Control device, control method, and program

Abstract

It can capture images suitable for facial recognition. [Solution] The control device includes an acquisition unit that acquires an image from a camera that captures an image including the subject's face, and a processing unit that sets the camera based on the blur detection result in the image and the information used to determine the blur.

Description

Technical Field

[0004] , , , , , , , , , , ,

[0006] , , , ,

[0005] , , , , , ,

[0007] , , ,

[0001] The present disclosure relates to a control device, a control method, and a program.

Background Art

[0002] In recent years, face recognition systems that identify who the subject of authentication is using face recognition technology have been applied in various places. In a face recognition system, face recognition is performed using an image obtained by a camera capturing the subject of authentication. Since face recognition systems are applied in various places, there are cases where an image suitable for face recognition is not captured due to various situations such as the position and orientation of the camera, the position and orientation of the subject of authentication, the time zone, and the weather.

[0003] Patent Document 1 describes a technique for detecting blur in an image of a subject and automatically adjusting the exposure of a camera according to the detection result.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, there is room for consideration regarding a method for capturing an image suitable for face recognition.

[0006] Non-limiting embodiments of the present disclosure contribute to providing a control device, a control method, and a program capable of capturing an image suitable for face recognition.

Means for Solving the Problems

[0007] A control device according to one embodiment of the present disclosure includes an acquisition unit that acquires an image from a camera that captures an image including the face of a subject, and a processing unit that sets the camera based on the blur detection result in the image and information used to determine the blur.

[0008] In one embodiment of the present disclosure, the control device acquires an image from a camera that has captured an image including the face of a subject, and sets the camera based on the blur detection result in the image and the information used to determine the blur.

[0009] A program according to one embodiment of the present disclosure causes a control device to acquire an image including the face of a subject from a camera that has taken such an image, and to perform a process to configure the camera based on the blur detection result in the image and the information used to determine the blur.

[0010] These comprehensive or specific embodiments may be implemented as systems, devices, methods, integrated circuits, computer programs, or recording media, or as any combination of systems, devices, methods, integrated circuits, computer programs, and recording media. [Effects of the Invention]

[0011] Non-limiting embodiments of this disclosure can capture images suitable for facial recognition.

[0012] Further advantages and effects of one embodiment of this disclosure will be made apparent from the specification and drawings. Such advantages and / or effects are provided by several embodiments and features described in the specification and drawings, but not all of them are necessarily provided in order to obtain one or more identical features. [Brief explanation of the drawing]

[0013] [Figure 1] A flowchart showing an example of exposure adjustment processing. [Figure 2]Flowchart showing an example of exposure adjustment processing based on blur detection processing [Figure 3] Flowchart showing an example of the flow of blur detection processing executed in S202 of FIG. 2 [Figure 4] Diagram showing a configuration example of a face authentication system according to an embodiment [Figure 5] Flowchart showing the flow of exposure adjustment processing of an embodiment [Figure 6] Flowchart showing a first example of blur determination processing executed in S404 of FIG. 5 [Figure 7] Diagram showing an example of motion detection processing [Figure 8] Flowchart showing the flow of a first example of motion detection processing executed in S503 of FIG. 6 [Figure 9] Flowchart showing the flow of a second example of motion detection processing executed in S503 of FIG. 6 [Figure 10] Flowchart showing the flow of a third example of motion detection processing executed in S503 of FIG. 6 [Figure 11] Flowchart showing a second example of blur determination processing executed in S404 of FIG. 5 [Figure 12] Flowchart showing a third example of blur determination processing executed in S404 of FIG. 5

Mode for Carrying Out the Invention

[0014] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same function are denoted by the same reference numerals, and redundant description is omitted.

[0015] (One Embodiment) <Findings Leading to the Present Disclosure> In recent years, face recognition systems that identify who the subject of authentication (hereinafter simply referred to as the subject) is using face recognition technology have been applied in various places. In a face recognition system, face recognition is performed using an image obtained by a camera photographing the subject. However, due to various situations such as the position and orientation of the camera, the position and orientation of the subject, the time zone of shooting, and the weather, an image suitable for face recognition may not be captured.

[0016] For example, due to various situations such as the position and orientation of the camera, the position and orientation of the subject, the time zone of shooting, and the weather, the illuminance of the light on the subject may decrease or the subject may be in a backlight state. In such cases, since the face of the subject becomes dark during shooting, an image suitable for face recognition cannot be captured, making face recognition difficult.

[0017] In order to capture an image suitable for face recognition, it is conceivable to adjust the parameters of the camera. For example, it is conceivable to capture an image suitable for face recognition by adjusting the exposure of the camera (that is, the shutter speed). For example, when the exposure value of the camera is increased, the image captured by the camera becomes brighter, so an image suitable for face recognition can be captured. The exposure value may also be referred to as an exposure parameter.

[0018] For example, as an example of a method for adjusting the exposure value, an exposure adjustment process for adjusting the exposure value using the luminance value within the image (for example, within the face region) is being studied. Note that the face region corresponds to the region in the image that includes the face of the subject. Also, the portion of the face region extracted from the image may be referred to as a face region image. Also, the frame surrounding the face region extracted from the image may be referred to as a face frame.

[0019] FIG. 1 is a flowchart showing an example of the exposure adjustment process. The exposure adjustment process may be executed by the camera itself or by a control device that adjusts the parameters of the camera. The flowchart shown in FIG. 1 shows an example in which a control device that adjusts the parameters of the camera executes the exposure adjustment process.

[0020] The control device acquires an image from the camera and performs face detection processing to detect faces in the image (S101).

[0021] The control device determines whether or not a face has been detected (S102).

[0022] If no face is detected (NO in S102), the flow returns to S101.

[0023] If a face is detected (YES in S102), the control device performs the process of acquiring an image of the face region from the image (S103).

[0024] The control device measures the brightness value within the face area (S104).

[0025] The control unit obtains the current exposure value from the camera (S105).

[0026] The control device calculates an exposure value that satisfies the target brightness value (S106). For example, the control device may have a pre-established correspondence between the target brightness value and the exposure value, and calculate the exposure value that satisfies the target brightness value based on this correspondence. For example, if the measured brightness value is smaller than the target brightness value, the control device calculates an exposure value that is larger than the current exposure value as the exposure value that satisfies the target brightness value.

[0027] The control device reflects the exposure value calculated in S106 into the camera's exposure value (S107). Then the process ends.

[0028] For example, by performing exposure adjustment processing as shown in Figure 1, the camera's exposure value is adjusted based on the current brightness value. This allows for the capture of images suitable for face recognition that improve the face recognition score, even when the subject's face becomes dark during shooting due to backlighting or other reasons.

[0029] As mentioned above, increasing the camera's exposure value makes the captured image brighter, which is suitable for facial recognition. However, increasing the camera's exposure value may also cause blurring in the captured image. If blurring occurs, the image may not be suitable for facial recognition.

[0030] Therefore, in order to suppress the occurrence of blur, it is being considered to set an upper limit on the exposure value (for example, a maximum exposure value). By setting a maximum exposure value, it is possible to avoid setting the exposure value above that maximum value, thereby suppressing the occurrence of blur.

[0031] For example, one could set the maximum exposure value of the camera based on the amount of blur produced in the image captured by the camera. Hereafter, the maximum exposure value may be referred to as the maximum exposure value.

[0032] For example, the degree of blur is detected using blur detection processing based on techniques such as Deep Learning. Blur detection processing detects whether the image being detected is blurred or not, and if so, how blurred it is. The degree of blurring corresponds to the degree of blur. The degree of blur is quantified by a value called a score, for example. A higher score indicates greater blur.

[0033] Figure 2 is a flowchart showing an example of exposure adjustment processing based on blur detection. Note that in Figure 2, processes similar to those in Figure 1 are given the same numbering and explanations may be omitted.

[0034] The control device acquires an image of the face region (S103) and performs blur detection processing (S201). For example, the control device calculates a score indicating the magnitude of the blur. The blur detection processing will be described later.

[0035] The control device determines whether or not blur has been detected (S202).

[0036] If blur is detected (YES in S202), the control unit sets the maximum exposure value to 312 (S203).

[0037] If no blur is detected (NO in S202), the control unit sets the maximum exposure value to 10000 (S204).

[0038] After S203 or S204, the control device performs exposure adjustment processing. For example, the control device obtains the current exposure value (S205).

[0039] The control device calculates an exposure value that satisfies the target exposure value and is less than or equal to the maximum exposure value (S206). For example, the control device may have a pre-established correspondence between the target luminance value and the exposure value, and calculate an exposure value that satisfies the target luminance value based on this correspondence. For example, if the measured luminance value is smaller than the target luminance value, the control device calculates an exposure value that is greater than the current exposure value and less than or equal to the maximum exposure value set in S203 or S204 as the exposure value that satisfies the target luminance value.

[0040] The control device reflects the exposure value calculated in S206 into the camera's exposure value (S207).

[0041] The control device performs facial recognition processing (S208). For example, in S207, the control device acquires an image captured by a camera that reflects the exposure value, and performs facial recognition processing based on the acquired image. Through facial recognition processing, it is determined which of the registered individuals the person whose face is included in the captured image belongs to.

[0042] The control device determines whether or not facial recognition was successful (S209). For example, if it can determine that the person whose face is in the captured image is one of the registered people, then facial recognition is considered successful. If it cannot determine that the person whose face is in the captured image is one of the registered people, then facial recognition is considered unsuccessful.

[0043] If facial recognition fails (NO in S209), the flow returns to S101.

[0044] If facial recognition is successful (YES in S209), the flow shown in Figure 2 will end.

[0045] Figure 3 is a flowchart showing an example of the flow of the blur detection process performed in S202 of Figure 2.

[0046] The control device performs deep learning-based blur detection processing on the face region image (S301). For example, the control device calculates a score indicating the magnitude of the blur.

[0047] The control device determines whether the score is above a threshold (S302).

[0048] If the score is above the threshold (YES in S302), the control device determines that blur has been detected (S303). Then, the flow shown in Figure 3 ends.

[0049] If the score is not above the threshold (NO in S302), the control device determines that no blur was detected (S304). Then, the flow in Figure 3 ends.

[0050] As shown in Figures 2 and 3, by setting the maximum exposure value based on the blur detection results, the maximum exposure value when the blur is relatively large is set to be smaller than the maximum exposure value when the blur is relatively small. This avoids situations where the exposure value becomes too large when the blur is relatively large, thus suppressing the occurrence of blur in the captured image.

[0051] However, because the blur detection process detects all blur in an image as blur, there is a possibility that the camera settings (for example, the maximum exposure setting) may not be set appropriately.

[0052] Here, we will explain the relationship between different types of blur and exposure values.

[0053] Blur primarily includes types such as focus blur, low-resolution blur, and motion blur.

[0054] Focus blur refers to the blurring of an image caused by the camera lens not being in focus on the subject.

[0055] Low-resolution blur refers to the blurring of an image caused by a camera having a low number of pixels, resulting in insufficient detail and information.

[0056] Motion blur refers to the blurring of an image caused by the movement of the subject and / or the movement of the camera. Blurring caused by the movement of the subject is also called subject blur. Blurring caused by camera movement is also called camera shake.

[0057] Of the three types of blur mentioned above, focus blur and blur due to low resolution are not related to the exposure value. For example, increasing the camera's exposure value does not increase focus blur. Similarly, increasing the camera's exposure value does not increase blur due to low resolution.

[0058] On the other hand, of the three types of blur mentioned above, motion blur is related to the exposure value. For example, if you increase the camera's exposure value, the motion blur will increase.

[0059] The blur detection process shown in Figure 3 detects blur indiscriminately, so even when focus blur and / or blur due to low resolution, which are unrelated to the exposure value, occur, the maximum exposure value is adjusted. With such adjustments to the maximum exposure value, the camera cannot take pictures properly.

[0060] Therefore, in this embodiment, blur is identified, and the adjustment of the maximum exposure value is changed depending on whether a specific blur is detected or not.

[0061] Here, a specific blur can be considered as motion blur only, or as a blur in which motion blur is dominant. Alternatively, a specific blur can be considered as a blur in which motion blur is dominant within a mixture of multiple types of blur, including motion blur. Furthermore, a specific blur can be considered as a blur that includes motion blur.

[0062] Furthermore, if no specific blur is detected, this may include at least one of the following: if a blur other than motion blur is detected; if a blur other than motion blur is detected as dominant; or if no type of blur is detected.

[0063] <System Configuration> Figure 4 shows an example of the configuration of the facial recognition system 1 according to this embodiment. The facial recognition system 1 shown in Figure 4 includes a camera 10, a control device 20, a facial recognition server 30, and a gate 40. The facial recognition system 1 performs facial recognition processing on a person who is moving in the direction of arrow D and attempting to pass through gate 40, and determines whether the person is authorized to pass through gate 40.

[0064] Gate 40 is connected to control device 20 by wire and / or wireless. Camera 10 is connected to control device 20 by wire and / or wireless. Face recognition server 30 may be connected to control device 20 by wire and / or wireless, or it may be connected via a network (e.g., the Internet).

[0065] A camera 10 is installed at gate 40. Camera 10 photographs, for example, a person approaching the entrance of gate 40 in order to pass through, in the direction from the exit to the entrance of gate 40 (arrow R in Figure 2).

[0066] A control device 20 is connected to gate 40. The control device 20 controls gate 40 according to the result of face recognition processing based on the image captured by camera 10. The control device 20 also sets parameters of camera 10 (e.g., exposure value).

[0067] The control device 20 comprises a communication unit 201, a control unit 202, a storage unit 203, and a display unit 204. The control unit 202 comprises a face detection processing unit 205, a blur detection processing unit 206, a blur discrimination unit 207, a parameter setting unit 208, a face recognition processing unit 209, and a GUI control unit 210. The control unit 202 may also be referred to as a processing unit. Alternatively, at least one of the components included in the control unit 202 may be referred to as a processing unit.

[0068] The communication unit 201 communicates between the control device 20 and the camera 10, and between the control device 20 and the facial recognition server 30. For example, the communication unit 201 acquires captured images from the camera 10. The communication unit 201 also transmits information indicating a facial recognition request to the facial recognition server 30 and receives a response to the facial recognition request from the server device 30. The information indicating a facial recognition request may be information for requesting facial recognition from the facial recognition server 30.

[0069] The face detection processing unit 205 detects whether or not a person's face is included in the image acquired from the camera 10. For example, the face detection processing unit 205 detects whether or not the image contains feature points of a person's face. If feature points are included, it determines that a person's face is included; if feature points are not included, it determines that a person's face is not included.

[0070] The blur detection processing unit 206 performs blur detection processing, for example, using Deep Learning. For example, when the face detection processing unit 205 detects a face, the blur detection processing unit 206 acquires an image of the face region and performs blur detection processing. Exemplarily, the blur detection processing calculates a score indicating the magnitude of the blur. The blur detection processing unit 206 then compares the score with a threshold. If the score is equal to or greater than the threshold, it corresponds to the detection of blur above a predetermined level. If the score is not equal to or greater than the threshold, it corresponds to the detection of no blur above a predetermined level.

[0071] The blur detection processing unit 206 may also compare the score with two or more thresholds. In this case, the score will be classified into three or more levels.

[0072] The blur discrimination unit 207 performs blur discrimination based on the information used for blur discrimination. For example, the blur discrimination unit 207 performs blur discrimination if the blur detection process determines that the score is above a threshold. Exemplaryly, the blur discrimination unit 207 determines whether the blur is a specific type of blur, that is, whether a specific type of blur has been detected.

[0073] The information used to determine blur includes information about the subject's movement and / or information about the camera 10's movement. The information about the subject's movement includes information indicating the magnitude of the subject's movement and / or information indicating the direction of the subject's movement. The subject's movement may also be described as the subject's actions. The information about the camera 10's movement includes information indicating camera 10 blur. The information indicating camera 10 blur includes, for example, the signal-to-noise power ratio (hereinafter also referred to as the S / N ratio) and the average brightness value of the image captured by camera 10.

[0074] The information used for blur detection may be generated by the blur detection unit 207 based on the image acquired from the camera 10, or it may be acquired by an external sensor.

[0075] Furthermore, the blur discrimination unit 207 is not limited to determining whether the blur is a specific type of blur, that is, whether a specific type of blur has been detected or not. The blur discrimination unit 207 may classify the detected blur into three or more categories based on the information used to discriminate the blur. For example, the blur discrimination unit 207 may classify the detected blur into either a first type of blur, a second type of blur, or something else.

[0076] The parameter setting unit 208 sets the parameters of the camera 10. For example, the parameter setting unit 208 sets the exposure value of the camera 10. The parameter setting unit 208 makes different settings depending on whether the blur detection unit 207 determines that a specific blur has been detected or not. For example, if the parameter setting unit 208 determines that a specific blur has been detected, it sets the maximum exposure value to a first value, and if it determines that a specific blur has not been detected, it sets the maximum exposure value to a second value that is greater than the first value.

[0077] The parameter setting unit 208 sets the maximum exposure value, and then sets the exposure value of the camera 10 based on the brightness value of the image. The parameter setting unit 208 calculates an exposure value that is such that the brightness value becomes the target brightness value and is less than or equal to the maximum exposure value. Then, the parameter setting unit 208 reflects the calculated exposure value in the parameters of the camera 10.

[0078] The parameter setting unit 208 may also set parameters of the camera 10 other than the exposure value. For example, the parameter setting unit 208 may set the gain of the camera 10 instead of the exposure value.

[0079] The facial recognition processing unit 209 generates information indicating a facial recognition request, which includes facial feature quantities extracted from the image of the subject's face region, and transmits it to the facial recognition server 30 via the communication unit 201.

[0080] The facial recognition processing unit 209 obtains a response to the facial recognition request from the facial recognition server 30 via the communication unit 201. The response to the facial recognition request includes the facial recognition server 30's determination of whether or not the subject is a person authorized to pass through gate 40.

[0081] The facial recognition processing unit 209 may control gate 40 depending on whether the subject is a person authorized to pass through gate 40. If the subject is a person authorized to pass through gate 40, the facial recognition processing unit 209 performs control to allow passage through gate 40. The control to allow the subject to pass through gate 40 includes control to open the door provided in the passage of gate 40 and control to output an audio and / or display an indication to the subject that passage has been permitted. If the subject is not a person authorized to pass through gate 40, the facial recognition processing unit 209 performs control to block passage through gate 40. The control to block passage through gate 40 includes control to close the door provided in the passage of gate 40 and control to output an audio and / or display an indication to the subject that passage has been prohibited.

[0082] The GUI (Graphical User Interface) control unit 210 controls the display unit 204 and the operation unit (e.g., mouse and / or touch panel) of the control device 20. For example, the GUI control unit 210 controls the display unit 204 to display information to the user using the control device 20. The GUI control unit 210 also acquires information entered by the user via the operation unit and outputs the acquired information to other components of the control unit 202. The GUI control unit 210 may also control a display unit (omitted in Figure 4) installed on the gate 40, etc. Depending on the detection result of the blur detection unit 207, the GUI control unit 210 may provide information via the display unit 204 that instructs the actions of a person attempting to pass through the gate 40. For example, if the blur detection unit 207 detects a specific blur (e.g., motion blur), the GUI control unit 210 displays text information on the display unit 204 requesting the person to stay still or move slowly.

[0083] The memory unit 203 stores information used to control the control unit 202. For example, the memory unit 203 may store information indicating the correspondence between the target brightness value and the exposure value.

[0084] The facial recognition server 30 includes a communication unit 301, a control unit 302, and a facial matching unit 303. The facial recognition server 30 may also be a cloud server. The facial recognition server 30 stores information on individuals who are permitted to pass through gate 40. Individuals permitted to pass through gate 40 are referred to as registered individuals.

[0085] The memory unit 303 stores information about the registrant, including a facial image obtained from the registrant in advance. The information to be stored includes the facial features of the registrant.

[0086] The control unit 302 receives a facial recognition request from the control device 20 via the communication unit 301 and performs facial recognition. The control unit 302 compares the facial feature quantities of the subject included in the facial recognition request with the facial feature quantities of registered users stored in the memory unit 303, and calculates a facial recognition score for each registered user that indicates the similarity between the facial feature quantities of the subject and the facial feature quantities of the registered users. The control unit 302 then identifies the subject as the registered user corresponding to the highest facial recognition score if the highest facial recognition score is above a threshold. If the control unit 302 identifies the subject as one of the registered users, it determines that the subject is a person authorized to enter gate 40. If the control unit 302 cannot identify the subject as one of the registered users, it determines that the subject was not a person authorized to enter gate 40.

[0087] The control unit 302 transmits a response, including the result of facial recognition, to the control device 20 via the communication unit 301. For example, the response includes a determination result indicating whether or not the subject is an authorized person for gate 40.

[0088] In the system configuration shown in Figure 4, the control device 20 and the facial recognition server 30 are shown as separate devices, but this disclosure is not limited to this. The control device 20 may be configured integrally with the facial recognition server 30. Also, in the system configuration shown in Figure 4, the control device 20 is shown as being connected to the gate 40 by wire or wireless, but the control device 20 may be built into the gate 40. Furthermore, in the facial recognition system 1 according to this embodiment, some of the configurations shown in Figure 4 may be omitted, and configurations not shown in Figure 4 may be added. For example, the facial recognition processing unit 209 of the control device 20 may not be included in the control device 20. Also, the display unit 204, GUI control unit 210, etc., may not be included in the control device 20.

[0089] <An example of exposure adjustment processing> Next, the exposure adjustment process in this embodiment will be described. In the exposure adjustment process in this embodiment, the control device 20 determines blur before setting the exposure value, and sets different maximum exposure values ​​depending on whether or not a specific blur is detected.

[0090] Figure 5 is a flowchart showing the flow of the exposure adjustment process in this embodiment.

[0091] The control device 20 acquires an image from the camera 10 and performs face detection processing on the image (S401).

[0092] The control device 20 determines whether or not a face has been detected in the image (S402).

[0093] If no face is detected (NO in S402), the flow returns to S401, and face detection processing is performed on the next image.

[0094] If a face is detected (YES in S402), the control device 20 acquires an image of the face region (S403).

[0095] After acquiring the facial region image (after S403), the control device 20 performs blur detection processing (S404). The blur detection processing will be described later.

[0096] After the blur detection process (after S404), the control device 20 determines whether or not a specific blur has been detected (S405).

[0097] If a specific blur is detected (YES in S405), the control device 20 sets the maximum exposure value to 312 (S406). Note that "312" is just one example of a maximum exposure value, and this disclosure is not limited to this value.

[0098] If no specific blur is detected (NO in S405), the control device 20 sets the maximum exposure value to 10000 (S407). Note that "10000" is just one example of a maximum exposure value, and this disclosure is not limited to this value. The maximum exposure value set in S407 is not limited to "10000" as long as it is a greater number than the maximum exposure value set in S406.

[0099] After S406 or S407, the control device 20 performs exposure adjustment processing. Specifically, after S406 or S407, the control device 20 obtains the current exposure value (S408).

[0100] The control device 20 calculates an exposure value that satisfies the target brightness value and is less than or equal to the set maximum exposure value (S409). In S409, if the exposure value that satisfies the target brightness value exceeds the set maximum exposure value, the exposure value may be set to the maximum exposure value instead of the exposure value that satisfies the target brightness value.

[0101] The control device 20 reflects the calculated exposure value as a parameter of the camera 10 (S410).

[0102] The control device 20 acquires an image captured by the camera 10, which reflects the exposure value, and performs face recognition processing based on the acquired image (S411). Illustratively, the control device 20 extracts facial features from the acquired image, sends a face recognition request to the face recognition server 30, and receives a response from the face recognition server 30 to the face recognition request. The response includes information indicating whether or not face recognition was successful.

[0103] The control device 20 determines whether or not facial recognition was successful (S412).

[0104] If facial recognition fails (NO in S412), the flow returns to S401. Note that if facial recognition fails, the exposure value may be reset to the default value.

[0105] If facial recognition is successful (YES in S412), the flow shown in Figure 5 ends.

[0106] In the processing flow shown in Figure 5 described above, the control device 20 determines whether a specific blur has been detected through blur detection processing, and sets the maximum exposure value when a specific blur is detected to a smaller exposure value than the maximum exposure value when a specific blur is not detected. By setting the maximum exposure value when a specific blur is detected to a smaller exposure value than the maximum exposure value when a specific blur is not detected, it is possible to avoid a situation where the exposure value is increased when motion blur occurs, resulting in a larger blur, and thus enable appropriate shooting.

[0107] Next, we will explain the blur detection process performed in S404 of Figure 5. Three methods for blur detection will be explained. The first method combines blur detection and motion detection. The second method combines blur detection, motion detection, and resolution detection. The third method combines blur detection and camera shake detection.

[0108] <Method 1: An example of combining blur detection and motion detection> The first method of blur detection processing describes a blur detection process that identifies a specific type of blur by combining blur detection and motion detection.

[0109] Figure 6 is a flowchart showing a first example of the blur detection process performed in S404 of Figure 5.

[0110] The control device 20 performs deep learning-based blur detection processing on the face region image (S501). For example, the control device 20 calculates a score indicating the magnitude of the blur as a result of the blur detection processing.

[0111] The control device 20 determines whether the score is above a threshold (S502).

[0112] If the score is above a threshold (YES in S502), the control device 20 executes motion detection processing (S503). In motion detection processing, it is determined whether the subject has performed a specific action at or above a predetermined level. The motion detection processing will be described later.

[0113] The control device 20 determines whether or not an operation above a predetermined level has been detected by the operation detection process (S504).

[0114] If an operation exceeding a predetermined level is detected (YES in S504), the control device 20 determines that a specific blur has been detected (S505). Then, the flow shown in Figure 6 ends.

[0115] If no operation above a predetermined level is detected (NO in S504), the control device 20 determines that no specific blur has been detected (S506). Then, the flow shown in Figure 6 ends.

[0116] If the score is not above the threshold (NO in S502), the control device 20 determines that no specific blur has been detected (S506). The flow shown in Figure 6 then ends.

[0117] The blur detection process shown in Figure 6 determines whether a specific type of blur has been detected based on the presence or absence of blur above a predetermined level and the presence or absence of motion above a predetermined level. As a result, even if blur above a predetermined level is present, if there is no motion above a predetermined level, the blur is determined not to be a specific type of blur. This avoids a situation where the exposure value is not set appropriately based on blur that is not caused by motion (e.g., focus blur and / or blur due to low resolution).

[0118] <Example of motion detection> Next, an example of the motion detection process executed in S503 in Figure 6 will be explained.

[0119] Figure 7 shows an example of motion detection processing. Figure 7 shows an example of motion detection based on images taken by a camera 10 installed at gate 40 at two points in time. In the example in Figure 7, the person attempting to pass through gate 40 moves from right to left within the camera 10's field of view. Hereafter, the two points in time will be referred to as K-1 and K, respectively, the image taken at K-1 will be referred to as the K-1 image, and the image taken at K will be referred to as the K image. K may be a non-negative integer. For example, the K image is the image subject to blur detection processing, and the K-1 image is the image one point in time before the K image.

[0120] The K-1 and K images include the same subjects. At time K, the subjects are closer to gate 40 than at time K-1.

[0121] In the motion detection process, face frames are detected from both the K-1 image and the K image. The distance the detected face frames have moved within the image's capture range is then calculated. For example, the distance between the center of the face frame in the K-1 image and the center of the face frame in the K image is calculated. Based on this distance, a determination is made in the motion detection process.

[0122] For example, if the calculated distance is greater than or equal to a threshold, it is determined that an action above a predetermined level has been detected. Conversely, if the calculated distance is not greater than or equal to a threshold, it is determined that no action above a predetermined level was detected.

[0123] Furthermore, the motion detection process may use the direction of movement of the face frame. For example, the direction in which the detected face frame is moving within the image's capture range is calculated. For example, the direction from the center of the face frame in image K-1 to the center of the face frame in image K is calculated. Based on this direction, a determination is made in the motion detection process.

[0124] For example, if the calculated distance is greater than or equal to a threshold, and the calculated direction is a predetermined direction, it is determined that an action of a predetermined level or higher has been detected. Conversely, if the calculated distance is not greater than or equal to a threshold, or if the calculated direction is not a predetermined direction, it is determined that no action of a predetermined level or higher has been detected. The predetermined direction may be the direction in which the person attempting to pass through gate 40 is moving. In the example shown in Figure 7, the person attempting to pass through gate 40 moves from right to left within the camera 10's shooting range, so the predetermined direction is the direction from right to left within the shooting range.

[0125] As illustrated in Figure 7, motion detection processing is performed based on the captured image. Below, we show a first example of motion detection processing in which a determination is made based on distance, and a second example in which a determination is made based on both distance and direction.

[0126] Figure 8 is a flowchart showing the flow of a first example of the motion detection process executed in S503 in Figure 6.

[0127] The control device 20 acquires the K-1 image (S601).

[0128] In the K-1 image, the control device 20 detects the face frame (S602).

[0129] The control device 20 acquires the K image (S603).

[0130] The control device 20 detects a face frame in the K image (S604).

[0131] The control device 20 calculates the distance between the center of the face frame detected in S602 and the center of the face frame acquired in S604 (S605).

[0132] The control device 20 determines whether the calculated distance is greater than or equal to a threshold (S606).

[0133] If the calculated distance is greater than or equal to a threshold (YES in S606), the control device 20 determines that an action of a predetermined level or higher has been detected (S607). An action of a predetermined level or higher includes, for example, walking at a predetermined speed or higher, or crossing in front of the camera 10 at a predetermined speed or higher. After S607, the flow ends.

[0134] If the calculated distance is not above the threshold (NO in S606), the control device 20 determines that no operation above a predetermined level has been detected (S608). The flow then ends.

[0135] Figure 9 is a flowchart illustrating the flow of a second example of the motion detection process executed in S503 of Figure 6. In Figure 9, processes similar to those in Figure 8 are given the same reference numerals, and their explanations may be omitted.

[0136] If the calculated distance is not above the threshold (NO in S606), the control device 20 determines that no operation above a predetermined level has been detected (S613).

[0137] If the calculated distance is greater than or equal to a threshold (YES in S606), the control device 20 calculates the orientation from the center of the face frame in the K-1 image to the center of the face frame in the K image (for example, the direction of movement of the face frame) (S610).

[0138] The control device 20 determines whether the direction of movement of the face frame matches a specific orientation (S611). The specific orientation is the direction in which the person attempting to pass through the gate 40 is moving, and in the example in Figure 7, it is the direction from right to left.

[0139] If the direction of movement of the face frame matches a specific orientation (YES in S611), it is determined that movement above a predetermined level has been detected (S612). The flow then ends.

[0140] If the direction of movement of the face frame does not align with a specific orientation (NO in S611), it is determined that no movement above a predetermined level is detected (S613). The flow then terminates.

[0141] <Another example of motion detection> The above example demonstrates motion detection using captured images, but this disclosure is not limited to this. Another example of motion detection may involve the use of a sensor capable of measuring distance. For illustrative purposes, a third example is given below, which uses a camera capable of measuring three-dimensional distance. A camera capable of measuring three-dimensional distance may also be referred to as a depth camera.

[0142] Figure 10 is a flowchart showing the flow of a third example of the motion detection process executed in S503 of Figure 6. Note that in Figure 10, processes similar to those in Figures 8 and 9 are given the same reference numerals and their explanations may be omitted.

[0143] If the direction of movement of the face frame is aligned with a specific orientation (YES in S611), the control device 20 measures the 3D distance using the depth camera (S620).

[0144] The control device 20 determines whether the three-dimensional distance is greater than or equal to a threshold (S621).

[0145] If the 3D distance is greater than or equal to a threshold (YES in S621), the control device 20 determines that operation above a predetermined level has been detected (S622). The flow then ends.

[0146] If the 3D distance is not above the threshold (NO in S621), it is determined that no operation above a predetermined level is detected (S623). The flow then terminates.

[0147] If the calculated distance is not above the threshold (NO in S606), it is determined that no operation above a predetermined level is detected (S623). The flow then ends.

[0148] If the direction of movement of the face frame does not align with a specific orientation (NO in S610), it is determined that no movement above a predetermined level is detected (S623). The flow then terminates.

[0149] Figure 10 shows an example of combining the distance calculated from the image, the direction calculated from the image, and the distance measured by the depth camera for motion detection, but this disclosure is not limited to this. For example, instead of using the distance calculated from the image and the direction calculated from the image, the distance measured by the depth camera may be used for motion detection. If the distance calculated from the image and the direction calculated from the image are not used, the processing from S601 to S611 is omitted.

[0150] <Second method: An example combining blur detection, motion detection, and resolution detection> In the second method of blur detection processing, in addition to the blur detection and motion detection shown in the first method, a resolution detection method that detects the image resolution is combined to identify a specific blur.

[0151] Figure 11 is a flowchart showing a second example of the blur detection process performed in S404 of Figure 5. Note that in Figure 11, processes similar to those in Figure 6 are given the same numbering and their explanations may be omitted.

[0152] If an operation exceeding a predetermined level is detected (YES in S504), the control device 20 detects the image resolution (S701). For example, the control device 20 detects the image resolution based on the size of the face frame. The smaller the size of the face frame, the lower the image resolution is determined to be. However, the method for determining the resolution is not limited to this.

[0153] The control device 20 determines whether the detected resolution is above a threshold (S702). For example, if the size of the face frame is above a predetermined size, it is determined that the detected resolution is above the threshold, and if the size of the face frame is not above the predetermined size, it is determined that the detected resolution is not above the threshold.

[0154] If the resolution is above the threshold (YES in S702), for example, if it is not low resolution, it is determined that a specific blur has been detected (S703). Then the flow in Figure 11 ends.

[0155] If the resolution is not above the threshold (NO in S702), for example, if the resolution is low, it is determined that no specific blur is detected (S704). Then the flow in Figure 11 ends.

[0156] If the score is not above the threshold (NO in S502), it is determined that no specific blur was detected (S704). Then, the flow in Figure 11 ends.

[0157] If no operation above a predetermined level is detected (NO in S504), it is determined that no specific blur is detected (S704). Then, the flow shown in Figure 11 ends.

[0158] The blur detection process shown in Figure 11 determines whether a specific type of blur has been detected based on the presence or absence of blur above a predetermined level, the presence or absence of motion above a predetermined level, and the resolution. As a result, even if blur above a predetermined level is present, if there is no motion above a predetermined level and / or the resolution is low, the blur is determined not to be a specific type of blur. This avoids a situation where the exposure value is not set appropriately based on blur that is not caused by motion (e.g., focus blur and / or blur due to low resolution).

[0159] <Third method: An example of combining blur detection and camera shake detection> The third method for blur detection combines the blur detection described in the first method with the camera shake detection of the camera 10.

[0160] If camera 10 experiences camera shake, blurring occurs not only in the face area but also in the background area of ​​the image captured by camera 10. Therefore, the change in the signal-to-noise ratio (SNR) of the background area calculated for each image taken consecutively in the time direction is greater than if camera 10 were not experiencing camera shake. Also, if camera 10 experiences camera shake, blurring occurs not only in the face area but also in the background area of ​​the image captured by camera 10. Therefore, the change in the average brightness value calculated for each image taken consecutively in the time direction is greater than if camera 10 were not experiencing camera shake. Note that each image taken consecutively in the time direction may be called a frame. For example, if camera 10 experiences camera shake, there is a high probability that the change in the SNR between the frame at a certain time point T and the frame at the next time point T+1 is greater than or equal to a threshold. Also, for example, if camera 10 experiences camera shake, there is a high probability that the change in the average brightness value between the frame at a certain time point T and the frame at the next time point T+1 is greater than or equal to a threshold. Note that the amount of change may be called the difference, the magnitude of the change, or the absolute value of the change.

[0161] Therefore, in the third method, the presence or absence of camera shake is determined based on the change in the signal-to-noise ratio of the background area and the change in the average brightness value. Then, by excluding the blur caused by camera shake from the detected blur, blur caused by the subject's movement is distinguished.

[0162] Figure 12 is a flowchart showing a third example of the blur detection process performed in S404 of Figure 5. Note that in Figure 12, processes similar to those in Figures 6 and 11 are given the same numbering and their explanations may be omitted.

[0163] If the score is above a threshold (YES in S502), the control device 20 calculates the change in the signal-to-noise ratio (SNR) of areas other than the face between different frames (S801).

[0164] The control device 20 determines whether the change in the signal-to-noise ratio is less than a threshold (S802).

[0165] If the change in the signal-to-noise ratio outside the face region is less than a threshold (YES in S802), the control device 20 calculates the change in the average brightness value between different frames (S803).

[0166] The control device 20 determines whether the change in the average brightness value is less than a threshold (S804).

[0167] If the change in the average brightness value is less than the threshold (YES in S804), the control device 20 determines that a specific blur has been detected (S805). Then, the flow shown in Figure 12 ends.

[0168] If the change in the average brightness value is not below the threshold (NO in S804), the control device 20 determines that no specific blur has been detected (S806). The case where the change in the average brightness value is not below the threshold corresponds to a case where it is highly likely that the blur is due to camera shake in the camera 10. The flow in Figure 12 then ends.

[0169] If the score is not above the threshold (NO in S502), the control device 20 determines that no specific blur has been detected (S806). Then, the flow shown in Figure 12 ends.

[0170] If the signal-to-noise ratio (SNR) outside the face region is not below the threshold (NO in S802), the control device 20 determines that no specific blur has been detected (S806). The case where the change in the SNR outside the face region is not below the threshold corresponds to a case where it is highly likely that the blur is due to camera shake in the camera 10. The flow in Figure 12 then ends.

[0171] The blur detection process shown in Figure 12 determines whether a specific type of blur has been detected based on the presence or absence of blur above a predetermined level and the degree of camera shake in the camera 10. As a result, even if blur above a predetermined level is present, if the blur is likely to be due to camera shake, it is determined that the blur is not a specific type of blur. This avoids a situation where the exposure value is not set appropriately based on blur that is not caused by movement (e.g., focus blur and / or blur due to low resolution).

[0172] In each of the methods described above, a process of comparing with a threshold is shown, but the thresholds used in the process of comparing with a threshold may be different from each other. Each threshold may be fixed, set by a user such as the administrator of the facial recognition system 1, or set based on other information.

[0173] Furthermore, the methods described above may be combined as appropriate. For example, the third method, which combines blur detection and camera shake detection, may be combined with the resolution detection shown in the second method. For example, in Figure 12, if the change in the average brightness value is less than a threshold (YES in S804), the control device 20 may detect the resolution of the image, similar to S701 and S702 in Figure 11, and determine whether the detected resolution is above a threshold. If the resolution is above a predetermined level, for example, if it is not low resolution, the control device 20 may determine that a specific blur has been detected. By this combination, the control device 20 identifies blur caused by the movement of the subject by excluding blur caused by camera shake and blur caused by low resolution from the blur to be detected.

[0174] Furthermore, the order of processing in each of the methods described above may be changed. For example, in Figure 6, the processes of S503 and S504 related to motion detection may be performed before the processes of S501 and S502 related to blur detection. In this case, the control device 20 determines whether or not motion above a predetermined level has been detected by the motion detection process. If motion above a predetermined level is detected (YES in S504), S501 and S502 are executed. If motion above a predetermined level is not detected (NO in S504), S501 and S502 are not executed, and it is determined that no specific blur has been detected (S506).

[0175] <Summary of Embodiments> A control device according to one embodiment of the present disclosure includes an acquisition unit that acquires an image from a camera that captures an image including the face of a subject, and a processing unit that sets the camera based on the blur detection result in the image and information used to determine the blur.

[0176] In this control device, the information used to determine the blur includes information about the movement of the subject and / or information about the movement of the camera.

[0177] In this control device, the detection result includes a score indicating the magnitude of the blur, the information includes information regarding the movement of the subject, and the processing unit changes the camera settings depending on whether a first condition, that the score is greater than or equal to a first threshold, and a second condition, that the movement satisfies specific conditions, are met.

[0178] In this control device, the processing unit sets the maximum exposure value of the camera to a first exposure value if at least one of the first condition and the second condition is not met, and sets the maximum exposure value of the camera to a second exposure value which is smaller than the first exposure value if both the first condition and the second condition are met.

[0179] In this control device, the information includes a value indicating the magnitude of the movement, and the processing unit determines that the movement satisfies the specific condition if the value is greater than or equal to a second threshold.

[0180] In this control device, the information includes a value indicating the magnitude of the movement and the direction of the movement, and the processing unit determines that the movement satisfies the specific condition if the value is greater than or equal to a second threshold and the direction is a specific direction.

[0181] In this control device, the detection result includes a score indicating the magnitude of the blur, the information includes information regarding the subject's movement and the resolution of the image, and the processing unit changes the camera settings depending on whether each of the following conditions is met: a first condition that the score is greater than or equal to a first threshold, a second condition that the movement satisfies specific conditions, and a third condition that the resolution is greater than or equal to a third threshold.

[0182] In this control device, the processing unit sets the maximum exposure value of the camera to a first exposure value if at least one of the first condition, the second condition, and the third condition is not met, and sets the maximum exposure value of the camera to a second exposure value which is smaller than the first exposure value if each of the first condition, the second condition, and the third condition is met.

[0183] In this control device, the detection result includes a score indicating the magnitude of the blur, the information includes the change in the signal-to-noise power ratio and the change in the average brightness value between multiple time points in the image, and the processing unit changes the camera settings depending on whether each of the following conditions is met: a first condition that the score is greater than or equal to a first threshold, a fourth condition that the change in the signal-to-noise power ratio of the region of the image excluding the face is less than a fourth threshold, and a fifth condition that the change in the average brightness value is less than a fifth threshold.

[0184] In this control device, the processing unit sets the maximum exposure value of the camera to a first exposure value if at least one of the first condition, the fourth condition, and the fifth condition is not met, and sets the maximum exposure value of the camera to a second exposure value which is smaller than the first exposure value if each of the first condition, the fourth condition, and the fifth condition is met.

[0185] In one embodiment of the present disclosure, the control device acquires an image from a camera that has captured an image including the face of a subject, and sets the camera based on the blur detection result in the image and the information used to determine the blur.

[0186] A program according to one embodiment of the present disclosure causes a control device to acquire an image including the face of a subject from a camera that has taken such an image, and to perform a process to configure the camera based on the blur detection result in the image and the information used to determine the blur.

[0187] This disclosure can be implemented using software, hardware, or software integrated with hardware.

[0188] Each functional block used in the description of the above embodiments may be implemented partially or entirely as an integrated circuit (LSI), and each process described in the above embodiments may be controlled partially or entirely by a single LSI or a combination of LSIs. An LSI may consist of individual chips, or it may consist of a single chip that includes some or all of the functional blocks. An LSI may have data inputs and outputs. Depending on the degree of integration, LSIs may be referred to as ICs, system LSIs, super LSIs, or ultra LSIs.

[0189] The method of integration is not limited to LSIs; it may also be implemented using dedicated circuits, general-purpose processors, or dedicated processors. Furthermore, FPGAs (Field Programmable Gate Arrays) that can be programmed after LSI manufacturing, or reconfigurable processors that allow for the reconfiguration of the connections and settings of circuit cells within the LSI, may also be used. This disclosure may be implemented as digital or analog processing.

[0190] Furthermore, if advancements in semiconductor technology or related technologies lead to the emergence of integrated circuit technologies that replace LSIs, then naturally, these technologies can be used to integrate functional blocks. The application of biotechnology, for example, is a possible possibility.

[0191] This disclosure is applicable to all types of devices, systems, and equipment having communication capabilities (collectively referred to as communication equipment). Communication equipment may include a radio transceiver and a processing / control circuit. A radio transceiver may include a receiver and a transmitter, or both as functions. A radio transceiver (transmitter, receiver) may include an RF (Radio Frequency) module and one or more antennas. The RF module may include an amplifier, an RF modulator / demodulator, or similar. Non-exclusive examples of communication devices include telephones (mobile phones, smartphones, etc.), tablets, personal computers (PCs) (laptops, desktops, notebooks, etc.), cameras (digital still / video cameras, etc.), digital players (digital audio / video players, etc.), wearable devices (wearable cameras, smartwatches, tracking devices, etc.), game consoles, digital book readers, telehealth / telemedicine devices, vehicles or mobile transport with communication capabilities (cars, airplanes, ships, etc.), and combinations of the above-mentioned devices.

[0192] Communication devices are not limited to portable or movable devices, but also include all kinds of non-portable or fixed devices, devices, and systems, such as smart home devices (appliances, lighting equipment, smart meters or measuring instruments, control panels, etc.), vending machines, and any other "things" that may exist on an IoT (Internet of Things) network.

[0193] Furthermore, in recent years, Cyber-Physical Systems (CPS), a new concept in IoT (Internet of Things) technology that creates new added value through information linkage between the physical and cyber spaces, has been attracting attention. This CPS concept can also be adopted in the above-described embodiment.

[0194] In other words, as a basic configuration of CPS, for example, edge servers located in physical space and cloud servers located in cyberspace are connected via a network, and processing can be distributed and performed by the processors installed on both servers. Here, it is preferable that each processing data generated on the edge server or cloud server is generated on a standardized platform, and by using such a standardized platform, it is possible to improve efficiency when building systems that include various diverse groups of sensors and IoT application software.

[0195] Communication includes data communication via cellular systems, wireless LAN systems, and communication satellite systems, as well as data communication using combinations of these.

[0196] Furthermore, the communication device also includes devices such as controllers and sensors that are connected to or linked to a communication device that performs the communication functions described in this disclosure. For example, this includes controllers and sensors that generate control signals and data signals used by the communication device that performs the communication functions of the communication device.

[0197] Furthermore, communication equipment includes infrastructure facilities such as base stations, access points, and any other devices, devices, and systems that communicate with or control the aforementioned non-limited types of equipment.

[0198] Although various embodiments have been described above with reference to the drawings, it goes without saying that this disclosure is not limited to such examples. It is clear to those skilled in the art that various modifications or alterations can be conceived within the scope of the claims, and these will naturally also fall within the technical scope of this disclosure. Furthermore, the components in the above embodiments may be combined in any way without departing from the spirit of the disclosure.

[0199] The specific examples of this disclosure have been described in detail above, but these are merely illustrative and do not limit the scope of the claims. The technologies described in the claims include various modifications and changes to the specific examples described above. [Industrial applicability]

[0200] One embodiment of the present disclosure is suitable for a facial recognition system. [Explanation of Symbols]

[0201] 1. Facial Recognition System 10 Cameras 20 Control device 201, 301 Communications Department 202, 302 Control Unit 203, 303 Storage section 204 Display section 205 Face detection processing unit 206 Blur detection processing unit 207 Blur discrimination unit 208 Parameter setting section 209 Facial Recognition Processing Unit 210 GUI Control Unit 30 Face Recognition Servers 40 Gates

Claims

1. An acquisition unit that acquires the image from a camera that has captured an image including the subject's face, A processing unit that configures the camera based on the blur detection result in the aforementioned image and the information used to determine the blur, A control device equipped with the following features.

2. The information used to determine the blur includes information about the subject's movements and / or information about the camera's movements. The control device according to claim 1.

3. The detection result includes a score indicating the magnitude of the blur, The aforementioned information includes information relating to the movements of the subject, The aforementioned processing unit, The camera settings are changed depending on whether the first condition, that the score is above a first threshold, and the second condition, that the movement satisfies specific conditions, are met. The control device according to claim 1.

4. The aforementioned processing unit, If at least one of the first condition and the second condition is not met, the maximum exposure value of the camera is set to the first exposure value. If both the first and second conditions are met, the maximum exposure value of the camera is set to a second exposure value that is smaller than the first exposure value. The control device according to claim 3.

5. The aforementioned information includes a value indicating the magnitude of the movement, The aforementioned processing unit, If the aforementioned value is greater than or equal to the second threshold, it is determined that the movement satisfies the specific condition. The control device according to claim 3.

6. The information includes a value indicating the magnitude of the movement and the direction of the movement. The aforementioned processing unit, If the aforementioned value is greater than or equal to a second threshold, and the aforementioned direction is a specific direction, it is determined that the aforementioned movement satisfies the specific condition. The control device according to claim 3.

7. The detection result includes a score indicating the magnitude of the blur, The aforementioned information includes information regarding the movement of the subject and the resolution of the image, The aforementioned processing unit, The camera settings are changed depending on whether each of the following conditions is met: a first condition that the score is above a first threshold, a second condition that the motion satisfies specific conditions, and a third condition that the resolution is above a third threshold. The control device according to claim 1.

8. The aforementioned processing unit, If at least one of the first condition, the second condition, and the third condition is not met, the maximum exposure value of the camera is set to the first exposure value. If each of the first, second, and third conditions is met, the maximum exposure value of the camera is set to a second exposure value that is smaller than the first exposure value. The control device according to claim 7.

9. The detection result includes a score indicating the magnitude of the blur, The information includes the change in the signal-to-noise power ratio and the change in the average brightness value between multiple time points in the image. The aforementioned processing unit, The camera settings are changed depending on whether each of the following conditions is met: a first condition that the score is equal to or greater than a first threshold; a fourth condition that the change in the signal-to-noise power ratio of the region of the image excluding the face is less than a fourth threshold; and a fifth condition that the change in the average brightness value is less than a fifth threshold. The control device according to claim 1.

10. The aforementioned processing unit, If at least one of the first condition, the fourth condition, and the fifth condition is not met, the maximum exposure value of the camera is set to the first exposure value. If each of the first, fourth, and fifth conditions is met, the maximum exposure value of the camera is set to a second exposure value that is smaller than the first exposure value. The control device according to claim 9.

11. The control device The image is obtained from a camera that captures an image including the subject's face. Based on the blur detection result in the aforementioned image and the information used to determine the blur, the camera settings are configured. Control method.

12. In the control device, The image is obtained from a camera that captures an image including the subject's face. Based on the blur detection result in the aforementioned image and the information used to determine the blur, the camera settings are configured. A program that executes a process.

Images