predetermined sizes, to the size of the image of the original face region. For example, the generation unit 132B generates a plurality of reduced face images, which are images of a face region reduced to each of a plurality of predetermined sizes. Then, the generation unit 132B generates a plurality of enlarged face images by enlarging each of the plurality of reduced face images to the size of the image of the original face region. The generation unit 132B also generates a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of a face region reduced to each of a plurality of predetermined sizes that gradually increase from an image size smaller than the size of the image of the original face region, to the size of the image of the original face region. For example, the generation unit 132B generates a plurality of reduced face images, which are images of a face region reduced to each of a plurality of predetermined sizes that gradually increase from an image size smaller than the size of the image of the original face region. Then, the generation unit 132B generates a plurality of enlarged face images by enlarging each of the plurality of reduced face images to the size of the image of the original face region.

[0098] (Judgment unit 133B) The determination unit 133B determines whether the similarity between the image feature amount of each of the multiple enlarged face images and the image feature amount of the image of the original face region exceeds a predetermined similarity. Specifically, the determination unit 133B uses a feature extraction model to extract the image feature amount of each of the multiple enlarged face images from each of the multiple enlarged face images generated by the generation unit 132B. For example, the determination unit 133B inputs each of the multiple enlarged face images generated by the generation unit 132B into the feature extraction model to acquire the image feature amount of each of the multiple enlarged face images. The determination unit 133B also uses the feature extraction model to extract the image feature amount of the image of the original face region from the image of the original face region. For example, the determination unit 133B inputs the image of the original face region acquired by the detection unit 131 into the feature extraction model to acquire the image feature amount of the image of the original face region. The determination unit 133B also calculates the similarity between the image feature amount of each of the multiple enlarged face images and the image feature amount of the image of the original face region. For example, the determination unit 133B calculates cosine similarity as an example of similarity. Next, the determination unit 133B determines whether the similarity exceeds a predetermined similarity in ascending order of the predetermined size. For example, the determination unit 133B determines whether the cosine similarity exceeds a predetermined cosine similarity in ascending order of the predetermined size.

[0099] (Acquisition part 134B) When the determination unit 133B determines that the similarity exceeds the predetermined similarity, the acquisition unit 134B acquires, as a mosaic image, enlarged facial images corresponding to the predetermined size at which the similarity is determined to exceed the predetermined similarity. For example, when the determination unit 133B determines that the similarity exceeds the predetermined similarity, the acquisition unit 134B acquires, as a mosaic image, enlarged facial images corresponding to the smallest predetermined size at which the similarity is determined to exceed the predetermined similarity. In other words, the acquisition unit 134B acquires, as a mosaic image, enlarged facial images corresponding to the similarity at which the similarity is determined to exceed the predetermined similarity. For example, the acquisition unit 134B acquires, as a mosaic image, enlarged facial images corresponding to the smallest predetermined size at which the determination unit 133B determines that the cosine similarity exceeds the predetermined cosine similarity. In other words, the acquisition unit 134B acquires, as a mosaic image, enlarged facial images corresponding to the smallest predetermined size from among a plurality of enlarged facial images at which the cosine similarity is determined to exceed the predetermined cosine similarity.

[0100] [4-3. Processing Procedure] An example of a processing procedure of the information processing device 100B according to the third embodiment will be described with reference to FIG. 20. FIG. 20 is a flowchart showing an example of a processing procedure of the information processing device 100B according to the third embodiment. In FIG. 20, the detection unit 131 acquires an image (step S401). Subsequently, the detection unit 131 detects a face area from the image (step S402). For example, the detection unit 131 detects each of a plurality of face areas including the faces of each of a plurality of people from the image. The detection unit 131 acquires each of the plurality of face areas by detecting each of the plurality of face areas.

[0101] Furthermore, the generating unit 132B generates a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes (step S403). For example, the generating unit 132B generates a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes that gradually increase from an image size smaller than the size of the image of the original face region. Next, the generating unit 132B generates a plurality of enlarged face images by enlarging each of the plurality of reduced face images to the size of the image of the original face region (step S404).

[0102] Furthermore, the determination unit 133B calculates the similarity between the image feature amount of each of the enlarged face images and the image feature amount of the original face region image (step S405). Subsequently, the determination unit 133B determines whether the similarity exceeds a predetermined similarity (step S406). For example, the determination unit 133B determines whether the similarity exceeds the predetermined similarity in ascending order of the predetermined size.

[0103] If the determination unit 133B determines that the similarity does not exceed the predetermined similarity (step S406; No), it determines whether the similarity exceeds the predetermined similarity (step S406). For example, the determination unit 133B determines whether the similarity exceeds the predetermined similarity in ascending order of the predetermined size. On the other hand, if the determination unit 133B determines that the similarity exceeds the predetermined similarity (step S406; Yes), it acquires, as a mosaic image, an enlarged face image corresponding to the predetermined size at which it is determined that the similarity exceeds the predetermined similarity (step S407). For example, the determination unit 133B acquires, as a mosaic image, an enlarged face image corresponding to the smallest predetermined size at which it is determined that the similarity exceeds the predetermined similarity.

[0104] [4-4. Modifications] The determination unit 133B performs face detection on each of the plurality of enlarged face images and determines whether a face can be detected from each of the plurality of enlarged face images. If the determination unit 133B determines that a face can be detected, the acquisition unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the predetermined size in which it has been determined that a face can be detected.

[0105] Furthermore, the generating unit 132B generates a plurality of enlarged face images by enlarging a plurality of reduced face images, which are images of a face region reduced to a plurality of predetermined sizes that gradually decrease from the size of the image of the original face region, to the size of the image of the original face region. The determining unit 133B determines whether the similarity is equal to or less than a predetermined similarity, in order from the largest predetermined size. If the determining unit 133B determines that the similarity is equal to or less than the predetermined similarity, the acquiring unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the largest predetermined size whose similarity is determined to be equal to or less than the predetermined similarity.

[0106] [4-5. Effects] As described above, the information processing device 100B according to the third embodiment includes a detection unit 131, a generation unit 132B, a determination unit 133B, and an acquisition unit 134B. The detection unit 131 detects each of a plurality of face regions including the faces of a plurality of people from an image. The generation unit 132B generates a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of face regions reduced to a plurality of predetermined sizes, to the size of the image of the original face region. The determination unit 133B determines whether the similarity between the image feature amounts of each of the plurality of enlarged face images and the image feature amounts of the image of the original face region exceeds a predetermined similarity. If the determination unit 133B determines that the similarity exceeds the predetermined similarity, the acquisition unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the predetermined size for which the similarity is determined to exceed the predetermined similarity.

[0107] This allows the information processing device 100B to perform appropriate mosaic processing according to the size of each face area of ​​multiple people included in the image. Furthermore, since the information processing device 100 can perform appropriate mosaic processing according to the size of each face area of ​​multiple people included in the image, it can contribute to achieving Goal 9 of the Sustainable Development Goals (SDGs), "Build resilience, promote inclusive and sustainable industrialization, promote innovation and build resilience." Furthermore, the information processing device 100B can perform appropriate mosaic processing strength for each of multiple face areas included in the image without using a predetermined reduction ratio, minimum size, or maximum size.

[0108] Furthermore, the generating unit 132B generates a plurality of enlarged face images by enlarging a plurality of reduced face images, which are images of a face region reduced to a plurality of predetermined sizes that gradually increase from an image size smaller than the size of the image of the original face region, to the size of the image of the original face region. The determining unit 133B determines whether the similarity exceeds a predetermined similarity, starting from the smallest predetermined size. If the determining unit 133B determines that the similarity exceeds the predetermined similarity, the acquiring unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the smallest predetermined size whose similarity is determined to exceed the predetermined similarity.

[0109] This allows the information processing device 100B to perform mosaic processing of an appropriate strength on each of a plurality of face regions included in an image without using a predetermined reduction ratio, lower limit size, and upper limit size.

[0110] Furthermore, the determination unit 133B performs face detection on each of the plurality of enlarged face images and determines whether a face can be detected from each of the plurality of enlarged face images. If the determination unit 133B determines that a face can be detected, the acquisition unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the predetermined size in which it has been determined that a face can be detected.

[0111] This allows the information processing device 100B to perform mosaic processing of an appropriate strength on each of a plurality of face regions included in an image without using a predetermined reduction ratio, lower limit size, and upper limit size.

[0112] Furthermore, the generating unit 132B generates a plurality of enlarged face images by enlarging a plurality of reduced face images, which are images of a face region reduced to a plurality of predetermined sizes that gradually decrease from the size of the image of the original face region, to the size of the image of the original face region. The determining unit 133B determines whether the similarity is equal to or less than a predetermined similarity, in order from the largest predetermined size. If the determining unit 133B determines that the similarity is equal to or less than the predetermined similarity, the acquiring unit 134B acquires, as a mosaic image, the enlarged face image corresponding to the largest predetermined size whose similarity is determined to be equal to or less than the predetermined similarity.

[0113] This allows the information processing device 100B to perform mosaic processing of an appropriate strength on each of a plurality of face regions included in an image without using a predetermined reduction ratio, lower limit size, and upper limit size.

[0114] [5. Hardware Configuration] The information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in Fig. 21, for example. The information processing device 100 will be described below as an example. Fig. 21 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output I / F (Interface) 1060, an input I / F 1070, and a network I / F 1080 are connected via a bus 1090.

[0115] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The arithmetic device 1030 is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

[0116] The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. The secondary storage device 1050 may be an internal storage device or an external storage device. The secondary storage device 1050 may also be a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), a NAS (Network Attached Storage), a file server, or the like.

[0117] The output I / F 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a display, a projector, a printer, etc., and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input I / F 1070 is an interface for receiving information from various input devices 1020, such as a mouse, a keyboard, a keypad, a button, a scanner, etc., and is realized by a USB, etc.

[0118] Furthermore, the output I / F 1060 and the input I / F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, the output device 1010 and the input device 1020 may be wireless devices.

[0119] The output device 1010 and the input device 1020 may be integrated into one device, such as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated into one device as an input / output I / F.

[0120] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0121] The network I / F 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0122] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output I / F 1060 and the input I / F 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0123] For example, when the computer 1000 functions as the information processing device 100, the arithmetic unit 1030 of the computer 1000 executes a program loaded onto the primary storage device 1040 to realize the functions of the control unit 130. The arithmetic unit 1030 of the computer 1000 may also load a program acquired from another device via the network I / F 1080 onto the primary storage device 1040 and execute the loaded program. The arithmetic unit 1030 of the computer 1000 may also cooperate with the other device via the network I / F 1080 to call and use the functions and data of a program from another program of the other device.

[0124] [6. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the scope of so-called equivalents. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0125] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0126] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0127] For example, the above-mentioned information processing devices 100, 100A, and 100B may be realized by multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0128] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content. [Explanation of symbols]

[0129] 100, 100A, 100B Information processing device 110 Communications Department 120 Storage section 130, 130A, 130B control section 131 Detector 132, 133B Judgment section 133, 132B generation section 134 Decision Section 134B Acquisition Department

Claims

1. a detection unit that detects each of a plurality of face regions including the faces of a plurality of people from an image; a determination unit that determines whether or not the size of a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size; when the determining unit determines that the size of the first reduced face image is below a lower limit size, resizing the size of the first reduced face image to the lower limit size; when the determining unit determines that the size of the first reduced face image exceeds an upper limit size, resizing the size of the first reduced face image to the upper limit size; a generation unit that generates a first enlarged face image by enlarging the resized first reduced face image to the size of the original image of the face region; An information processing device comprising:

2. The generation unit generating a second enlarged face image by enlarging the first reduced face image to the size of the original image of the face region when the determination unit determines that the size of the first reduced face image is equal to or larger than the lower limit size and equal to or smaller than the upper limit size; The information processing device according to claim 1 .

3. a determination unit that determines the predetermined reduction ratio based on a reference reduction ratio and the size of the original image of the face region; The information processing device according to claim 1 , further comprising:

4. a determination unit that generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the original image of the face region, performs face detection on each of the plurality of third enlarged face images, determines whether or not a face can be detected from each of the plurality of third enlarged face images, and determines, as the lower limit size, a size larger than the predetermined size corresponding to the third enlarged face image in which it is determined that the face cannot be detected; The information processing device according to claim 1 , further comprising:

5. The determination unit generating a plurality of third enlarged face images by enlarging each of the plurality of second reduced face images, which are images of the face region reduced to each of the plurality of predetermined sizes that gradually increase from a size smaller than the size of the original image of the face region, to the size of the original image of the face region; performing face detection on each of the plurality of third enlarged face images in order from the smallest of the predetermined sizes; determining whether or not the face can be detected in order from the smallest of the predetermined sizes; and when the face is detected a predetermined number of times consecutively, determining the smallest predetermined size included in the predetermined number of times as the lower limit size; The information processing device according to claim 4 .

6. a determination unit that generates a plurality of third enlarged face images by enlarging each of a plurality of second reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the original image of the face region, calculates a similarity between an image feature amount of each of the plurality of third enlarged face images and an image feature amount of the original image of the face region, determines whether or not the similarity amount is equal to or less than a predetermined similarity amount, and determines, as the upper limit size, a size smaller than the predetermined size corresponding to the third enlarged face image determined to have the similarity amount equal to or less than the predetermined similarity amount; The information processing device according to claim 1 , further comprising:

7. The determination unit generating a plurality of third enlarged face images by enlarging each of the plurality of second reduced face images, which are images of the face region reduced to each of the plurality of predetermined sizes that gradually become smaller from the size of the original image of the face region, to the size of the original image of the face region, calculating the similarity in order from the largest of the predetermined sizes, determining whether or not the similarity is equal to or less than the predetermined similarity in order from the largest of the predetermined sizes, and if it is determined that the similarity is equal to or less than the predetermined similarity, determining the largest predetermined size that is equal to or less than the predetermined similarity as the upper limit size; The information processing device according to claim 6 .

8. a detection unit that detects each of a plurality of face regions including the faces of a plurality of people from an image; a generation unit that generates a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the original image of the face region; a determination unit that determines whether or not a similarity between an image feature amount of each of the plurality of enlarged face images and an image feature amount of the original image of the face region exceeds a predetermined similarity amount; an acquisition unit that acquires, when the determination unit determines that the similarity exceeds a predetermined similarity, an enlarged face image corresponding to the predetermined size for which the similarity is determined to exceed the predetermined similarity as a mosaic image; An information processing device comprising:

9. The generation unit generating a plurality of enlarged face images by enlarging each of the plurality of reduced face images, which are images of the face region reduced to each of the plurality of predetermined sizes that gradually increase from an image size smaller than the size of the original image of the face region, to the size of the original image of the face region; The determination unit determining whether the similarity exceeds the predetermined similarity in ascending order of the predetermined size; The acquisition unit If the determination unit determines that the similarity exceeds the predetermined similarity, the enlarged face image corresponding to the smallest predetermined size at which the similarity is determined to exceed the predetermined similarity is acquired as the mosaic image. The information processing device according to claim 8 .

10. The determination unit performing face detection on each of the plurality of enlarged face images and determining whether a face can be detected from each of the plurality of enlarged face images; The acquisition unit If the determination unit determines that the face can be detected, the enlarged face image corresponding to the predetermined size in which it is determined that the face can be detected is acquired as the mosaic image. The information processing device according to claim 8 .

11. The generation unit generating a plurality of enlarged face images by enlarging each of the plurality of reduced face images, which are images of the face region reduced to each of the plurality of predetermined sizes that gradually become smaller from the size of the original image of the face region, to the size of the original image of the face region; The determination unit determining whether the similarity is equal to or less than the predetermined similarity in descending order of the predetermined size; The acquisition unit If the determination unit determines that the similarity is equal to or smaller than the predetermined similarity, the enlarged face image corresponding to the largest predetermined size at which the similarity is determined to be equal to or smaller than the predetermined similarity is acquired as the mosaic image. The information processing device according to claim 8 .

12. An information processing method realized by a program executed by an information processing device, a detection step of detecting each of a plurality of face regions including the faces of each of a plurality of people from the image; a determining step of determining whether or not the size of a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size; If it is determined in the determining step that the size of the first reduced face image is below a lower limit size, the size of the first reduced face image is resized to the lower limit size; If it is determined in the determining step that the size of the first reduced face image exceeds an upper limit size, the size of the first reduced face image is resized to the upper limit size; a generating step of generating a first enlarged face image by enlarging the resized first reduced face image to the size of the original image of the face region; An information processing method including:

13. An information processing method realized by a program executed by an information processing device, a detection step of detecting each of a plurality of face regions including the faces of each of a plurality of people from the image; a generating step of generating a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the original image of the face region; a determining step of determining whether or not a similarity between an image feature amount of each of the plurality of enlarged face images and an image feature amount of the original image of the face region exceeds a predetermined similarity amount; an acquisition step of acquiring, as a mosaic image, an enlarged face image corresponding to the predetermined size at which it is determined that the similarity exceeds the predetermined similarity in the determination step; An information processing method including:

14. a detection step of detecting each of a plurality of face regions including the faces of each of a plurality of people from the image; a determination step of determining whether or not the size of a first reduced face image, which is an image of the face region reduced at a predetermined reduction rate, is equal to or larger than a lower limit size and equal to or smaller than an upper limit size; If it is determined in the determination step that the size of the first reduced face image is below a lower limit size, resizing the size of the first reduced face image to the lower limit size; If it is determined in the determination step that the size of the first reduced face image exceeds an upper limit size, resizing the size of the first reduced face image to the upper limit size; a generating step of generating a first enlarged face image by enlarging the resized first reduced face image to the size of the original image of the face region; An information processing program that causes a computer to execute the above.

15. a detection step of detecting each of a plurality of face regions including the faces of each of a plurality of people from the image; a generation step of generating a plurality of enlarged face images by enlarging each of a plurality of reduced face images, which are images of the face region reduced to each of a plurality of predetermined sizes, to the size of the original image of the face region; a determination step of determining whether or not a similarity between an image feature amount of each of the plurality of enlarged face images and an image feature amount of the original image of the face region exceeds a predetermined similarity amount; an acquisition step of acquiring, when it is determined by the determination step that the similarity exceeds a predetermined similarity, an enlarged face image corresponding to the predetermined size for which it is determined that the similarity exceeds the predetermined similarity as a mosaic image; An information processing program that causes a computer to execute the above.

Images