WO2022264453A1 - 画像処理装置及び画像処理方法 - Google Patents
画像処理装置及び画像処理方法 Download PDFInfo
- Publication number
- WO2022264453A1 WO2022264453A1 PCT/JP2021/044346 JP2021044346W WO2022264453A1 WO 2022264453 A1 WO2022264453 A1 WO 2022264453A1 JP 2021044346 W JP2021044346 W JP 2021044346W WO 2022264453 A1 WO2022264453 A1 WO 2022264453A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face
- user
- camera
- image
- display
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims description 5
- 238000000034 method Methods 0.000 claims description 25
- 230000001815 facial effect Effects 0.000 abstract description 11
- 238000000605 extraction Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 8
- 230000010365 information processing Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000004904 shortening Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/012—Head tracking input arrangements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/60—Static or dynamic means for assisting the user to position a body part for biometric acquisition
- G06V40/67—Static or dynamic means for assisting the user to position a body part for biometric acquisition by interactive indications to the user
Definitions
- the present invention relates to an image processing device and an image processing method.
- Patent Document 1 a technology for recognizing the face of a user riding in a car has been known (Patent Document 1).
- the invention described in Patent Document 1 captures a picture of a user with a camera attached to an automobile, and recognizes the user's face using facial feature information of the captured facial image and pre-registered facial feature information. .
- the camera when the camera takes an image of the user, the user may not necessarily face the appropriate direction. In this case, it may take time to register or authenticate the user's face data.
- the present invention has been made in view of the above problems, and its object is to provide an image processing apparatus and an image processing method capable of shortening the time required for registration or authentication of user's face data.
- An image processing apparatus provides a plurality of face orientations captured by a camera that are within a first angle based on a state in which the user is facing the camera and are different from each other.
- the user's facial data is registered or authenticated using the facial image of the user, and until the registration or authentication is completed, a moving image simulating a human face is displayed on the display, and the direction from the sitting position to the camera is displayed. and the direction from the seated position of the user to the display is smaller than the first angle.
- the time required for registration or authentication of user's face data is reduced.
- FIG. 1 is a configuration diagram of an image processing apparatus 1 according to an embodiment of the present invention.
- FIG. 2 is a diagram for explaining the positions where the camera 11 and the display 12 are installed.
- FIG. 3 is a diagram for explaining a moving image in which a CG image simulating a human face changes its face direction.
- FIG. 4 is a diagram illustrating an example of angles related to face directions.
- FIG. 5 is a diagram for explaining a CG image simulating a human face.
- FIG. 6 is a diagram illustrating an example of the positional relationship between the camera 11 and the display 12.
- FIG. 7 is a diagram illustrating an example of the positional relationship between the camera 11 and the display 12. As shown in FIG. FIG. FIG.
- FIG. 8 is a diagram illustrating an example of the positional relationship between the camera 11 and the display 12.
- FIG. 9 is a diagram illustrating an example of the positional relationship between the camera 11 and the display 12.
- FIG. 10 is a flow chart illustrating an operation example of the image processing apparatus 1 according to the embodiment of the present invention.
- FIG. 11 is a flow chart illustrating an operation example of the image processing apparatus 1 according to the embodiment of the present invention.
- FIG. 12 is a diagram illustrating an example of how to use face ID.
- the image processing device 1 includes an input I/F 10, a camera 11, a controller 20, a display 12, a speaker 13, and a storage device .
- the image processing device 1 in this embodiment is a device that executes processing related to face authentication of a user (mainly a driver). Face recognition includes two phases. One is a phase of newly registering the user's face data. The other is the phase of utilizing the registered face data. The phase of using the registered face data is, for example, a phase of matching the camera image with the registered face data to authenticate the face data.
- the input I/F 10 is a virtual button displayed on the display 12 or a mechanical switch installed near the display 12.
- the input I/F 10 is used when the user newly registers face data.
- the camera 11 has an imaging element such as a CCD (charge-coupled device) or a CMOS (complementary metal oxide semiconductor).
- the camera 11 is installed inside the vehicle. For example, as shown in FIG. 2, the camera 11 is installed in the central portion of the steering wheel. The camera 11 mainly captures the face of the user sitting in the driver's seat. An image captured by the camera 11 is output to the controller 20 .
- Reference numeral 30 shown in FIG. 2 is a CG image imitating a human face (CG: Computer Graphics). Reference numeral 30 is hereinafter referred to as face image 30 .
- the display 12 is installed in the central part of the instrument panel as shown in FIG.
- a moving image reproducing unit 23 which will be described later, reproduces moving images on the display 12 .
- a moving image in the present embodiment is a moving image in which the face image 30 changes the direction of the face.
- the moving image is a moving image of the face image 30 shaking its head.
- the camera 11 and the display 12 are installed side by side in the vehicle width direction.
- the controller 20 is a general-purpose microcomputer equipped with a CPU (central processing unit), memory, and input/output unit.
- a computer program for functioning as the image processing apparatus 1 is installed in the microcomputer.
- the microcomputer By executing the computer program, the microcomputer functions as a plurality of information processing circuits included in the image processing apparatus 1.
- FIG. Here, an example of realizing a plurality of information processing circuits provided in the image processing apparatus 1 by software is shown. It is also possible to construct a circuit. Also, a plurality of information processing circuits may be configured by individual hardware.
- the controller 20 includes, as a plurality of information processing circuits, an input reception unit 21, a state determination unit 22, a moving image reproduction unit 23, a feature extraction unit 24, an ID registration unit 25, a feature comparison unit 26, an ID An authentication unit 27 and a notification unit 28 are provided.
- the phase for newly registering the user's face data will be described.
- the user is sitting in the driver's seat of the vehicle.
- the registration button (input I/F 10).
- This registration button may be a virtual button displayed on the display 12 or a mechanical switch installed near the display 12 .
- the user's input is transmitted to the input reception unit 21 .
- the input reception unit 21 Upon receiving an input from the user, the input reception unit 21 transmits a signal indicating that the input has been received to the state determination unit 22 .
- the state determination unit 22 determines the state of the vehicle when receiving the signal from the input reception unit 21 .
- the state determination unit 22 determines whether or not the power source state of the vehicle is "IGN-ON".
- the "IGN-ON" power state of the vehicle is defined as a state in which the power switch installed in the vehicle is on and all electrical components including the meter and blower motor are in operation.
- the state determination unit 22 determines whether or not the shift position is "P".
- the condition that the power switch is ON may be employed. That is, the condition that the power switch of the vehicle is turned on and the shift position is "P" may be adopted as the condition for registering the face ID.
- the state determination unit 22 determines that the conditions for registering the face ID are satisfied, the state determination unit 22 transmits a signal indicating the determination result to the video playback unit 23 .
- “Satisfying the conditions for face ID registration” means that the power state of the vehicle is “IGN-ON” and the shift position is “P”.
- the moving image reproduction unit 23 reproduces the moving image on the display 12 when receiving the signal from the state determination unit 22 .
- a moving image reproduced by the moving image reproducing unit 23 will be described with reference to FIG.
- the moving images are stored in the storage device 14 .
- the storage device 14 is composed of an HDD (Hard Disk Drive), an SSD (Solid State Drive), and the like.
- the moving image reproducing unit 23 reproduces moving images stored in the storage device 14 .
- the moving image changes the orientation of the face image.
- the face image moves or shakes the head.
- the face image 31 faces rightward.
- the face image 32 faces left.
- the face image 33 faces upward.
- the face image 34 faces downward.
- videos may be stored in a cloud-type server (so-called cloud server). If the video is stored in the cloud server, the controller 20 can access the cloud server and play the video. As a result, the latest moving images are always available.
- angle of the neck is the angle for capturing the image of the face direction required for registering or authenticating the face ID.
- the user moves his or her face (neck) so that the orientation of the face is the same as the orientation of the face in the video.
- the camera 11 captures a plurality of face images with different face orientations while the user is moving his/her face.
- Examples of “a plurality of face images with different face orientations” are face images 35 to 39 shown in FIG.
- the orientation of the face image 35 is 20 degrees upward and 30 degrees rightward.
- the orientation of the face image 36 is 20 degrees downward and 20 degrees rightward.
- the orientation of the face image 37 is the front (0 degrees in the vertical and horizontal directions).
- the orientation of the face image 38 is 20 degrees upward and 20 degrees leftward.
- the orientation of the face image 39 is 20 degrees downward and 30 degrees leftward.
- the camera 11 captures five face images (face images 35 to 39) with different face orientations. However, 5 sheets is an example, and 3 sheets or 4 sheets may be sufficient as long as it is more than one. It should be noted that it is sufficient if the orientations of the faces are different from each other,
- a plurality of face images 35 to 39 captured by the camera 11 are sent to the feature extraction unit 24.
- a feature amount extraction unit 24 extracts features of face data using a plurality of face images 35 to 39 acquired from the camera 11 .
- the feature quantity extraction unit 24 extracts features of face data using a convolutional neural network (CNN).
- CNN convolutional neural network
- the feature quantity extraction unit 24 transmits the extracted features of the face data to the ID registration unit 25 .
- the ID registration unit 25 registers face IDs using the features of the face data acquired from the feature amount extraction unit 24 .
- the registered face ID is saved in the storage device 14 . This completes the registration of the face ID.
- the ID registration unit 25 transmits a signal indicating that registration of the face ID has been completed to the moving image reproduction unit 23 and the notification unit 28 .
- the motion picture reproduction section 23 stops the motion picture, and the notification section 28 notifies the user that the registration has been completed.
- the notification unit 28 may display "Registration of face ID is completed" on the display 12, or may use voice.
- the moving image reproducing unit 23 reproduces the moving image until registration of the face ID is completed.
- the user moves his/her face in the same manner as the moving image until registration of the face ID is completed. This makes it possible to capture a plurality of face images with different face orientations in a short period of time, thereby shortening the time required to register face data.
- the facial image changes the direction of the face (shaking the head), but there are parts that move and parts that do not move.
- an area 40 above the neck moves, and an area 41 below the neck does not move.
- Region 40 includes the face and neck itself.
- Region 41 includes the upper body portion from the chest to the neck.
- Reference numeral 50 in FIG. 6 indicates the user, and reference numeral 51 indicates the user's nose (orientation of the user's face).
- the upper diagram in FIG. 6 shows a state in which the user faces the camera 11 directly.
- Reference numeral 52 indicates a predetermined angle.
- the predetermined angle is defined as an angle at which a large amount of face data is included in the face image captured by the camera 11, with the user 50 facing the front of the camera 11 as a reference.
- the predetermined angle 52 is the range of angles of the orientation of the face of the image required for registration or authentication of the face ID.
- the image simulating a human face changes the orientation of the face (the head is shaken) within the same angular range as the predetermined angle 52 .
- the orientation of the face of the user 50 is preferably within the range of the predetermined angle 52 .
- the predetermined angle 52 is obtained through experiments and simulations.
- the predetermined angle 52 is composed of first angles 61 and 62 in the left and right directions with respect to the state in which the user 50 faces the camera 11 .
- An example of the first angles 61 and 62 is 30 degrees to the left and 30 degrees to the right, with the user facing the front of the camera 11 (0 degrees in the vertical and horizontal directions).
- the range of the predetermined angle 52 is 60 degrees.
- the user 50 moves his/her face while gazing at the moving image displayed on the display 12 . Then, the line of sight of the user 50 is inevitably directed to the display 12 (lower diagram in FIG. 6).
- Reference numeral 63a in FIG. 6 indicates a second angle formed by the direction from the seating position of the user 50 toward the camera 11 and the direction from the seating position of the user 50 toward the display 12 . "The direction from the seated position of the user 50 toward the camera 11" may be expressed as "the line-of-sight direction of the user 50 when the user 50 looks at the camera 11".
- the direction from the seated position of the user 50 toward the display 12 may be expressed as "the line-of-sight direction of the user 50 when the user 50 looks at the display 12".
- Reference numeral 64a in FIG. 6 indicates the range of angles in which the user 50 moves his/her face in the horizontal direction while gazing at the moving image. When the user 50 moves his/her face so that the direction of the face is the same as that of the moving image, the size of the range 64 a becomes the same as the size of the predetermined angle 52 .
- the range 64a does not overlap the range of the predetermined angle 52.
- the face orientation of the face image captured by the camera 11 when the user 50 moves the face in the horizontal direction while watching the moving image is not included in the range of the predetermined angle 52 .
- the user 50 gazes at the moving image and moves his/her face in the same manner as in the moving image it may be difficult to obtain an image of the face orientation required for registration or authentication of the face ID.
- the range of angles in which the user moves his or her face in the horizontal direction while gazing at the moving image overlaps with the range of the predetermined angle 52. is preferred. Therefore, in this embodiment, the camera 11 and the display 12 are installed at positions such that the range of angles in which the user 50 moves his/her face in the horizontal direction while watching the moving image overlaps with the range of the predetermined angle 52 . If the camera 11 and the display 12 are installed close to each other, the second angle 63a becomes smaller, and the angle range 64a in which the user 50 moves his/her face in the horizontal direction while watching the moving image approaches the range of the predetermined angle 52.
- the camera 11 and the display 12 are installed at a position such that the second angle 63b is smaller than the predetermined angle 52 consisting of the first angles 61 and 62, for example, as shown in FIG.
- Range 64b is a clockwise offset of range 64a. Since the range 64 b partially overlaps with the range of the predetermined angle 52 , the orientation of one face of the user 50 can be imaged within the range of the predetermined angle 52 .
- the camera 11 and the display 12 may be installed at a position such that the second angle 63b is smaller than the first angles 61,62.
- Range 64c is a further clockwise offset of range 64b, with second angle 63c in FIG. 8 being less than second angle 63b in FIG.
- the range 64c has a larger portion that overlaps the range of the predetermined angle 52 than the range 64b, and the left and right face orientations of the user 50 can be imaged within the range of the predetermined angle 52.
- the distance between the camera 11 and the display 12 is short.
- the range of the predetermined angle 52 may be adjusted so that the range of the predetermined angle 52 is larger than the second angle.
- the angle at which the image imitating a human face shakes the head is adjusted so that the user 50 moves left and right while watching the moving image.
- the range of angles in which the face is moved may overlap the range of the predetermined angle 52 .
- the range 65 of moving the face to the right while gazing at the moving image is larger than the second angle 63d.
- the angle at which the image simulating a human face shakes its head may be adjusted.
- the video playback unit 23 sets the angle at which the image simulating a human face shakes its head leftward (corresponding to the range 65 in which the user moves his/her face rightward) to be larger than the second angle 63d. play a video.
- the range of the second angle 63d is larger than the range of the predetermined angle 52
- the orientation of the left and right faces of the user 50 can be imaged within the range 52 .
- step S101 the input reception unit 21 receives input from the user. Upon receiving an input from the user, the input reception unit 21 transmits a signal indicating that the input has been received to the state determination unit 22 .
- step S103 the state determination unit 22 receives the signal from the input reception unit 21, it determines the state of the vehicle. When determining that the condition for registering the face ID is satisfied, the state determination unit 22 transmits a signal indicating the determination result to the moving image reproduction unit 23 .
- step S105 when the moving image reproduction unit 23 receives the signal from the state determination unit 22, it reproduces the moving image on the display 12 (see FIG. 3).
- the notification unit 28 faces the camera 11 and turns the face up, down, left, and right in the same way as the moving image until registration or authentication of the face ID is completed. to the user.
- Notification methods include character information notification and voice notification.
- the notification unit 28 may display text on the display 12, saying, "Look at the camera and turn your face up, down, left, and right like a moving image.”
- the notification unit 28 may issue an audio notification through the speaker 13, saying, "Look at the camera and turn your face up, down, left, and right like a moving image.”
- step S107 when the user is moving his/her face while gazing at the moving image, the camera 11 adjusts the face orientation to the first angle 61 with reference to the state in which the user faces the camera 11 facing forward. , 62 and a plurality of different face images are captured.
- step S109 the feature amount extraction unit 24 determines whether or not the features of the face data can be extracted.
- the determination method is not particularly limited, for example, when it is detected that the user is wearing a mask, the feature amount extraction unit 24 determines that the features of the face data cannot be extracted (NO in step S109). On the other hand, if it is not detected that the user is wearing a mask, the feature amount extraction unit 24 determines that the features of the face data can be extracted (YES in step S109). If NO in step S109, the process is interrupted. At this time, the notification unit 28 may notify "Please take off the mask and take another image" or "Are you wearing something that hides your face?".
- step S109 the process proceeds to step S111, and the feature amount extraction unit 24 determines whether or not a plurality of images have been acquired within a predetermined time. If the camera 11 cannot acquire a plurality of images even after the predetermined time has passed (NO in step S111), the process proceeds to step S113, and the notification unit 28 prompts the user to retry image capturing, and displays the moving image on the display 12. When displaying, the user is notified to face the direction of the camera 11 and change the direction of the face in the same way as in the moving image until registration or authentication of the face ID is completed. The notification method is the same as in step S105. After alerting the user by notification, the process returns to step S101.
- step S111 the process proceeds to step S115, and the feature quantity extraction unit 24 uses a plurality of face images acquired from the camera 11 to extract features of face data.
- the feature quantity extraction unit 24 transmits the extracted features of the face data to the ID registration unit 25 .
- step S ⁇ b>117 the ID registration unit 25 registers a face ID using the features of the face data acquired from the feature amount extraction unit 24 .
- the ID registration unit 25 transmits a signal indicating that registration of the face ID has been completed to the moving image reproduction unit 23 and the notification unit 28 .
- step S119 upon receiving this signal, the motion picture reproduction section 23 stops the motion picture, and the notification section 28 notifies the user that the registration has been completed.
- step S201 the input reception unit 21 determines whether or not a trigger for authentication is on.
- the trigger for authentication is on means “the accessory is on”, “the user presses the authentication button (input I/F 10)", and "the signal indicating that the vehicle door has been opened and then closed” is received. Either.
- “accessories are on” is defined as a state in which the power switch installed in the vehicle is on and all electrical components except the meter and blower motor are in operation. However, the definition of "accessory is on” is not limited to this.
- a predetermined signal is sent to the controller 20 when the user presses the unlocking switch of the intelligence key that the user possesses before getting into the vehicle.
- the controller 20 receiving this predetermined signal shifts the power supply position from power off to a predetermined state. This state may be defined as "accessory on”.
- Intelligence keys are used to remotely control the unlocking and locking of doors. Intelligence keys are sometimes referred to as smart keys or remote keys. Also, instead of “receiving a signal indicating that a vehicle door has opened and then closed", “receiving a signal indicating that a vehicle door has opened” or “receiving a signal indicating that a vehicle door has closed” May be employed as a trigger.
- step S201 If the trigger for authentication is on (YES in step S201), the process proceeds to step S203, and the state determination unit 22 determines the state of the vehicle.
- the state determining unit 22 transmits a signal indicating the determination result to the moving image reproducing unit 23 .
- “Satisfies the conditions for facial ID authentication” means that the power state of the vehicle is “IGN-ON” and the shift position is “P”. Note that "satisfying the conditions for authenticating the face ID” may be "the accessory is on” and the shift position is “P”.
- step S205 to 215 The processing of steps S205 to 215 is the same as the processing of steps S105 to 115 shown in FIG. 10, so description thereof will be omitted.
- step S ⁇ b>217 the feature quantity comparison unit 26 compares the features of the face data extracted in step S ⁇ b>215 with the features of the face data stored in the storage device 14 .
- the feature quantity comparison unit 26 outputs the face ID with the highest degree of similarity to the ID authentication unit 27 as the recognition result.
- the process proceeds to step S219, and the ID authentication unit 27 authenticates the face ID.
- ID The authentication unit 27 may authenticate the user as "GUEST".
- GUIEST means that the user is not a unique user whose face ID is registered, and when a user is authenticated as "GUEST", initial values are reflected in various settings.
- the ID authentication unit 27 transmits a signal indicating that face ID authentication has been completed to the moving image reproducing unit 23 and the notification unit 28 . The process proceeds to step S221, and upon receiving this signal, the moving image reproduction unit 23 stops the moving image, and the notification unit 28 notifies the user that the authentication has been completed.
- the image processing device 1 includes a camera 11 that captures an image of the user, a controller 20 that registers or authenticates the user's face data using the image captured by the camera 11, and a display that displays moving images.
- the controller 20 selects a plurality of different face images whose orientation of the face imaged by the camera 11 is within first angles 61 and 62 with reference to the state in which the user is facing the camera 11 frontally. is used to enroll or authenticate the user's facial data.
- the controller 20 displays on the display 12 a moving image in which an image simulating a human face changes the direction of the face until registration or authentication is completed.
- a second angle between the direction from the user's sitting position toward the camera 11 and the direction from the user's sitting position toward the display 12 is smaller than the first angles 61 and 62 .
- the range of angles in which the face is moved partially overlaps the range of the predetermined angle 52 .
- an image required for face ID registration or authentication is quickly obtained.
- the camera 11 is installed in front of the seat inside the vehicle.
- the direction in which the face is turned includes either up, down, left, or right, or a combination of up, down, left, or right (see FIG. 4).
- the camera 11 and the display 12 are installed side by side in the vehicle width direction or the vehicle height direction (see FIG. 2). When the user is sitting in the driver's seat, the camera 11 can image the user from the front.
- the controller 20 may notify the user that the face turns at the same speed as the image simulating a human face changes the face direction.
- Notification methods include character information notification and voice notification.
- the controller 20 may display text on the display 12 saying, "Please change the direction of your face at the same speed as the moving image.”
- the controller 20 may issue an audio notification through the speaker 13 saying, "Please change the direction of your face at the same speed as the moving image.” This prevents the user from moving too fast or too slow.
- the controller 20 may notify the user that, while displaying the moving image on the display 12, the user should turn his/her face in the same way as the moving image until registration or authentication is completed.
- the controller 20 instructs the user to face the camera 11 and turn his/her face up, down, left, and right like the moving image until registration or authentication is completed. may be notified to An example of the notification method has been described in S111 above.
- the user is prevented from stopping before registration or authentication is completed. It is possible to encourage the user to change the direction of the face with reference to the state in which the user faces the camera 11, and the range of angles in which the user moves the face tends to overlap with the range of the predetermined angle 52. - ⁇ Images required for face ID enrollment or authentication are obtained more quickly.
- the direction of the face image captured by the camera 11 does not matter as long as the direction is different.
- a condition may be added that at least one face image facing four directions of up, down, left, and right is required. Under this condition, if face images oriented upward, downward, and rightward are acquired, but face images oriented leftward are not acquired, the controller 20 selects the missing orientation (leftward). User may be notified. As a notification method, the color may be changed when the CG image faces left.
- the camera 11 is installed in front of the seat inside the vehicle.
- the camera 11 and the display 12 may be installed side by side in the longitudinal direction of the vehicle.
- the camera 11 also faces the front. This makes it easier to pick up a characteristic face image.
- the image processing device 1 may further include a sensor that detects the sitting height of the user.
- the controller 20 may change the animation displayed on the display 12 according to the sitting height detected by the sensor.
- the height with respect to the camera 11 differs between a user with a low sitting height and a user with a high sitting height.
- the controller 20 can reproduce a moving image that matches the viewing angle of the user from the camera 11 .
- a plurality of moving images are stored in the storage device 14 to correspond to the sitting height.
- Either the angle at which the image imitating a human face shakes its head to the right or to the left may be larger than the second angle.
- the angle of shaking the head toward the camera 11 side as viewed from the display 12 to be larger than the second angle, the user can turn his/her face while watching the moving image even if the range of the second angle is larger than the range of the predetermined angle 52. Since a part of the moving range 65 overlaps the predetermined angle 52 , the left and right face orientations of the user 50 can be imaged within the range of the predetermined angle 52 .
- the controller 20 may determine whether the user's gaze direction is toward the camera 11 or toward the display 12 based on the image captured by the camera 11 .
- the controller 20 may change the moving image displayed on the display 12 based on the determination result. This enables the controller 20 to reproduce the moving image corresponding to the user's line-of-sight direction.
- a plurality of moving images are stored in the storage device 14 to correspond to the viewing direction of the user.
- the controller 20 determines that the line-of-sight direction of the user 50 is directed toward the display 12, the controller 20 sets one of the angles at which the image simulating a human face shakes its head to the right or to the left as a second angle. It may be larger than the angle. As a result, when the line of sight of the user 50 is directed toward the display 12, the controller 20 can play back a moving image in which the angle at which the user 50 shakes his or her head in the direction toward the camera 11 as viewed from the display 12 is greater than the second angle. becomes. Since a part of the range 65 in which the user moves his/her face while gazing at the moving image overlaps the predetermined angle 52 , the left and right face orientations of the user 50 can be imaged within the range of the predetermined angle 52 .
- the angle in the direction opposite to either one of the angles at which the image simulating a human face shakes its head to the right or to the left. may be smaller than the second angle.
- the range 66 in which the user moves his/her face while gazing at the moving image becomes smaller, and the face outside the predetermined angle 52 becomes smaller. It is possible to suppress the imaging of an image in the direction. Image processing unnecessary for face ID registration or authentication can be suppressed, and the processing load of the controller 20 can be reduced.
- Processing circuitry includes programmed processing devices, such as processing devices that include electrical circuitry. Processing circuitry also includes devices such as application specific integrated circuits (ASICs) and circuit components arranged to perform the described functions.
- ASICs application specific integrated circuits
- the image processing device 1 has been described as a device mounted on a vehicle, it is not limited to this.
- the image processing device 1 may be a terminal device (for example, a smart phone).
- the terminal device may take an image of the user with a camera while reproducing a moving image on the display. Processing related to face ID registration or authentication is implemented by a controller built into the terminal device.
- FIG. 12 there is known a technique of associating a vehicle key ID (an ID transmitted from a key 70) with an in-vehicle device and controlling the in-vehicle device and functions according to the key ID.
- a meter 74 , a HUD 75 , a mirror 78 , a seat 80 , a steering wheel 81 and the like are examples of the in-vehicle devices associated with the key ID.
- the function associated with the key ID includes an air conditioning 76, a drive mode 77, and the like.
- one vehicle is shared by a plurality of people. For example, family sharing. When sharing one vehicle, there is usually one key. Therefore, it is not possible to set the in-vehicle equipment and functions according to the preferences of a plurality of people only with the key ID.
- face ID By using the face ID to log in to the IVI 72 (in-vehicle information), the user ID associated with the face ID becomes available. This user ID may be associated with the in-vehicle device and function settings. By using two IDs, a key ID and a user ID (face ID), even if one vehicle is shared, it is possible to set the in-vehicle equipment and functions according to the preferences of each user. .
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Collating Specific Patterns (AREA)
Abstract
Description
以上説明したように、本実施形態に係る画像処理装置1によれば、以下の作用効果が得られる。
Claims (15)
- ユーザを撮像するカメラと、
前記カメラによって撮像された画像を用いて前記ユーザの顔データを登録または認証するコントローラと、
動画を表示するディスプレイと、を備え、
前記コントローラは、
前記カメラによって撮像された顔の向きが、前記ユーザが前記カメラに対して正面を向いている状態を基準とした第1角度内であって、且つそれぞれ異なる複数の顔画像を用いて前記ユーザの顔データを登録または認証し、
前記登録または前記認証が完了するまで人間の顔を模した画像が顔の向きを変える動画を前記ディスプレイに表示し、
前記ユーザの着座位置から前記カメラに向かう方向と、前記ユーザの着座位置から前記ディスプレイに向かう方向とが成す第2角度は、前記第1角度より小さいことを特徴とする画像処理装置。 - ユーザを撮像するカメラと、
前記カメラによって撮像された画像を用いて前記ユーザの顔データを登録または認証するコントローラと、
動画を表示するディスプレイと、を備え、
前記コントローラは、
前記カメラによって撮像された顔の向きが、前記ユーザが前記カメラに対して正面を向いている状態を基準とした第1角度内であって、且つそれぞれ異なる複数の顔画像を用いて前記ユーザの顔データを登録または認証し、
前記登録または前記認証が完了するまで人間の顔を模した画像が顔の向きを変える動画を前記ディスプレイに表示し、
前記第1角度は、前記ユーザの着座位置から前記カメラに向かう方向と、前記ユーザの着座位置から前記ディスプレイに向かう方向とが成す第2角度より大きい
ことを特徴とする画像処理装置。 - 前記カメラは車内の着座シートの前方に設置され、
前記顔の向きを変える方向には、上下左右方向のいずれか、または上下左右方向の組合せが含まれ、
前記カメラ及び前記ディスプレイは、車幅方向または車両の高さ方向に並ぶように設置される
ことを特徴とする請求項1または2に記載の画像処理装置。 - 前記コントローラは、前記動画を前記ディスプレイに表示しているとき、前記人間の顔を模した画像が顔の向きを変える速度と同じ速度で顔の向きを変えることを前記ユーザに通知する
ことを特徴とする請求項1~3のいずれか1項に記載の画像処理装置。 - 前記コントローラは、前記動画を前記ディスプレイに表示しているとき、前記登録または前記認証が完了するまで前記動画と同じように顔の向きを変えることを前記ユーザに通知する
ことを特徴とする請求項1~4のいずれか1項に記載の画像処理装置。 - 前記コントローラは、前記動画を前記ディスプレイに表示しているとき、前記登録または前記認証が完了するまで、前記カメラの方向を向いて、前記動画と同じように上下左右方向に顔の向きを変えることを前記ユーザに通知する
ことを特徴とする請求項1~5のいずれか1項に記載の画像処理装置。 - 前記コントローラは、前記カメラによって撮像された顔の向きがそれぞれ異なる顔画像のうち、不足している向きを前記ユーザに通知する
ことを特徴とする請求項1~6のいずれか1項に記載の画像処理装置。 - 前記カメラは車内の着座シートの前方に設置され、
前記カメラ及び前記ディスプレイは、車両の前後方向に並ぶように設置される
ことを特徴とする請求項1または2に記載の画像処理装置。 - 前記ユーザの座高を検出するセンサをさらに備え、
前記コントローラは、前記センサによって検出された前記座高に応じて、前記ディスプレイに表示する動画を変更する
ことを特徴とする請求項1~8のいずれか1項に記載の画像処理装置。 - 前記人間の顔を模した画像が右方向または左方向に首を振る角度のうちどちらか一方の角度は、前記第2角度より大きい
ことを特徴とする請求項1~9のいずれか1項に記載の画像処理装置。 - 前記コントローラは、
前記カメラによって撮像された画像に基づいて、前記ユーザの視線方向が前記カメラに向かっているか、または前記ディスプレイに向かっているかを判定し、
判定結果に基づいて前記ディスプレイに表示する動画を変更する
ことを特徴とする請求項1~9のいずれか1項に記載の画像処理装置。 - 前記コントローラは、
前記ユーザの視線方向が前記ディスプレイに向かっていると判定した場合に、前記人間の顔を模した画像が右方向または左方向に首を振る角度のうちどちらか一方の角度を前記第2角度より大きくする
ことを特徴とする請求項11に記載の画像処理装置。 - 前記コントローラは、
前記ユーザの視線方向が前記ディスプレイに向かっていると判定した場合に、前記人間の顔を模した画像が右方向または左方向に首を振る角度のうちどちらか一方とは逆方向の角度を前記第2角度より小さくする
ことを特徴とする請求項11または12に記載の画像処理装置。 - 前記人間の顔を模した画像が顔の向きを変える動画において、首から上の領域が動く一方で、首から下の領域は動かない
ことを特徴とする請求項1~13のいずれか1項に記載の画像処理装置。 - ユーザを撮像するカメラと、前記カメラによって撮像された画像を用いて前記ユーザの顔データを登録または認証するコントローラと、動画を表示するディスプレイとを備える画像処理装置の画像処理方法であって、
前記コントローラは、
前記カメラによって撮像された顔の向きが、前記ユーザが前記カメラに対して正面を向いている状態を基準とした第1角度内であって、且つそれぞれ異なる複数の顔画像を用いて前記ユーザの顔データを登録または認証し、
前記登録または前記認証が完了するまで人間の顔を模した画像が顔の向きを変える動画を前記ディスプレイに表示し、
前記ユーザの着座位置から前記カメラに向かう方向と、前記ユーザの着座位置から前記ディスプレイに向かう方向とが成す第2角度は、前記第1角度より小さい
ことを特徴とする画像処理方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180099263.0A CN117480541A (zh) | 2021-06-15 | 2021-12-02 | 图像处理装置和图像处理方法 |
EP21945374.3A EP4358060A4 (en) | 2021-06-15 | 2021-12-02 | IMAGE PROCESSING DEVICE AND IMAGE PROCESSING METHOD |
JP2023529444A JPWO2022264453A1 (ja) | 2021-06-15 | 2021-12-02 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/022695 WO2022264264A1 (ja) | 2021-06-15 | 2021-06-15 | 画像処理装置及び画像処理方法 |
JPPCT/JP2021/022695 | 2021-06-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022264453A1 true WO2022264453A1 (ja) | 2022-12-22 |
Family
ID=84525995
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/022695 WO2022264264A1 (ja) | 2021-06-15 | 2021-06-15 | 画像処理装置及び画像処理方法 |
PCT/JP2021/044346 WO2022264453A1 (ja) | 2021-06-15 | 2021-12-02 | 画像処理装置及び画像処理方法 |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/022695 WO2022264264A1 (ja) | 2021-06-15 | 2021-06-15 | 画像処理装置及び画像処理方法 |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4358060A4 (ja) |
JP (1) | JPWO2022264453A1 (ja) |
CN (1) | CN117480541A (ja) |
WO (2) | WO2022264264A1 (ja) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015800A (ja) * | 2006-07-06 | 2008-01-24 | Omron Corp | なりすまし検知装置 |
JP2008017227A (ja) | 2006-07-06 | 2008-01-24 | Denso Corp | 顔認識装置及びそれを用いた自動車用ユーザーもてなしシステム |
JP2009113621A (ja) * | 2007-11-06 | 2009-05-28 | Toyota Motor Corp | 乗員画像撮像装置、運転支援装置 |
JP2010006362A (ja) * | 2008-05-27 | 2010-01-14 | Tokai Rika Co Ltd | 乗員撮像装置及び居眠り防止装置 |
JP2015090662A (ja) * | 2013-11-07 | 2015-05-11 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置 |
WO2015194135A1 (ja) * | 2014-06-19 | 2015-12-23 | 日本電気株式会社 | 認証装置、認証システム、認証方法およびプログラム記憶媒体 |
JP2019083015A (ja) * | 2017-10-31 | 2019-05-30 | キヤノンマーケティングジャパン株式会社 | 情報処理装置、及びその制御方法、プログラム |
JP2019134397A (ja) * | 2018-01-30 | 2019-08-08 | パナソニックIpマネジメント株式会社 | 誘導制御装置、方法、及びコンピュータプログラム |
JP2019212156A (ja) * | 2018-06-07 | 2019-12-12 | パナソニックIpマネジメント株式会社 | 顔画像登録システム、顔画像登録方法、移動体端末、及び顔認証画像登録装置 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190080065A1 (en) * | 2017-09-12 | 2019-03-14 | Synaptics Incorporated | Dynamic interface for camera-based authentication |
-
2021
- 2021-06-15 WO PCT/JP2021/022695 patent/WO2022264264A1/ja active Application Filing
- 2021-12-02 EP EP21945374.3A patent/EP4358060A4/en active Pending
- 2021-12-02 CN CN202180099263.0A patent/CN117480541A/zh active Pending
- 2021-12-02 WO PCT/JP2021/044346 patent/WO2022264453A1/ja active Application Filing
- 2021-12-02 JP JP2023529444A patent/JPWO2022264453A1/ja active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008015800A (ja) * | 2006-07-06 | 2008-01-24 | Omron Corp | なりすまし検知装置 |
JP2008017227A (ja) | 2006-07-06 | 2008-01-24 | Denso Corp | 顔認識装置及びそれを用いた自動車用ユーザーもてなしシステム |
JP2009113621A (ja) * | 2007-11-06 | 2009-05-28 | Toyota Motor Corp | 乗員画像撮像装置、運転支援装置 |
JP2010006362A (ja) * | 2008-05-27 | 2010-01-14 | Tokai Rika Co Ltd | 乗員撮像装置及び居眠り防止装置 |
JP2015090662A (ja) * | 2013-11-07 | 2015-05-11 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置 |
WO2015194135A1 (ja) * | 2014-06-19 | 2015-12-23 | 日本電気株式会社 | 認証装置、認証システム、認証方法およびプログラム記憶媒体 |
JP2019083015A (ja) * | 2017-10-31 | 2019-05-30 | キヤノンマーケティングジャパン株式会社 | 情報処理装置、及びその制御方法、プログラム |
JP2019134397A (ja) * | 2018-01-30 | 2019-08-08 | パナソニックIpマネジメント株式会社 | 誘導制御装置、方法、及びコンピュータプログラム |
JP2019212156A (ja) * | 2018-06-07 | 2019-12-12 | パナソニックIpマネジメント株式会社 | 顔画像登録システム、顔画像登録方法、移動体端末、及び顔認証画像登録装置 |
Non-Patent Citations (2)
Title |
---|
「速報:iPhone X「Face ID」認証はこんなに速い。 設定方法を紹介」, YouTube [online] [video], 01 November 2017, [retrieval date 27 December 2021], URL: https://www.youtube.com/watch?v=L7FIxbYyrLQ * |
See also references of EP4358060A4 |
Also Published As
Publication number | Publication date |
---|---|
EP4358060A1 (en) | 2024-04-24 |
CN117480541A (zh) | 2024-01-30 |
JPWO2022264453A1 (ja) | 2022-12-22 |
EP4358060A4 (en) | 2024-07-17 |
WO2022264264A1 (ja) | 2022-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN209044516U (zh) | 用于汽车的用户识别装置 | |
US10745018B2 (en) | Hybrid user recognition systems for vehicle access and control | |
CN103383595B (zh) | 基于用户人脸的分析控制移动终端的装置和方法 | |
US11693937B2 (en) | Automatic retries for facial recognition | |
US7835551B2 (en) | Television set and authentication device | |
US8842155B2 (en) | Portable video communication system | |
US10747860B2 (en) | Sitting posture for biometric identification | |
JP6630665B2 (ja) | 生体id、フィードバックおよびユーザインタラクション状態の相関表示 | |
US10769415B1 (en) | Detection of identity changes during facial recognition enrollment process | |
EP2605172A2 (en) | Multi-person gestural authentication and authorization system and method of operation thereof | |
US9202027B2 (en) | Private/public gesture security system and method of operation thereof | |
WO2019151368A1 (ja) | 生体認証装置、システム、方法および記録媒体 | |
JP7049453B2 (ja) | 信頼されたモバイルコンピューティングデバイスに関連してビークル内カメラを使用するシームレスな運転者の認証 | |
CN110678871A (zh) | 面部认证装置和面部认证方法 | |
KR102532746B1 (ko) | 전자 장치 및 그 제어 방법 | |
WO2022264453A1 (ja) | 画像処理装置及び画像処理方法 | |
US20220219717A1 (en) | Vehicle interactive system and method, storage medium, and vehicle | |
CN114202677A (zh) | 认证车辆内部中的乘员的方法和*** | |
CN112203903A (zh) | 车载设备的控制装置和控制方法 | |
CN114760417A (zh) | 一种图像拍摄方法和装置、电子设备和存储介质 | |
JP2020121668A (ja) | 利用者支援システム及び利用者支援装置 | |
JP6906023B2 (ja) | 車両用認証装置 | |
US20230256939A1 (en) | Vehicle and Control Method Thereof | |
KR20120046582A (ko) | 차량 내 스마트키 인증 시스템 및 그 방법 | |
JP2004064433A (ja) | 機器操作システム及び機器操作プログラム、並びに機器操作方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21945374 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023529444 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180099263.0 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2021945374 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021945374 Country of ref document: EP Effective date: 20240115 |