Information processing device and control method
The information processing device uses face detection and authentication to ensure only registered users activate the system, addressing erroneous activation risks and power efficiency in standby states.
Patent Information
- Application Number
- JP2023212196
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-12-15
- Publication Date
- 2024-11-14
- Estimated Expiration
- 2043-12-15
AI Technical Summary
Existing information processing devices activate even when an unregistered user approaches due to decreased recognition rates in face authentication during low power consumption standby states, risking erroneous system activation.
Implement a system with a face detection unit that detects the presence of a person and performs face authentication only when a registered user is confirmed, limiting authentication attempts and switching between low-power person detection and face authentication processes based on detection results and authentication failures.
Prevents unintentional system activation by unregistered users while minimizing power consumption and maintaining accurate face recognition, ensuring appropriate system startup only when a registered user is present.
Smart Images

Figure 0007583903000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device and a control method. [Background technology]
[0002] There is an information processing device that transitions to a usable state when a person approaches, and transitions to a standby state in which all functions except for some functions are stopped when the person leaves. For example, in Patent Document 1, an infrared sensor is used to detect whether a person is approaching or has moved away.
[0003] In recent years, the accuracy of detecting a face from an image has improved due to the development of computer vision and the like. Therefore, instead of detecting a person using an infrared sensor, detecting a person using face detection is becoming common. In addition, after starting up an information processing device, login authentication is performed to authenticate whether or not the user is a registered user, and face authentication is becoming more and more popular as this authentication method. For example, when a person approaches, the information processing device starts up by detecting the face of the person, and then performs login authentication such as face authentication to allow the user to log in to the system if the user is a registered user, and transitions to a usable state. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2016-148895 A Summary of the Invention [Problem to be solved by the invention]
[0005] The above-mentioned method of activating the device by face detection has a problem that the device may be activated even if a person other than a registered user approaches. In order to solve this problem, a method is conceivable in which, when a person is detected by face detection, it is determined whether the person is a registered user by face authentication, and the device is activated only when it is determined that the person is a registered user. However, in a standby state before activation, it is necessary to keep power consumption low, so the recognition rate during face authentication decreases. If the recognition rate decreases, there is a possibility that an unregistered person may be erroneously determined to be a registered user, even if the probability is low. Therefore, if an unregistered person is in front of the information processing device for a long period of time, there is a concern that an erroneous determination may occur during that time, resulting in activation.
[0006] The present invention has been made in consideration of the above-mentioned circumstances, and one of its objectives is to provide an information processing device and a control method that can properly start up the system when a registered user approaches. [Means for solving the problem]
[0007] The present invention has been made to solve the above-mentioned problems, and an information processing device according to a first aspect of the present invention includes a memory for temporarily storing a system program, a first processor for executing a face recognition process that detects an area of a face image in which a face is captured from an image captured by an imaging unit, and authenticates whether or not a person in the detected face image is a registered user based on information based on the detected face image and information based on a face image of a registered user, and a second processor for starting up the system from a standby state by executing the system program based on success of authentication by the face recognition process, wherein the first processor executes the face recognition process again if authentication by the face recognition process fails, and when the face recognition process has been repeatedly executed due to failure of authentication by the face recognition process, stops the face recognition process based on the number of times it has been executed.
[0008] In the above information processing device, the first processor may execute a person detection process to detect the presence of a person by detecting an area of a facial image in which a face is captured from the captured image, and when the presence of a person is detected by the person detection process, transition from the person detection process to the face recognition process, and stop the face recognition process based on the number of times the face recognition process has been executed since the presence of a person was detected by the person detection process reaching a preset number.
[0009] In the information processing device, the first processor may transition to the person detection process when the face recognition process is stopped due to a failure of authentication by the face recognition process.
[0010] In the above information processing device, the first processor may determine whether or not the number of people present has changed when the presence of a person is detected by the person detection processing after the face recognition processing is stopped, and if it is determined that the number of people present has changed, transition again from the person detection processing to the face recognition processing.
[0011] In the above information processing device, the first processor may continue the person detection processing without transitioning to the face recognition processing if the presence of a person is no longer detected by the person detection processing after the face recognition processing is stopped, and transition from the person detection processing to the face recognition processing if the presence of a person is detected.
[0012] In the information processing device, the person detection process consumes less power than the face recognition process. but It may be a low treatment.
[0013] In the above information processing device, the person detection process may have a lower frame rate than the face recognition process when detecting an area of a face image in which a face is captured from the captured image, and the first processor may switch the frame rate when transitioning from the person detection process to the face recognition process and when transitioning from the face recognition process to the person detection process.
[0014] In the information processing device, the second processor permits login to the system based on a face image detected from an image captured by the imaging unit after the system is started. mosquito The face recognition process, which is executed in the standby state before the system is started, consumes less power than the login authentication process. but It may be a low treatment.
[0015] In the above information processing device, the face authentication process executed in the standby state before the system is started is performed such that a frame rate for detecting a face image area in which a face is captured from the captured image is set to a frame rate equal to or higher than that of the login authentication process. The frame rate of the image captured by the imaging unit It may be lower than that.
[0016] In the information processing device, the first processor may execute a user registration process for registering information based on a face image of a user who uses the information processing device.
[0017] In addition, according to a second aspect of the present invention, a control method in an information processing device including a memory for temporarily storing a system program, a first processor, and a second processor includes the steps of: the first processor detecting an area of a facial image in which a face is captured from an image captured by an imaging unit, and executing a facial recognition process to authenticate whether or not a person in the detected facial image is a registered user based on information based on the detected facial image and information based on a facial image of a registered user; the second processor starting up the system from a standby state by executing a program of the system based on success of authentication by the facial recognition process; the first processor executing the facial recognition process again if authentication by the facial recognition process fails; and, if the first processor has repeatedly executed the facial recognition process due to failure of authentication by the facial recognition process, stopping the facial recognition process based on the number of times it has been executed. Effect of the Invention
[0018] According to the above-described aspects of the present invention, the system can be appropriately started up when a registered user approaches. [Brief description of the drawings]
[0019] [Figure 1] 4 is a view for explaining an overview of HPD processing of the information processing device according to the embodiment. [Diagram 2] 5 is a diagram showing an example of a person detection range of the information processing device according to the embodiment. [Diagram 3] 1 is a flowchart showing an overview of HPD processing according to an embodiment. [Figure 4] FIG. 1 is a perspective view showing an example of the external configuration of an information processing apparatus according to an embodiment. [Diagram 5] FIG. 2 is a diagram showing an example of a hardware configuration of an information processing apparatus according to an embodiment. [Figure 6] FIG. 2 is a block diagram showing an example of a functional configuration of an information processing apparatus according to an embodiment. [Figure 7] 11 is a flowchart showing an example of an HPD process in a standby state according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0020] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. First, an overview of the information processing device according to the present embodiment will be described. The information processing device 1 according to the present embodiment is, for example, a notebook type (clamshell type) PC (Personal Computer). The information processing device 1 may be any type of information processing device, such as a desktop type PC, a tablet type PC, or a smartphone.
[0021] The information processing device 1 can transition between at least a normal operation state (power-on state) and a standby state as the system operation state. The normal operation state is an operation state in which processing can be executed without particular restrictions, and corresponds to, for example, the S0 state defined by ACPI (Advanced Configuration and Power Interface). The standby state is a state in which at least a part of the system processing is restricted. For example, the standby state may be a standby state, a sleep state, or the like, and may be a state equivalent to modern standby in Windows (registered trademark) or the S3 state (sleep state) defined by ACPI. For example, the standby state is an operation state in which power consumption is lower than that of the normal operation state.
[0022] In the following, the transition of the system's operating state from the standby state to the normal operating state may be referred to as "activation." In the standby state, the activity of the operation is generally lower than in the normal operating state, so activating the system of the information processing device 1 activates the operation of the system in the information processing device 1.
[0023] FIG. 1 is a diagram for explaining an outline of the HPD process of the information processing device 1 according to the present embodiment. The information processing device 1 detects a person (i.e., a user) existing in the vicinity of the information processing device 1. This process of detecting the presence of a person is called HPD (Human Presence Detection) process. The information processing device 1 detects the presence or absence of a person by the HPD process, and controls the operation state of the system of the information processing device 1 based on the detection result. For example, as shown in FIG. 1(A), when the information processing device 1 detects a change from a state in which no person is present in front of the information processing device 1 (Absence) to a state in which a person is present (Presence), that is, when it detects that a person has approached the information processing device 1 (Approach), it determines that a user has approached, automatically starts the system, and transitions to a normal operation state. Also, as shown in FIG. 1(B), when a person is present in front of the information processing device 1 (Presence), it determines that a user is present, and continues the normal operation state. Then, when the information processing device 1 detects a change from a state in which a person is present (Presence) in front of the information processing device 1 (front) to a state in which a person is not present (Absence), that is, when the information processing device 1 detects that the person has left the information processing device 1 (Leave), as shown in FIG. 1(C), it determines that the user has left and transitions the system to a standby state.
[0024] The information processing device 1 detects the presence of a person within a predetermined range ahead (on the front side). FIG. 2 is a diagram showing an example of a detection range of a person of the information processing device 1 according to the present embodiment. In the example shown in the figure, a detection range FoV (Field of View: detection viewing angle) in front (front side) of the information processing device 1 is a range in which a person can be detected. For example, the information processing device 1 detects a face image area (hereinafter referred to as a "face area") in which a face is captured from a captured image capturing the front (front side), thereby detecting a person present in front of (in front of) the information processing device 1. The detection range FoV corresponds to an imaging angle of view captured by the information processing device 1. When a face area is detected from a captured image, the information processing device 1 determines that a person is present. On the other hand, when a face area is not detected from a captured image, the information processing device 1 determines that a person is not present.
[0025] Here, if the information processing device 1 starts up the system from the standby state by only detecting a face area from a captured image in the HPD process, the system will also start up if a person other than the authorized user of the information processing device 1 approaches. Therefore, when the information processing device 1 determines that a person is present by detecting a face area from a captured image in the standby state, the information processing device 1 further determines (authenticates) whether or not the person is a registered user (authorized user who uses the information processing device 1). If the information processing device 1 determines that the person is a registered user, the system starts up from the standby state. On the other hand, if the information processing device 1 determines that the user is not a registered user, the system remains in the standby state without starting up.
[0026] A registered user is a user (authorized user) who is registered in advance as a user who uses the information processing device 1. In order to authenticate whether or not a person detected in the HPD processing is a registered user, the information processing device 1 registers feature information based on a facial image of the authorized user as the user ID of the authorized user. The user ID used for authentication in the HPD processing is hereinafter referred to as an "HPD user ID." Moreover, authenticating whether or not a person detected in the HPD processing is a registered user using the HPD user ID is hereinafter referred to as "HPD user authentication."
[0027] The registration of the HPD user ID may be performed by the information processing device 1 using an application (application program) for user registration. For example, the information processing device 1 may execute the application for user registration, capture a face image of the user himself / herself by the user's operation using the executed application, and register (store) feature information based on the captured face image as the HPD user ID. Furthermore, the registration of the HPD user ID may be performed by the information processing device 1 at a predetermined timing without the user's operation. For example, the information processing device 1 may register (store) feature information based on a face image (e.g., a face image facing forward) detected within a predetermined time (e.g., within 5 seconds) after successful authentication in login authentication for permitting login to the system at the time of system startup as the HPD user ID.
[0028] Methods of system login authentication include password authentication, in which the user is authenticated by entering a password from the keyboard, PIN authentication, in which the user is authenticated by entering a PIN (Personal Identification Number), face authentication, in which the user is authenticated by using his or her face, and fingerprint authentication, in which the user is authenticated by using his or her fingerprint.
[0029] Here, when face authentication is used for login authentication of the system, high power consumption is permitted because the system is in operation and highly accurate face authentication is required. On the other hand, when HPD user authentication is performed, it is desirable to keep power consumption as low as possible because the system is in standby. For example, in the case of face authentication in login authentication, a captured image (IR image) captured by an IR (Infrared Rays) camera is used, but in HPD user authentication in the standby state, a captured image (RGB image) captured by an RGB camera (normal visible light camera) that consumes less power than an IR camera is used. Also, the frame rate at which captured images are captured in HPD user authentication is set lower than the frame rate at which captured images are captured in login authentication.
[0030] In this way, the HPD user authentication in the standby state needs to keep power consumption lower than the face authentication in the login authentication, and therefore the recognition rate of the face authentication decreases. If the recognition rate decreases, even if a registered person is correctly determined to be a registered user with a probability of, for example, about 80%, an unregistered person may be erroneously determined to be a registered user with a probability of, for example, about 0 to 40%. If an unregistered person is present for a long period of time, even if a false determination occurs even once during that time, the device will start up, and there is a concern that even an unregistered person may erroneously start up.
[0031] Therefore, the information processing device 1 of this embodiment starts the system from a standby state if authentication by HPD user authentication is successful, but continues the HPD user authentication if authentication by HPD user authentication fails, but limits the number of times that the HPD user authentication is repeatedly executed if authentication failures continue.
[0032] An overview of HPD processing in which the information processing device 1 starts up the system when a registered user is detected using HPD user authentication will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an overview of the HPD processing according to this embodiment.
[0033] The information processing device 1 executes a person detection process (step S11) to detect the presence of a person by detecting a face area (face detection) from a captured image captured in a detection range FoV (see FIG. 2) in a standby state. If the information processing device 1 detects the presence of a person in step S11, the information processing device 1 proceeds to step S13.
[0034] In step S13, the information processing device 1 transitions from person detection processing to HPD user authentication processing. In the HPD user authentication processing, the information processing device 1 detects a face area (face detection) from a captured image captured in the detection range FoV (see FIG. 2), and determines (authenticates) whether or not the detected person is a registered user based on feature information based on the detected face image and a registered HPD user ID (feature information based on a face image of a registered user). If the authentication is successful in step S13 (determines that the detected person is a registered user), the information processing device 1 starts up the system (step S15).
[0035] On the other hand, if the information processing device 1 fails the authentication in step S13 (determines that the detected person is not a registered user), the process proceeds to step S17.
[0036] In step S17, the information processing device 1 determines whether the number of times the HPD user authentication process has been executed due to authentication failure has reached the upper limit. If the information processing device 1 determines that the upper limit has not been reached (NO), it returns to step S13 and executes the HPD user authentication process again. On the other hand, if the information processing device 1 determines that the number of times the HPD user authentication process has been executed due to authentication failure has reached the upper limit (YES), it stops the HPD user authentication process (step S19). The upper limit for the number of times the HPD user authentication process is stopped is set in advance, and is, for example, "10 times." After stopping the HPD user authentication process, the information processing device 1 executes a person detection process.
[0037] In this way, if authentication by the HPD user authentication process fails, the information processing device 1 executes the HPD user authentication process again, and if the HPD user authentication process is executed repeatedly due to authentication failure, the information processing device 1 stops the HPD user authentication process based on the fact that the number of executions has reached an upper limit (a preset number of times).
[0038] This makes it possible for the information processing device 1 to suppress unintentional startup due to erroneous determination that an unregistered person is a registered user. Therefore, the information processing device 1 can appropriately start the system when a registered user approaches.
[0039] Next, the configuration of the information processing device 1 according to this embodiment will be described in detail. [External configuration of information processing device] FIG. 4 is a perspective view showing an example of the external configuration of the information processing device 1 according to the present embodiment. The information processing device 1 includes a first housing 10, a second housing 20, and a hinge mechanism 15. The first housing 10 and the second housing 20 are connected using the hinge mechanism 15. The first housing 10 is rotatable relative to the second housing 20 around a rotation axis defined by the hinge mechanism 15. The opening angle resulting from the rotation of the first housing 10 and the second housing 20 is illustrated as "θ".
[0040] The first housing 10 is also called the A cover or the display housing. The second housing 20 is also called the C cover or the system housing. In the following description, the sides of the first housing 10 and the second housing 20 on which the hinge mechanism 15 is provided are called the sides 10c and 20c, respectively. The sides of the first housing 10 and the second housing 20 opposite the sides 10c and 20c are called the sides 10a and 20a, respectively. In the drawings, the direction from the side 20a to the side 20c is called the "rear", and the direction from the side 20c to the side 20a is called the "front". The right and left sides of the rear are called the "right" and "left", respectively. The left sides of the first housing 10 and the second housing 20 are called the sides 10b and 20b, respectively, and the right sides are called the sides 10d and 20d, respectively. Moreover, a state in which the first housing 10 and the second housing 20 overlap and are completely closed (a state in which the opening angle θ=0°) is referred to as a "closed state." In the closed state, the surfaces of the first housing 10 and the second housing 20 that face each other are referred to as the "inner surfaces," and the surfaces opposite the inner surfaces are referred to as the "outer surfaces." Moreover, a state in which the first housing 10 and the second housing 20 are open relative to the closed state is referred to as an "open state."
[0041] The external appearance of the information processing device 1 shown in FIG. 4 shows an example of an open state. In the open state, the side surface 10a of the first housing 10 and the side surface 20a of the second housing 20 are separated. In the open state, the inner surfaces of the first housing 10 and the second housing 20 are exposed. The open state is one of the states when the user uses the information processing device 1, and is typically used in a state where the opening angle θ is about 100 to 130°. The range of the opening angle θ in the open state can be arbitrarily determined depending on the range of angles that can be rotated by the hinge mechanism 15, etc.
[0042] A display unit 110 is provided on the inner surface of the first housing 10. The display unit 110 is configured to include a liquid crystal display (LCD) or an organic EL (Electro Luminescence) display. An imaging unit 120 is provided in a peripheral region of the display unit 110 on the inner surface of the first housing 10. For example, the imaging unit 120 is disposed on the side surface 20a side of the peripheral region of the display unit 110. Note that the position where the imaging unit 120 is disposed is only an example, and the imaging unit 120 may be disposed in another position as long as it is possible to capture an image in the direction facing the inner surface of the first housing 10 (forward).
[0043] In the open state, the imaging unit 120 captures an image of a predetermined imaging range in a direction (forward) facing the inner surface of the first housing 10. The predetermined imaging range is a range of an angle of view determined by an imaging element of the imaging unit 120 and an optical lens provided in front of the imaging surface of the imaging element, and corresponds to the person (face) detection range FoV shown in Fig. 2. For example, the imaging unit 120 can capture an image including a person (e.g., a user) present in front of (on the front side of) the information processing device 1.
[0044] A power button 140 is provided on the side surface 20b of the second housing 20. The power button 140 is an operator for the user to instruct turning the power on or off, transitioning from a standby state to a normal operation state, transitioning from a normal operation state to a standby state, and the like. A keyboard 151 and a touch pad 153 are provided on the inner surface of the second housing 20 as input devices for accepting user operation inputs. Note that, as the input devices, instead of or in addition to the keyboard 151 and the touch pad 153, a touch sensor may be provided, or a mouse or an external keyboard may be connected. In the case of a configuration in which a touch sensor is provided, an area corresponding to the display surface of the display unit 110 may be configured as a touch panel for accepting operations. The input device may also include a microphone into which voice is input.
[0045] [Hardware configuration of information processing device] 5 is a schematic block diagram showing an example of a hardware configuration of the information processing device 1 according to this embodiment. The information processing device 1 includes a display unit 110, an imaging unit 120, a power button 140, an input device 150, a communication unit 160, a storage unit 170, an EC (Embedded Controller) 200, a face detection unit 210, a main processing unit 300, and a power supply unit 400. The display unit 110 displays display data (images) generated based on system processing executed by the main processing unit 300 and processing of application programs running on the system processing.
[0046] The imaging unit 120 captures an image of an object within a predetermined angle of view (for example, the detection range FoV shown in FIG. 2) in the direction facing the inner surface of the first housing 10 (forward), and outputs the captured image to the face detection unit 210 and the main processing unit 300. For example, the imaging unit 120 includes an RGB camera and an IR (Infrared Rays) camera. The RGB camera is a normal camera that captures images based on visible light. The IR camera is a camera that captures images using infrared rays, and captures images based on the infrared rays reflected from an object by irradiating the object with infrared rays when capturing the image.
[0047] An IR camera, for example, irradiates infrared rays when capturing an image, and therefore consumes more power when capturing an image than an RGB camera. Therefore, when detecting a face area from a captured image and performing face authentication in a standby state, an RGB camera, for example, is used instead of an IR camera, in order to minimize standby power consumption. On the other hand, when detecting a face area from a captured image and performing face authentication in login authentication, an IR camera, for example, is used to improve authentication accuracy. Note that both an IR camera and an RGB camera may be used when performing login authentication by face authentication.
[0048] The power button 140 outputs an operation signal to the EC 200 in response to a user operation. The input device 150 is an input unit that accepts user input, and is configured to include, for example, a keyboard 151 and a touchpad 153. In response to accepting an operation on the keyboard 151 and the touchpad 153, the input device 150 outputs an operation signal indicating the operation content to the EC 200.
[0049] The communication unit 160 is communicably connected to other devices via a wireless or wired communication network, and transmits and receives various data. For example, the communication unit 160 includes a wired LAN interface such as Ethernet (registered trademark) and a wireless LAN interface such as Wi-Fi (registered trademark).
[0050] The storage unit 170 includes storage media such as a hard disk drive (HDD), a solid state drive (SSD), a random access memory (RAM), a read only memory (ROM), etc. The storage unit 170 stores various programs such as an OS, device drivers, and applications, as well as various data acquired by the operation of the programs.
[0051] The power supply unit 400 supplies power to each unit according to the operating state of each unit of the information processing device 1. The power supply unit 400 includes a DC (Direct Current) / DC converter. The DC / DC converter converts the voltage of direct current power supplied from an AC (Alternate Current) / DC adapter or a battery (battery pack) into a voltage required by each unit. The power whose voltage has been converted by the DC / DC converter is supplied to each unit via each power supply system. For example, the power supply unit 400 supplies power to each unit via each power supply system based on a control signal input from the EC 200.
[0052] The EC200 is a microcomputer including a CPU (Central Processing Unit), RAM, ROM, and an I / O (Input / Output) logic circuit. The CPU of the EC200 reads a control program (firmware) prestored in its own ROM, and executes the read control program to fulfill its functions. The EC200 operates independently of the main processing unit 300, controls the operation of the main processing unit 300, and manages its operating state. The EC200 is also connected to a power button 140, an input device 150, a power supply unit 400, and the like.
[0053] For example, the EC 200 communicates with the power supply unit 400 to obtain information on the battery state (such as remaining capacity) from the power supply unit 400 and outputs control signals and the like for controlling the supply of power according to the operating state of each unit of the information processing device 1 to the power supply unit 400. The EC 200 also obtains operation signals from the power button 140 and the input device 150, and outputs to the main processing unit 300 operation signals related to the processing of the main processing unit 300 among the obtained operation signals.
[0054] The face detection unit 210 includes a processor that processes image data of a captured image captured by the imaging unit 120. The face detection unit 210 acquires image data of a captured image captured by the imaging unit 120, and temporarily stores the acquired image data in a memory. The memory that stores the image data may be the system memory 304, or may be a memory (not shown) in the face detection unit 210.
[0055] The face detection unit 210 processes image data of a captured image acquired from the imaging unit 120 to perform face detection processing for detecting a face area from the captured image and face authentication processing for authenticating a face image of the detected face area, thereby executing HPD processing for detecting the presence of a person and authenticating whether or not the person is a registered user. For example, in the HPD processing in the standby state, the face detection unit 210 performs person detection processing for detecting the presence of a person by detecting a face area from a captured image captured by the RGB camera of the imaging unit 120. Also, in the HPD processing in the standby state, when the presence of a person is detected by the person detection processing, the face detection unit 210 performs HPD user authentication processing for detecting a face area from a captured image captured by the RGB camera of the imaging unit 120 and authenticating whether or not the detected person is a registered user by face authentication processing.
[0056] Furthermore, when the system is started from a standby state, the face detection unit 210 performs face detection processing for detecting a face area from an image captured by the IR camera of the imaging unit 120 and face authentication processing for system login authentication. Furthermore, in a normal operating state, the face detection unit 210 may also perform processing using an image captured by the IR camera of the imaging unit 120 when performing HPD processing.
[0057] The face detection unit 210 transmits the detection result of the HPD processing, the authentication result of the face authentication processing for login, and the like to the chipset 303 of the main processing unit 300. The functional configuration related to the HPD processing will be described in detail later.
[0058] The main processing unit 300 is composed of a CPU (Central Processing Unit) 301, a GPU (Graphic Processing Unit) 302, a chipset 303, and a system memory 304, and is capable of executing processing of various application programs on an OS (Operating System) through system processing based on the OS.
[0059] The CPU 301 executes processes by the BIOS, processes by the OS, processes by application programs running on the OS, and the like. The CPU 301 controls the operating state of the system based on instructions from the chipset 303 and the like. For example, the CPU 301 executes a startup process to start the system from a standby state. After startup from the standby state, the CPU 301 also executes a login authentication process to perform user authentication to determine whether or not to permit login to the system, and transitions to a normal operating state if the authentication is successful. For example, the CPU 301 executes an authentication process using face authentication in the login authentication. Note that the CPU 301 may execute authentication processes other than face authentication (for example, password authentication, PIN authentication, fingerprint authentication, and the like) in the login authentication.
[0060] The GPU 302 is connected to the display unit 110. The GPU 302 executes image processing and generates display data under the control of the CPU 301. The GPU 302 outputs the generated display data to the display unit 110.
[0061] The chipset 303 has a function as a memory controller and a function as an I / O controller. For example, the chipset 303 controls the reading and writing of data from the system memory 304, the storage unit 170, etc. by the CPU 301 and the GPU 302. The chipset 303 also controls input and output of data from the communication unit 160, the display unit 110, and the EC 200. The chipset 303 also has a function as a sensor hub. For example, in the HPD processing, the chipset 303 obtains the detection result of the person detection processing, the authentication result of the HPD user authentication processing, the authentication result of the face authentication processing for login, etc. from the face detection unit 210, and issues an instruction on the operating state of the system based on the detection result.
[0062] The system memory 304 is used as a reading area for the programs executed by the CPU 301, a working area for writing processing data, etc. The system memory 304 also temporarily stores image data of images captured by the imaging unit 120.
[0063] The CPU 301, GPU 302, and chipset 303 may be configured as a single integrated processor, or some or each may be configured as individual processors. For example, in a normal operation state, the CPU 301, GPU 302, and chipset 303 are all in operation, but in a standby state, at least a part of the chipset 303 is in operation. In the standby state, at least the functions necessary for the HPD processing at the time of startup are in operation.
[0064] [Functional configuration of information processing device] Next, a functional configuration in which the information processing device 1 controls the operating state of the system through HPD processing will be described.
[0065] FIG. 6 is a block diagram showing an example of a functional configuration of the information processing device 1 according to this embodiment. The information processing device 1 includes a face detection unit 210, a system processing unit 310, and an HPD control processing unit 330. The face detection unit 210 corresponds to the face detection unit 210 shown in FIG. 5, and is a functional configuration realized by executing a program in the face detection unit 210. The system processing unit 310 and the HPD control processing unit 330 are functional configurations realized by the main processing unit 300 shown in FIG. 5 executing an OS and a program running on the OS. For example, the system processing unit 310 is a functional configuration realized by the CPU 301 executing a program of the OS. Also, the HPD control processing unit 330 is a functional configuration realized by the chipset 303 executing a program running on the OS.
[0066] The face detection unit 210 includes a face detection processing unit 211, a face authentication processing unit 212, an HPD user ID registration unit 213, and an HPD processing unit 214. The system processing unit 310 includes an operation control unit 311 and an authentication processing unit 312. The HPD control processing unit 330 includes an operation instruction unit 331 and an authentication result notification unit 332.
[0067] The face detection processing unit 211 reads out image data of captured images captured by the imaging unit 120 at a predetermined frame rate (predetermined frequency) from the system memory 304, and detects a face area from each captured image. As a face detection method, any detection method can be applied, such as a face detection algorithm that detects a face based on facial feature information, or face detection using learning data (trained model) machine-learned based on facial feature information or a face detection library.
[0068] The frame rate at which the imaging unit 120 captures an image is controlled to, for example, 1 fps when performing face detection processing to detect the presence of a person in a standby state, and 4 fps when performing HPD user authentication processing to authenticate whether a detected person is a registered user. The frame rate at which the imaging unit 120 captures an image is controlled to, for example, 15 fps when starting from a standby state and performing login authentication processing, and 1 fps in a normal operating state after the login authentication processing.
[0069] For example, when performing face detection processing for detecting the presence of a person in a standby state, the face detection processing unit 211 detects a face area from a captured image (RGB image) captured at 1 fps using the RGB camera of the imaging unit 120. Also, for example, when performing HPD user authentication processing, the face detection processing unit 211 detects a face area from a captured image (RGB image) captured at 4 fps using the RGB camera of the imaging unit 120. Also, for example, when performing login authentication after startup, the face detection processing unit 211 detects a face area from a captured image (IR image) captured at 15 fps using the IR camera of the imaging unit 120. Note that, the face detection processing unit 211 may detect a face area from a captured image (IR image and RGB image) captured using the IR camera and RGB camera of the imaging unit 120 during login authentication.
[0070] The face authentication processing unit 212 executes face authentication processing for performing face authentication based on a face image in the detected face region. For example, when performing HPD user authentication processing, the face authentication processing unit 212 performs face authentication processing based on feature information based on a face image of a face region detected by the face detection processing unit 211 from a captured image (RGB image) captured at 4 fps using the RGB camera of the imaging unit 120, and feature information based on a face image of a registered user registered as an HPD user ID.
[0071] Furthermore, during login authentication after startup, the face authentication processing unit 212 performs face authentication by comparing a face image detected from a captured image (IR image) captured at 15 fps using the IR camera of the imaging unit 120 with a face image of a user registered in advance as user information (account information) for logging in to the system. Specifically, for example, during login authentication, the face authentication processing unit 212 performs face authentication by comparing feature information based on the face image detected from the captured image (IR image) with feature information based on a face image of a user registered in advance.
[0072] The facial image of the user registered as user information (account information) for logging in is, for example, a facial image detected from an image (IR image) captured at 15 fps using the IR camera of the imaging unit 120 in the facial recognition image registration menu in the system settings.
[0073] The HPD user ID registration unit 213 registers an HPD user ID used for HPD user authentication. For example, the HPD user ID registration unit 213 registers the HPD user ID by storing it in the system memory 304 or a memory (not shown) in the face detection unit 210. As described above, the registration of the HPD user ID may be performed in the information processing device 1 using an application (application program) for user registration, or may be performed by the information processing device 1 at a predetermined timing without a user operation.
[0074] For example, the HPD user ID registration unit 213 registers, as an HPD user ID, feature information based on a face image of the user himself / herself captured by the user's operation in a user registration application. Also, for example, the HPD user ID registration unit 213 may register, as an HPD user ID, feature information based on a face image (e.g., a face image facing forward) detected by the face detection processing unit 211 within a predetermined time (e.g., within 5 seconds) after authentication by the login authentication process is successful. When registering an HPD user ID, the HPD user ID registration unit 213 registers a new HPD user ID if the HPD user ID is not registered, and updates the registered HPD user ID if the HPD user ID is already registered.
[0075] The HPD processing unit 214 outputs information indicating the detection result of the HPD processing based on the detection result of the face detection processing by the face detection processing unit 211 and the authentication result of the face authentication processing by the face authentication processing unit 212. For example, in a standby state, the HPD processing unit 214 executes a person detection process that detects the presence of a person based on the detection result of the face detection processing by the face detection processing unit 211. When the face detection processing unit 211 detects a face area in the captured image (RGB image), the HPD processing unit 214 detects the presence of a person, that is, determines that a person is present (Presence=true). On the other hand, when the face detection processing unit 211 does not detect a face area in the captured image (RGB image), the HPD processing unit 214 determines that no person is present (Presence=false).
[0076] Furthermore, when the presence of a person is detected by the person detection process, the HPD processing unit 214 transitions from the person detection process to the HPD user authentication process. For example, the HPD processing unit 214 judges whether or not the person in the detected face image is a registered user based on the authentication result of the HPD user authentication in which the face authentication processing unit 212 performs face authentication processing based on feature information based on the face image of the face area detected from the captured image (RGB image) by the face detection processing unit 211 and the HPD user ID.
[0077] If the result of the HPD user authentication is a success, the HPD processing unit 214 outputs to the HPD control processing unit 330 presence information indicating that a registered user is present in front of the information processing device 1.
[0078] On the other hand, if the authentication result of the HPD user authentication is authentication failure, the HPD processing unit 214 executes the HPD user authentication process again, and if the authentication failure continues, executes the HPD user authentication process repeatedly. However, if the HPD processing unit 214 executes the HPD user authentication process repeatedly due to authentication failure, the HPD processing unit 214 stops the HPD user authentication process based on the fact that the number of times the HPD user authentication process has been executed has reached a preset number of times (for example, 10 times). When the HPD processing unit 214 stops the HPD user authentication process, it transitions to person detection processing.
[0079] Here, when the HPD processing unit 214 stops the HPD user authentication processing and transitions to person detection processing, it detects the presence of a person, although the person is not a registered user, i.e., it determines that a person is present (Presence = true). If the presence of a person is detected by person detection processing after the HPD user authentication processing is stopped, the HPD processing unit 214 determines whether or not the number of people present has changed. If the HPD processing unit 214 determines that the number of people present has changed, there is a possibility that a registered user is present, so it transitions again from person detection processing to HPD user authentication processing.
[0080] Note that even if the number of people present has changed, if the presence of people is no longer detected, the HPD processing unit 214 determines that no people are present (Presence=false) and continues the person detection processing without transitioning to the HPD user authentication processing. Again, if the presence of a person is detected by the person detection processing, the HPD processing unit 214 determines that a person is present (Presence=true) and transitions from the person detection processing to the HPD user authentication processing.
[0081] When the HPD processing unit 214 detects the presence of a registered user within the detection range FoV, it outputs presence information to the HPD control processing unit 330, but when it does not detect the presence of a person within the detection range FoV, it outputs absence information indicating that no user is present in front of the information processing device 1 to the HPD control processing unit 330. In addition, even when the HPD processing unit 214 detects the presence of a person within the detection range FoV but determines that the person is not a registered user, it also outputs absence information to the HPD control processing unit 330.
[0082] In the standby state, when operation instruction unit 331 acquires presence information output from HPD processing unit 214, it issues an instruction to start the system from the standby state. For example, operation instruction unit 331 outputs start-up instruction information indicating an instruction to start the system from the standby state to operation control unit 311. Furthermore, in the standby state, while operation instruction unit 331 acquires absence information from HPD processing unit 214, it does not issue an instruction to start the system.
[0083] In addition, in the normal operation state, the operation instruction unit 331 issues an instruction to transition the system to a standby state when it acquires absence information from the HPD processing unit 214. For example, the operation instruction unit 331 outputs, to the operation control unit 311, standby instruction information indicating an instruction to transition the system to the standby state.
[0084] When the operation control unit 311 acquires the start-up instruction information output from the operation instruction unit 331, it executes a system program and starts the system from a standby state. After starting the system from the standby state, the operation control unit 311 generates a login authentication event. Then, the operation control unit 311 waits without permitting login until authentication is successful. If authentication is successful, the operation control unit 311 permits login and transitions to a normal operation state.
[0085] In addition, in the normal operation state, when the operation control section 311 receives standby instruction information output from the operation instruction section 331, it transitions the system from the normal operation state to the standby state.
[0086] When a login authentication event occurs, the authentication processing unit 312 executes login authentication processing of the system. For example, the authentication processing unit 312 executes login authentication processing by any one of face authentication, password authentication, PIN authentication, fingerprint authentication, etc. For example, when executing authentication processing by face authentication, the authentication processing unit 312 acquires the authentication result of face authentication from the face detection unit 210, and executes login authentication processing based on the acquired authentication result. The authentication processing unit 312 determines that the user is a legitimate user if the authentication result of the login authentication processing is successful, and determines that the user is not a legitimate user if the authentication fails.
[0087] In the case of password authentication or PIN authentication, the authentication processing unit 312 acquires an operation signal based on a user's operation on the keyboard 151 via the EC 200. Then, based on the acquired operation signal, the authentication processing unit 312 executes the authentication process by comparing the password or PIN entered by the user's operation with a password or PIN registered in advance. In the case of fingerprint authentication, the authentication processing unit 312 executes the authentication process by comparing a fingerprint acquired using a fingerprint sensor (not shown) with a fingerprint registered in advance.
[0088] The authentication result notification unit 332 may notify the face detection unit 210 of the authentication result of the login authentication by the authentication processing unit 312. Then, the HPD user ID registration unit 213 of the face detection unit 210 may use the notification of the authentication result of the login authentication as a trigger to register, as an HPD user ID, feature information based on a face image taken when facing forward within a predetermined time (e.g., within 5 seconds) after authentication by the login authentication process is successful.
[0089] [HPD processing operation] Next, the operation of the HPD process in the standby state will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the HPD process in the standby state according to this embodiment.
[0090] (Step S101) The face detection unit 210 acquires a captured image (RGB image) captured using the RGB camera of the imaging unit 120 in a standby state. For example, the face detection unit 210 acquires a captured image (RGB image) captured by the imaging unit 120 at a frame rate of 1 fps. Then, the face detection unit 210 executes a person detection process to detect the presence of a person by detecting a face area from the captured image (RGB image) for each frame. Here, it is assumed that no person is present (Presence=false) initially in the standby state. Then, the process proceeds to step S103.
[0091] (Step S103) The face detection unit 210 determines whether or not a person is detected by the person detection process in step S101. If the face detection unit 210 does not detect a face area in the captured image (RGB image), it determines that no person is present (Presence = false) (NO) and returns to the process of step S101. On the other hand, if the face detection unit 210 detects a face area in the captured image (RGB image), it determines that a person is present (Presence = true) (YES) and proceeds to the process of step S105.
[0092] (Step S105) The face detection unit 210 sets a counter that counts the number of times n that the HPD user authentication process has been executed to "n=0" and starts counting. Then, the process proceeds to step S107.
[0093] (Step S107) The face detection unit 210 switches the frame rate of the imaging unit 120 to 4 fps, and transitions from person detection processing to HPD user authentication processing. The face detection unit 210 acquires a captured image (RGB image) captured by the imaging unit 120 at a frame rate of 4 fps. The face detection unit 210 detects a face area from the captured image (RGB image) for each frame, and authenticates whether or not the person in the detected face image is a registered user based on feature information based on the detected face image and an HPD user ID (feature information based on a face image of a registered user). Then, the process proceeds to step S109.
[0094] (Step S109) The face detection unit 210 judges whether or not the authentication result of the HPD user authentication process in step S107 is a successful authentication.) If the face detection unit 210 judges that the authentication is successful (YES), the process proceeds to step S111. On the other hand, if the face detection unit 210 judges that the authentication is unsuccessful (NO), the process proceeds to step S115.
[0095] (Step S111) If it is determined in step S109 that the authentication is successful, face detection unit 210 outputs presence information to HPD control processing unit 330. On acquiring the presence information output from face detection unit 210, HPD control processing unit 330 outputs start-up instruction information indicating an instruction to start the system from a standby state to system processing unit 310 as a start-up instruction by HPD processing. On acquiring the start-up instruction information output from HPD control processing unit 330, system processing unit 310 executes a system program to start the system from a standby state.
[0096] If there is a startup instruction other than the startup instruction by the HPD processing, the system processing unit 310 suspends the HPD processing in this standby state and starts up the system from scratch. A startup instruction other than the startup instruction by the HPD processing is, for example, an input (operation) to a HID (Human Interface Device) such as the input device 150 or the power button 140.
[0097] (Step S113) After starting the system from the standby state in step S111, the system processing unit 310 executes login authentication processing. For example, the system processing unit 310 executes authentication processing using any one of face authentication, password authentication, PIN authentication, and fingerprint authentication. If authentication is successful in the login authentication processing, the system processing unit 310 permits login and transitions to a normal operation state.
[0098] (Step S115) If it is determined in step S109 that the authentication has failed, the face detection unit 210 adds 1 to the counter that counts the number of times n that the HPD user authentication process has been executed (n=n+1), and proceeds to the process of step S117.
[0099] (Step S117) The face detection unit 210 determines whether the number of executions n of the HPD user authentication process is less than 10 (n<10). If the face detection unit 210 determines that the number of executions n of the HPD user authentication process is less than 10 (YES), the process returns to step S107 and executes the HPD user authentication process again. On the other hand, if the face detection unit 210 determines that the number of executions n of the HPD user authentication process has reached 10 (NO), the process proceeds to step S119.
[0100] (Step S119) The face detection unit 210 stops the HPD user authentication process, switches the frame rate of the imaging unit 120 to 1 fps, and proceeds to person detection process. The face detection unit 210 acquires a captured image (RGB image) captured by the imaging unit 120 at a frame rate of 1 fps. The face detection unit 210 then executes person detection process to detect the presence of a person by detecting a face area from within the captured image (RGB image) for each frame. Here, a person other than a registered user is present (Presence = true). Then, the process proceeds to step S121.
[0101] (Step S121) The face detection unit 210 determines whether or not the number of people detected in step S119 has changed. If the face detection unit 210 determines that the number of people detected has not changed (NO), the process returns to step S119 and executes the person detection process again. On the other hand, if the face detection unit 210 determines that the number of people detected has changed (YES), the process proceeds to step S123.
[0102] (Step S123) The face detection unit 210 determines whether the number of people detected in step S119 is 1 or more. If the face detection unit 210 determines that the number of people detected is 1 or more (YES), it determines that there is a possibility that a registered user exists, and returns to the process of step S105, sets the number of times the HPD user authentication process is executed to "n=0" and restarts counting, proceeds to the process of step S107, and executes the HPD user authentication process again. On the other hand, if the number of people detected becomes 0 (i.e., people no longer exist) (NO), the face detection unit 210 returns to the process of step S101 and continues executing the person detection process in a state where no people exist (Presence=false).
[0103] In the example of the HPD processing shown in FIG. 7, an example has been described in which the HPD user authentication processing is stopped when the number of times the HPD user authentication processing has been executed since the presence of a person was detected by the person detection processing reaches 10 times. However, the number of times that the HPD user authentication processing is stopped is not limited to 10 times, and can be set to any number.
[0104] [Summary of the embodiment] As described above, the information processing device 1 according to this embodiment includes a system memory 304 (an example of a memory) that temporarily stores a system program, a face detection unit 210 (an example of a first processor), and a main processing unit 300 (for example, a CPU 301, an example of a second processor). The face detection unit 210 detects a region (face region) of a face image in which a face is captured from an image captured by the imaging unit 120, and executes an HPD user authentication process (an example of a face authentication process) that authenticates whether or not a person in the detected face image is a registered user based on feature information (an example of information) based on the detected face image and an HPD user ID (feature information (an example of information) based on a face image of a registered user). The main processing unit 300 starts the system from a standby state by executing a system program based on the success of authentication by the HPD user authentication process. Furthermore, if authentication by the HPD user authentication process fails, the face detection unit 210 executes the HPD user authentication process again, and if the HPD user authentication process is executed repeatedly due to failure of authentication by the HPD user authentication process, the face detection unit 210 stops the HPD user authentication process based on the number of times the HPD user authentication process has been executed.
[0105] As a result, when authentication by the HPD user authentication process fails, the information processing device 1 does not continue to execute the HPD user authentication process even if authentication failures continue, but stops the process based on the number of times it has been executed, so that even if an unregistered person is in front of the information processing device 1 for a long period of time, it is possible to prevent the information processing device 1 from erroneously determining that the person is a registered user and unintentionally starting up. Therefore, the information processing device 1 can properly start up the system when a registered user approaches.
[0106] For example, the face detection unit 210 executes a person detection process to detect the presence of a person by detecting an area (face area) of a face image in which a face is captured from a captured image, and when the presence of a person is detected by the person detection process, the process transitions from the person detection process to the HPD user authentication process. Also, the face detection unit 210 stops the HPD user authentication process when the number of times the HPD user authentication process has been executed since the presence of a person was detected by the person detection process has reached a preset number (e.g., 10 times).
[0107] As a result, the information processing device 1 executes the HPD user authentication process when a person is present in front of the information processing device 1, and stops the HPD user authentication process based on the number of times it has been executed rather than continuing to execute the process even if authentication failures continue, so that even if an unregistered person is in front of the information processing device 1 for a long period of time, it is possible to prevent the information processing device 1 from being erroneously determined to be a registered user and being unintentionally started up. Therefore, the information processing device 1 can appropriately start up the system when a registered user approaches.
[0108] Furthermore, when the face detection unit 210 stops the HPD user authentication process due to a failure in the HPD user authentication process, the process proceeds to human detection process.
[0109] This allows the information processing device 1 to detect the situation of a person present in front of the information processing device 1 after an unregistered person is in front of the information processing device 1 and the HPD user authentication process is stopped.
[0110] Furthermore, if the presence of a person is detected by person detection processing after the HPD user authentication processing is stopped, the face detection unit 210 determines whether the number of people present has changed, and if it determines that the number of people present has changed, transitions again from person detection processing to HPD user authentication processing.
[0111] As a result, after stopping the HPD user authentication process, if the number of people in front of the information processing device 1 changes, there is a possibility that a registered user is present, so the information processing device 1 can determine again whether a registered user is present by performing the HPD user authentication process.
[0112] Furthermore, if the presence of a person is no longer detected by the person detection processing after the HPD user authentication processing is stopped, the face detection unit 210 continues the person detection processing without transitioning to the HPD user authentication processing, and if the presence of a person is detected, the face detection unit 210 transitions from the person detection processing to the HPD user authentication processing.
[0113] As a result, after stopping the HPD user authentication processing, if the presence of a person is no longer detected even if the number of people in front of the information processing device 1 has changed, the information processing device 1 can continue the person detection processing without performing the HPD user authentication processing unnecessarily.
[0114] In addition, the human detection process consumes less power than the HPD user authentication process. but Low processing,
[0115] As a result, the information processing device 1 does not execute the HPD user authentication process unnecessarily in the standby state, which not only prevents the user from being erroneously determined to be a registered user, but also reduces power consumption.
[0116] For example, the frame rate for detecting a region (face region) of a face image in which a face is captured from a captured image is lower in the person detection process than in the HPD user authentication process. The face detection unit 210 switches the frame rate when transitioning from the person detection process to the HPD user authentication process and when transitioning from the HPD user authentication process to the person detection process.
[0117] As a result, when the information processing device 1 stops the HPD user authentication process and transitions to the person detection process, the information processing device 1 can reduce power consumption by lowering the frame rate. Also, when executing the HPD user authentication process, the information processing device 1 can perform the face recognition process by increasing the frame rate compared to the person detection process.
[0118] After the system is started, the main processing unit 300 permits login to the system based on a face image detected from an image captured by the imaging unit 120. mosquito In this case, the HPD user authentication process executed in the standby state before the system is started consumes less power than the login authentication process. but It is a low processing.
[0119] This allows the information processing device 1 to perform HPD user authentication processing (face authentication processing) while minimizing power consumption in a standby state, and to perform highly accurate face authentication in the login authentication processing after the system is started up.
[0120] For example, the HPD user authentication process, which is executed in the standby state before the system is started, has a frame rate of 100 times faster than the login authentication process when detecting the area of the face image from the captured image. The frame rate of the captured image captured by the imaging unit 120 Lower than.
[0121] As a result, the information processing device 1 can perform HPD user authentication processing (face authentication processing) at a low frame rate in standby state with power consumption as low as possible, and perform highly accurate face authentication at a high frame rate during login authentication processing after system startup.
[0122] Furthermore, the face detection unit 210 executes a user registration process for registering feature information (an example of information) based on a face image of a user who uses the information processing device 1 (for example, registering as an HPD user ID).
[0123] This enables the information processing device 1 to determine whether or not the person standing in front of the information processing device 1 is a legitimate user of the information processing device 1.
[0124] Further, in the control method of the information processing device 1 according to the present embodiment, which includes a system memory 304 (an example of a memory) that temporarily stores a system program, a face detection unit 210 (an example of a first processor), and a main processing unit 300 (e.g., a CPU 301, an example of a second processor), the face detection unit 210 detects a region (face region) of a face image in which a face is captured from an image captured by the imaging unit 120, and determines whether or not a person in the detected face image is a registered user based on feature information (an example of information) based on the detected face image and an HPD user ID (feature information (an example of information) based on a face image of a registered user). the step of the main processing unit 300 starting up the system from a standby state by executing a system program based on the success of authentication by the HPD user authentication processing; the step of the face detection unit 210 executing the HPD user authentication processing again if authentication by the HPD user authentication processing has failed; and the step of the face detection unit 210 stopping the HPD user authentication processing based on the number of times the HPD user authentication processing has been executed if the HPD user authentication processing has been repeatedly executed due to failure of authentication by the HPD user authentication processing.
[0125] As a result, when authentication by the HPD user authentication process fails, the control method in the information processing device 1 stops the HPD user authentication process based on the number of times it has been executed rather than continuing to execute the process even if authentication failures continue, so that even if an unregistered person is in front of the information processing device 1 for a long period of time, it is possible to prevent the system from being erroneously determined to be a registered user and being unintentionally started up. Therefore, the control method in the information processing device 1 can properly start up the system when a registered user approaches.
[0126] Although the embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to the above embodiment, and the present invention also includes designs that do not deviate from the gist of the present invention. For example, the configurations described in the above embodiment can be combined in any combination.
[0127] The imaging unit 120 may include either an IR camera or an RGB camera. For example, an IR camera may be used in both the HPD process and the login authentication process, or an RGB camera may be used in both the HPD process and the login authentication process.
[0128] Also, the frame rate of the imaging unit 120 in each operating state and process is an example and is not limited to the above-mentioned frame rate example. For example, the frame rate when performing the person detection process and the HPD user authentication process in the standby state is preferably set lower than the frame rate when performing the login process after startup, but the above-mentioned frame rate value is an example and is not limited to this example.
[0129] In the above embodiment, the configuration example in which the imaging unit 120 is built into the information processing device 1 has been described, but the present invention is not limited to this. For example, the imaging unit 120 does not have to be built into the information processing device 1, and may be configured to be attachable to the information processing device 1 (for example, any one of the side surfaces 10a, 10b, 10c, etc.) as an external accessory of the information processing device 1, and may be communicatively connected to the information processing device 1 wirelessly or via a wire.
[0130] Furthermore, the CPU 301 and the chipset 303 (an example of a second processor) may be configured as separate processors, or may be integrated into a single processor.
[0131] In the above embodiment, an example has been shown in which the face detection unit 210 is provided separately from the chipset 303, but a part or all of the face detection unit 210 may be provided in the chipset 303, or in a processor integrated with the chipset 303. The face detection unit 210, the chipset 303, and the CPU 301 may be integrated into a single processor. The face detection unit 210 may be provided in part or all of the EC 200.
[0132] The above-mentioned standby state may include a hibernation state, a power-off state, etc. The hibernation state corresponds to, for example, the S4 state defined by ACPI. The power-off state corresponds to, for example, the S5 state (shutdown state) defined by ACPI. Among the standby states, the standby state, sleep state, hibernation state, power-off state, etc. are states in which power consumption is lower (states in which power consumption is reduced) than in the normal operating state.
[0133] The information processing device 1 described above has a computer system inside. A program for implementing the functions of each component of the information processing device 1 described above may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed to perform processing in each component of the information processing device 1 described above. Here, "reading a program recorded on a recording medium into a computer system and executing it" includes installing the program into a computer system. The "computer system" here includes hardware such as an OS and peripheral devices. The "computer system" may also include multiple computer devices connected via a network including a communication line such as the Internet, a WAN, a LAN, or a dedicated line. The "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, and a storage device such as a hard disk built into a computer system. In this way, the recording medium storing the program may be a non-transient recording medium such as a CD-ROM.
[0134] The recording medium also includes a recording medium installed inside or outside and accessible from a distribution server to distribute the program. The program may be divided into a plurality of parts, downloaded at different times, and then combined by each component of the information processing device 1, or each divided program may be distributed by a different distribution server. Furthermore, the "computer-readable recording medium" includes a recording medium that holds a program for a certain period of time, such as a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network. The program may be a recording medium for implementing part of the above-mentioned functions. Furthermore, the program may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system.
[0135] In addition, some or all of the functions of the information processing device 1 in the above-mentioned embodiment may be realized as an integrated circuit such as an LSI (Large Scale Integration). Each function may be individually processed, or some or all of the functions may be integrated into a processor. The integrated circuit method is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. In addition, when an integrated circuit technology that replaces LSI appears due to the progress of semiconductor technology, an integrated circuit based on that technology may be used. [Explanation of symbols]
[0136] 1 Information processing device, 10 First housing, 20 Second housing, 15 Hinge mechanism, 110 Display unit, 120 Imaging unit, 140 Power button, 150 Input device, 151 Keyboard, 153 Touch pad, 160 Communication unit, 170 Memory unit, 200 EC, 210 Face detection unit, 211 Face detection processing unit, 212 Face authentication processing unit, 213 HPD user ID registration unit, 214 HPD processing unit, 300 Main processing unit, 301 CPU, 302 GPU, 303 Chipset, 304 System memory, 310 System processing unit, 311 Operation control unit, 312 Authentication processing unit, 330 HPD control processing unit, 331 Operation instruction unit, 332 Authentication result notification unit, 400 Power supply unit
Claims
1. A memory for temporarily storing system programs; a first processor that executes a face recognition process to detect a face image area in which a face is captured from an image captured by an imaging unit, and to authenticate whether or not a person in the detected face image is a registered user based on information based on the detected face image and information based on a face image of a registered user; a second processor that starts the system from a standby state by executing a program of the system based on the success of the authentication by the face authentication process; Equipped with The first processor, a person detection process is executed to detect the presence of a person by detecting a face image area in which a face is captured from the captured image, and when the presence of a person is detected by the person detection process, the process is shifted from the person detection process to the face authentication process; if authentication by the face authentication process fails, execute the face authentication process again, and if the face authentication process is repeatedly executed due to the failure of authentication by the face authentication process, stop the face authentication process based on the number of times the face authentication process has been executed and based on the number of times that the face authentication process has been executed since the presence of a person was detected by the person detection process reaching a preset number of times, When the face recognition process is stopped due to a failure of the face recognition process, the process proceeds to the person detection process; if the presence of a person is detected by the person detection process after the face recognition process is stopped, it is determined whether or not the number of people present has changed, and if it is determined that the number of people present has changed, the process transitions from the person detection process to the face recognition process again. Information processing device.
2. The first processor, If the presence of a person is no longer detected by the person detection process after the face recognition process is stopped, the person detection process is continued without transitioning to the face recognition process, and if the presence of a person is detected, the person detection process is transitioned from the person detection process to the face recognition process. The information processing device according to claim 1 .
3. The person detection process consumes less power than the face recognition process. The information processing device according to claim 1 .
4. the person detection process has a lower frame rate when detecting a face image area in which a face is captured from the captured image than the face authentication process; The first processor, switching a frame rate when transitioning from the person detection processing to the face authentication processing and when transitioning from the face authentication processing to the person detection processing; The information processing device according to claim 1 .
5. The second processor After the system is started, a login authentication process is executed to authenticate whether or not to permit login to the system based on a face image detected from an image captured by the imaging unit; The face authentication process executed in the standby state before the system is started consumes less power than the login authentication process. The information processing device according to claim 1 .
6. the face authentication process executed in the standby state before the start-up of the system has a frame rate for detecting a face image area in which a face is captured from the captured image that is lower than a frame rate of the captured image captured by the imaging unit in the login authentication process; The information processing device according to claim 5 .
7. The first processor, executing a user registration process for registering information based on a face image of a user who uses the information processing device; The information processing device according to claim 1 .
8. A control method for an information processing device including a memory for temporarily storing a system program, a first processor, and a second processor, comprising: a step of executing a face recognition process by the first processor, in which an area of a face image in which a face is captured is detected from an image captured by an imaging unit, and authenticating whether or not a person in the detected face image is a registered user based on information based on the detected face image and information based on a face image of a registered user; a step of starting up the system from a standby state by executing a program of the system by the second processor based on the success of the authentication by the face authentication processing; a step in which the first processor executes a person detection process for detecting the presence of a person by detecting a face image area in which a face is captured from the captured image, and when the presence of a person is detected by the person detection process, transitions from the person detection process to the face authentication process; a step of executing the face authentication process again by the first processor when authentication by the face authentication process has failed; When the first processor repeatedly executes the face authentication process due to a failure of authentication by the face authentication process, the first processor stops the face authentication process based on the number of times the face authentication process has been executed, based on the number of times that the face authentication process has been executed since the presence of a person was detected by the person detection process reaching a preset number of times; a step of transitioning to the person detection process when the first processor stops the face recognition process due to a failure of authentication by the face recognition process; a step in which the first processor determines whether or not the number of people present has changed when the presence of a person has been detected by the person detection process after the face recognition process has been stopped, and when it is determined that the number of people present has changed, transitions again from the person detection process to the face recognition process; A control method comprising:
Citation Information
Patent Citations
Computer system, personal authentication method for the same and image processing method
JP2001014463A
Authentication device and authentication method
JP2007122493A
Imaging apparatus
JP2014180024A
Instrument with face authentication function
JP2016148895A
Information processing apparatus and information processing method
JP2019174855A
