KR20160015704A - System and method for recognition acquaintance by wearable glass device - Google Patents

Abstract

The present invention relates to an acquaintance recognition system using a glass type wearable device and a recognition method thereof. The acquaintance recognition method using the glass type wearable device according to an embodiment of the present invention includes: a step (S100) of acquiring a video or an image including a face of an opponent; a step (S200) of extracting a face area from the video or the image; a step (S300) of extracting feature information from the extracted face area; a step (S400) of recognizing an acquaintance corresponding to the opponent, by judging by comparing the feature information of a stored acquaintance face with the extracted feature information; and a step (S500) of informing the acquaintance corresponding to the opponent of a user. According to the present invention, in case the user can not remember suddenly who a person acknowledging the user is, the method of the present invention can remove a situation that the user becomes sorry for not remembering the acquaintance by informing the user who the opponent is.

Description

TECHNICAL FIELD [0001] The present invention relates to a recognition system and a recognition method using a wearable device of a glass type,

The present invention relates to a recognition system and a recognition method using a wearable device of a glass type. More particularly, the present invention relates to a system and a method for acquiring a facial image or an image of a partner to recognize whether the face image or image is known by the user.

Recently wearable devices are emerging. It has appeared in the form of glasses that are linked to smart phones, and some forms that can operate independently without a smartphone are also emerging.

People sometimes meet people pretending to know themselves on the street. At this time, if you do not recognize the other person, you may get confused or embarrassed. Also, the face of the other person's memory is remembered, but the name of the other person can not be remembered.

An object of the present invention is to provide a method and apparatus for acquiring a face image or an image using a wearable device of a glass type for acquiring a facial image or an image of a counterpart and comparing a face in the image or image with a face of a stored acquaintance, System and method of recognition.

According to another aspect of the present invention, there is provided a recognition method using a glass-like wearable device, comprising: acquiring an image or an image including a face of a partner; Extracting a face region from the image or image; Extracting feature information from the extracted face region; Comparing the extracted feature information with feature information of a face of a user and recognizing an acquaintance corresponding to the partner; And notifying a user of an acquaintance corresponding to the other party.

In addition, the step of comparing the extracted feature information with the feature information of the stored face information and determining an acquaintance corresponding to the opponent may be performed by a control unit of the glass wearable device or an external server .

In addition, the step of informing the user of an acquaintance of the other party may include a method of displaying a photograph or name of an acquaintance corresponding to the opponent on a display, a method of announcing the name of an acquaintance corresponding to the opponent by acoustical output, A method of displaying a photograph or name of an acquaintance corresponding to the other party on the display of the external device interlocked with the wearable device.

In addition, the feature information of the stored face may be extracted from a photograph of an acquaintance stored in an external server or a storage unit of the glass-like wearable device, and the feature information may be stored in the external And searching for an acquaintance including the same feature information as the feature information of the face image of the opposite party extracted by the server or the glass-like wearable device.

The method may further include the step of providing the user with information on an acquaintance corresponding to the other party.

The acquaintance recognition system using the glass-like wearable device according to another embodiment of the present invention acquires a video or image including a face of the other party, extracts feature information from the face of the other party in the video or image, A wearable device of a glass type for receiving data related to the other party from an external server and notifying the user of the data; And an external server for storing a face image of the user and obtaining an acquaintance corresponding to the other party based on the extracted feature information and providing the acquaintance to the wearable device via wireless communication.

In addition, the glass-type wearable device may further include: a first camera that acquires a video or an image including a face of the other party; A wireless communication unit for exchanging information with the external server; A face region extracting unit for extracting a face region of the opposite side in the image or the image, and a feature extracting unit extracting the feature information from the extracted face region; And an output unit for informing the user of an acquaintance corresponding to the other party.

Also, the output unit may include a display unit for displaying a photograph or name of an acquaintance corresponding to the other party; Or an acoustic output unit for notifying the name of an acquaintance corresponding to the other party.

The external server may further include: a storage unit for storing a face image of the user; A wireless communication unit for exchanging information with the wearable device; And a face recognizing unit for recognizing an acquaintance corresponding to the other party based on the received facial feature information.

In addition, the storage unit may store information on the acquaintance of the user.

According to another aspect of the present invention, there is provided an acquaintance recognition system using a glass-like wearable device, comprising: a first camera for acquiring an image or an image including a face of the other party; A face region extracting unit for extracting a face region of the opposite side in the image or image, a feature extracting unit for extracting the feature information from the extracted face region, and a face recognizing unit for recognizing an acquaintance corresponding to the opposite side based on the feature information ; A storage unit for storing a face photograph of the user; And an output unit for informing the user of an acquaintance corresponding to the other party.

Also, the output unit may include a display unit for displaying a photograph or name of an acquaintance corresponding to the other party; Or an acoustic output unit for notifying the name of an acquaintance corresponding to the other party.

The storage unit may store information on a user's acquaintance; And the output unit may provide the user with information on an acquaintance corresponding to the other party.

The information on the acquaintance may include at least one of a job, a school, an age, a background in acquaintance, interest, and common knowledge.

According to the present invention, when the user suddenly does not remember who pretends to know the user, the present invention can inform the user of who the other party is and can eliminate the situation of being sorry or embarrassed because they can not remember their acquaintances.

In addition, even if the face of the other party is remembered but the name is not remembered, the name information of the other party can be quickly provided, thereby preventing a problem that may occur due to the failure to memorize the name.

Also, on the streets, it is often unclear whether you are a person you know and can not pretend to know. In this case, it is possible to judge whether the user knows only if the image or the image including the face of the other party is obtained in the vicinity of the other party.

That is, if a face photograph and personal information of an acquaintance are stored in advance in the storage unit of the glass-like wearable device or the storage unit of the external server, the present invention can recognize the other party in real time by the present invention.

1 is a configuration diagram of a glass-type wearable device system according to an embodiment of the present invention
2 is a flow chart of a recognition method using a wearable device of a glass type according to an embodiment of the present invention
3 is a perspective view of a wearable device of a glass type according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating an example of an acquaintance of a corresponding party through a display unit; FIG.
FIG. 5 is a diagram showing a configuration of a friend recognizing system using a glass-type wearable device and an external server according to an embodiment of the present invention
6 is a configuration diagram of a recognition system using a wearable device of a glass type according to an embodiment of the present invention

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms " comprises "and / or" comprising "used in the specification do not exclude the presence or addition of one or more other elements in addition to the stated element.

FIG. 1 is a configuration diagram of a glass-type wearable device system according to an embodiment of the present invention, and FIG. 2 is a flowchart of a method of recognizing a friend using a glass-type wearable device according to an embodiment of the present invention. FIG. 3 is a perspective view of a wearable device of a glass type according to an exemplary embodiment of the present invention, and FIG. 4 is an exemplary view showing an acquaintance of a partner through a display unit. FIG. 5 is a configuration diagram of a recognition system using a glass-type wearable device and an external server according to an embodiment of the present invention, FIG. 6 is a diagram illustrating a configuration of a recognition system using a glass- .

1 to 5 show a system 100, a user input unit 110, an application 111, a keyboard 112, a voice input unit 113, a touch pad 114, a GPS signal unit 115, A camera 120, a first camera 121, a second camera 122, a third camera 123, a sensing unit 130, a gyro sensor 131, an acceleration sensor 132, a pressure sensor 133, an iris recognition sensor 134, a heartbeat detection sensor 135, an electromyogram sensor 136, an information processing module 210, a voice recognition unit 220, a situation evaluation module 230, An output unit 300, a display unit 310, an audio output unit 320, an alarm unit 330, a haptic module 340, Lt; / RTI >

The system 100 of the wearable wearable device according to an embodiment of the present invention includes a camera unit 120, an audio input unit 113, a user input unit 110, a sensing unit 130, an output unit 300, A communication unit 250, a memory 260, an interface unit 270, a control unit 210, a situation evaluation module 230, a power supply unit, and a voice recognition unit 220.

The camera unit 120 is for inputting video signals or image signals, and may be provided in accordance with a configuration of the device. The camera unit 120 processes an image frame such as a still image or a moving image obtained by the image sensor in the video communication mode or the photographing mode. The processed image frame can be displayed on the display unit 310. [ The image frame processed by the camera unit 120 may be stored in the memory 260 or transmitted to the outside through the wireless communication unit 250. [ When an image signal or a video signal is used as an input for information processing, the image signal and the video signal are transmitted to the control unit 210.

The voice input unit 113 is for inputting voice signals and may include a microphone and the like. The microphone receives an external acoustic signal by a microphone in a communication mode, a recording mode, a voice recognition mode, and the like and processes it as electrical voice data. The processed voice data can be converted into a form that can be transmitted to the mobile communication base station through the mobile communication unit and output when the voice data is in the call mode. A variety of noise canceling algorithms may be used to remove the noise generated by the microphone in receiving an external acoustic signal.

The user input unit 110 generates key input data that the user inputs for controlling the operation of the device. The user input unit 110 may include a key pad, a keyboard, a dome switch, a touch pad (static / static), a jog wheel, a jog switch, and a finger mouse. Particularly, when the touch pad has a mutual layer structure with the display unit 310 described later, it can be called a touch screen.

The sensing unit 130 senses the current state of the device such as the open / close state of the device, the position of the device, the presence or absence of the user, and generates a sensing signal for controlling the operation of the device. In addition, the sensing unit 130 may function as an input unit for receiving an input signal for information processing of a device, and may perform various sensing functions such as recognition of connection to an external device.

The sensing unit 130 may include a proximity sensor, a pressure sensor 133, a motion sensor, a fingerprint recognition sensor, an iris recognition sensor 134, a heartbeat detection sensor 135, a skin temperature sensor, And the like.

The proximity sensor makes it possible to detect the presence of an object to be approached or nearby, without mechanical contact. The proximity sensor can detect a nearby object by using the change of the alternating magnetic field or the change of the static magnetic field, or by using the change rate of the capacitance. The proximity sensor may be equipped with two or more sensors according to the configuration.

The pressure sensor 133 can detect whether or not pressure is applied to the device, the magnitude of the pressure, and the like. The pressure sensor 133 may be installed in a part of the device where the pressure needs to be detected depending on the use environment. When the pressure sensor 133 is installed on the display unit 310, a touch input through the display unit 310 and a pressure applied by the touch input The pressure touch input can be identified. Also, according to the signal output from the pressure sensor 133, the magnitude of the pressure applied to the display unit 310 at the time of pressure touch input can be known.

The motion sensor includes at least one of an acceleration sensor 132, a gyro sensor 131, and a geomagnetic sensor, and detects the position and movement of the device using the sensor. The acceleration sensor 132, which can be used for a motion sensor, is a device that converts an acceleration change in one direction into an electric signal and is widely used along with the development of MEMS (micro-electromechanical systems) technology. The acceleration sensor 132 includes a gravity sensor that recognizes a change in gravitational acceleration. Further, the gyro sensor 131 is a sensor for measuring the angular velocity, and can sense the direction of rotation with respect to the reference direction.

The heartbeat detection sensor 135 measures changes in the optical blood flow due to changes in the thickness of the blood vessel caused by the heartbeat in order to collect emotion signals. The skin temperature sensor measures the skin temperature as the resistance value changes in response to the temperature change. The skin resistance sensor measures the skin's electrical resistance.

The iris recognition sensor 134 performs a function of recognizing a person using iris information of an eye having a characteristic unique to each person. The human iris is completed after 18 months of age, and the circular iris pattern, which is raised near the medial side of the iris, is almost unchanged once determined, and the shape of each person is different. Therefore, iris recognition is the application of information technology to security for information of different iris characteristics. That is, it is an authentication method developed to identify people by analyzing the shape and color of iris and the morphology of retinal capillaries.

The iris recognition sensor 134 encodes a pattern of iris and converts it into a video signal to compare and judge. The general operation principle is as follows. First, when the user's eye is aligned with the mirror located at the center of the iris recognizer at a certain distance, the infrared camera adjusts the focus through the zoom lens. After the iris camera images the user's iris as a photo, the iris recognition algorithm analyzes the iris pattern of the iris region to generate iris codes unique to the user. Finally, a comparison search is performed at the same time that the iris code is registered in the database.

The output unit 300 is for outputting an audio signal, a video signal, or an alarm signal. The output unit 300 may include a display unit 310, an audio output module, an alarm unit 330, a haptic module 340, and the like.

The display unit 310 displays and outputs information processed in the device. For example, when the device is in the call mode, a UI (User Interface) or GUI (Graphic User Interface) associated with the call is displayed. When the device is in the video communication mode or the photographing mode, the captured or received image can be displayed individually or simultaneously, and the UI and the GUI are displayed.

Meanwhile, as described above, when the display unit 310 and the touch pad have a mutual layer structure to constitute a touch screen, the display unit 310 can be used as an input device in addition to the output device. If the display unit 310 is configured as a touch screen, it may include a touch screen panel, a touch screen panel controller, and the like.

In addition, the display unit 310 may be a liquid crystal display, a thin film transistor-liquid crystal display, an organic light-emitting diode, a flexible display, a three-dimensional display (3D display). There may be two or more display units 310 depending on the implementation type of the device. For example, the device may include an external display unit 310 and an internal display unit 310 at the same time.

The display unit 310 may be implemented as a head up display (HUD), a head mounted display (HMD), or the like. HMD (Head Mounted Display) is an image display device that allows you to enjoy large images on your head like glasses. A Head Up Display (HUD) is a video display device that projects a virtual image onto a glass in a visible region of a user.

The sound output module 320 outputs audio data received from the wireless communication unit or stored in the memory 260 in a call signal reception mode, a call mode or a recording mode, a voice recognition mode, a broadcast reception mode, and the like. Also, the sound output module 320 outputs sound signals related to functions performed in the device, for example, call signal reception tones, message reception tones, and the like. The sound output module 320 may include a speaker, a buzzer, and the like.

The alarm unit 330 outputs a signal for notifying the occurrence of an event of the device. Examples of events that occur in a device include receiving a call signal, receiving a message, and inputting a key signal. The alarm unit 330 outputs a signal for notifying the occurrence of an event in a form other than an audio signal or a video signal. For example, it is possible to output a signal in a vibration mode including a vibration alarm unit. The alarm unit 330 may output a signal to notify when a call signal is received or a message is received. Also. When the key signal is input, the alarm unit 330 can output a signal as a feedback signal to the key signal input. The user can recognize the occurrence of an event through the signal output by the alarm unit 330. A signal for notifying the occurrence of an event in the device may also be output through the display unit 310 or the sound output module.

The haptic module 340 generates various tactile effects that the user can feel. A typical example of the haptic effect generated by the haptic module 340 is a vibration effect. When the haptic module 340 generates vibration with a haptic effect, the intensity and pattern of the vibration generated by the haptic module 340 can be converted, and the different vibrations may be synthesized and output or sequentially output.

The wireless communication unit 250 may include a broadcast receiving module, a mobile communication module, a wireless Internet module, a short distance communication module, and a GPS module.

The broadcast receiving module receives at least one of a broadcast signal and broadcast related information from an external broadcast management server through a broadcast channel. At this time, the broadcast channel may include a satellite channel, a terrestrial channel, and the like. The broadcast management server may refer to a server for generating and transmitting at least one of a broadcast signal and broadcast related information and a server for receiving at least one of the generated broadcast signal and broadcast related information and transmitting the broadcast signal to the terminal.

The broadcast-related information may mean information related to a broadcast channel, a broadcast program, or a broadcast service provider. The broadcast-related information can also be provided through a mobile communication network, in which case it can be received by the mobile communication module. Broadcast-related information can exist in various forms.

The broadcast receiving module receives a broadcast signal using various broadcast systems, and can receive a digital broadcast signal using a digital broadcast system. In addition, the broadcast receiving module may be configured to be suitable for all broadcasting systems that provide broadcast signals as well as the digital broadcasting system. The broadcast signal and / or broadcast related information received through the broadcast receiving module may be stored in the memory 260.

The mobile communication module transmits and receives radio signals to and from at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various types of data according to a voice call signal, a video call signal, or a text / multimedia message transmission / reception.

The wireless Internet module refers to a module for wireless Internet access, and the wireless Internet module can be embedded in a device or externally. Wireless Internet technologies include WLAN (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), LTE (Long Term Evolution-Advanced) or the like can be used.

The short-range communication module 116 is a module for short-range communication. Beacon, Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), ZigBee and the like can be used as a short distance communication technology.

Beacon is a wireless communication device that transmits very small frequency signals around them using a protocol based on Bluetooth 4.0 (BLE-Bluetooth Low Energy). Bluetooth 4.0 allows devices to communicate with devices within approximately 5m to 70m, and is low power with minimal impact on battery life, so you can always turn on Bluetooth with minimal power wastage.

The GPS (Global Position System) module 115 receives position information from a plurality of GPS satellites.

The memory 260 may store a program for processing and controlling the control unit 210 and may perform a function for temporarily storing input or output data (e.g., a message, a still image, a moving image, etc.) It is possible.

The memory 260 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory 260 XD memory 260, etc.), RAM, ROM, and the like. The device may also operate web storage to perform storage functions of memory 260 on the Internet.

The memory 260 may be represented by a storage unit 260 as follows.

The interface unit 270 serves as an interface with all external devices connected to the device. Examples of external devices connected to the device include a wired / wireless headset, an external charger, a wired / wireless data port, a memory 260 card, a Subscriber Identification Module (SIM) or a User Identity Module A card socket, an audio I / O (input / output) terminal, a video I / O (input / output) terminal, and an earphone. The interface unit 270 may receive data from the external device or supply power to the respective components in the device, and may transmit data in the device to the external device.

The control unit 210 typically controls the operation of each unit to control the overall operation of the device. For example, voice communication, data communication, video communication, and the like. In addition, the control unit 210 performs a function of processing data for multimedia reproduction. In addition, it performs a function of processing data input from the input unit or the sensing unit 130.

The control unit 210 may be expressed as an information processing module 210 hereinafter.

The situation evaluation module 230 determines a situation in which the user uses the wearable wearable device based on the criteria stored in the memory 260 or the criteria received from the user. That is, the device usage status of the user is determined based on various criteria, and the system configuration of the device or the signal to be received is determined.

The power supply unit receives external power and internal power under the control of the controller 210, and supplies power necessary for operation of the respective components.

The speech recognition unit 220 performs a function of recognizing verbally meaningful contents from the speech by automatic means. Specifically, a speech waveform is input to identify a word or a word sequence, and a meaning is extracted. The process is largely divided into voice analysis, phoneme recognition, word recognition, sentence analysis, and semantic extraction. The voice recognition unit 220 may further include a voice evaluation module that compares the stored voice with the input voice. The voice recognition unit 220 may further include a voice-to-text conversion module 240 that converts the input voice to text or converts the voice to voice.

Hereinafter, an acquaintance recognition system and a recognition method using a glass-like wearable device according to embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a flowchart of a recognition method using a wearable device of a glass type according to a preferred embodiment of the present invention.

Referring to FIG. 1, an acquaintance recognition method using a glass-like wearable device according to a preferred embodiment of the present invention includes acquiring an image or an image including a face of the other party (S100); Extracting a face region from the image or image (S200); Extracting feature information from the extracted face region (S300); Comparing the extracted feature information with the feature information of the face of the user and recognizing an acquaintance corresponding to the partner (S400); And informing the user of the name of the other party (S500). A recognition method using a glass-like wearable device according to an embodiment of the present invention will be described in order.

The image or the image including the face of the other party is obtained (S100). The first camera 121 provided at one side of the front portion of the glass-like wearable device to acquire an image or an image of the front of the user may be an image or image including a face of the other side in a direction viewed by the user, .

The first camera 121 can be operated by at least one of a voice input of a user, a touch command, a blink of an eye, and a gesture. The operation by the user's voice input is performed by inputting the user's voice by the voice input unit 113 and recognizing the meaning of the user voice inputted by the voice recognition unit 220 and instructing the first camera 121 Method. The operation by the user's touch command is performed by a user touching the touch unit 114 provided at one side of the glass-like wearable device and transmitting a command corresponding to the touch operation to the first camera 121 . The operation by the blinking of the user is performed by the second camera 122, which is provided at one side of the glass-type wearable device and acquires the image or the image of the user's pupil direction, recognizes the blink of the user's eye, And transmits the command to the first camera 121 to drive the camera. The operation by the gesture of the user may be performed by recognizing movement of the user's head by the motion sensor provided in the glass-like wearable device or by recognizing the user's specific hand gesture by the first camera 121, To the first camera 121 to receive the image or the image.

A face region is extracted from the image or image (S200). Face extraction (or detection) refers to determining whether a human face exists in a given arbitrary image or image, and, if so, determining the position and range in which each person exists. The face extraction method includes a knowledge-based method for detecting a person using rules between human factors derived from a prior knowledge of human, a human pose, a person-type Feature invariant approach that extracts structural features (Facial Features, Texture, Skin, Multiple Features, etc.) in advance and detects faces by searching and classifying characteristic values in input image, (Template matching method) that extracts the correlation with the input image after describing the standard pattern to be formed and extracts the expression form of the face form from several human type learning images, Based face recognition method (Appearance-based method). These various techniques can be applied to perform facial region extraction. However, the face region extraction method is not limited to the proposed method, but can be implemented by mutually complementing various other techniques and various techniques.

Feature information is extracted for face recognition in the extracted face area (S300).

The face recognition is a process of extracting feature information of a face image or an image from the extracted face region to discriminate the face of the person. Various face recognition algorithms have been developed. Here, the feature information refers to information indicating a unique characteristic of a predetermined face included in a face image or an image. For example, Principal Component Analysis (PCA) and Linear Discriminate Analysis (LDA) can be selected and used for feature information extraction. As another example, a 2-Dimensional Principal Component Analysis (2D-PCA) technique capable of extracting feature information of a facial image based on a two-dimensional image matrix can be used. Since the 2D-PCA technique has a smaller size of the projection matrix than the conventional PCA technique, it can be easily applied to a portable device and a low-end embedded system because the computation amount and required memory can be relatively lowered. Therefore, face recognition can be performed in a short time, and face recognition can be performed in real time. However, the method of extracting the feature information of the face image is not limited to this, and various feature information extraction methods can be applied.

The extracted feature information is compared with the stored feature information of the face of the acquaintance, and an acquaintance corresponding to the opponent is recognized (S400). The extracted feature information is compared with the feature information of the face image of the acquaintance stored in the glass-like wearable device or the external server 400 to recognize the face included in the input image or the image. If the distance difference between the extracted feature information and the feature information of the face image of the acquaintance stored in the device is within the threshold value, the extracted face region and the face of the acquaintance stored in the device can be recognized as the same face.

The step of comparing the extracted feature information with the feature information of the stored face information and determining an acquaintance of the other party can be performed by the control unit 210 or the external server 400 of the glass-like wearable device . That is, when the external server 400 grasps an acquaintance corresponding to the other party, the external server 400 receives the extracted feature information from the wearable device via wireless communication, A face image corresponding to the other of the face images of the acquaintances stored in the external server 400 is searched.

In addition, the feature information of the stored face is extracted and stored in the photograph of the acquaintance stored in the external server 400 or the storage unit 260 of the glass-like wearable device, It is possible to search for an acquaintance including the same feature information as the feature information of the extracted face image of the other party in the external server 400 or the glass type wearable device.

And informs the user of the corresponding party (S500). The step of informing the user of an acquaintance corresponding to the other party may include a method of displaying a photograph or name of an acquaintance corresponding to the other party on the display, a method of announcing the name of an acquaintance corresponding to the other party through sound output, And a method of displaying a photograph or name of an acquaintance corresponding to the other party on the display of the external device interlocked with the external device.

Also, an embodiment of the present invention may include the step of providing the user with information on an acquaintance corresponding to the other party. The information on the acquaintance may include a job, a school, an age, a background in acquaintance, interest, common knowledge, and the like. FIG. 4 shows a diagram showing information of an acquaintance corresponding to the other party.

5 is a configuration diagram of a recognition system using a glass-like wearable device and an external server 400 according to an embodiment of the present invention. In FIG. 5, a detailed description of the configuration described above will be omitted.

Referring to FIG. 5, a recognition system using a glass-type wearable device according to another embodiment of the present invention includes a glass-type wearable device; And an external server 400. The glass-type wearable device acquires an image or an image including a face of the other party, extracts feature information from the face of the other face in the image or image, transmits the extracted feature information to the external server 400, And notifies the user of the corresponding data. The external server 400 stores a photograph of a face of the user, identifies an acquaintance corresponding to the other party based on the extracted feature information, and provides the acquired information to the wearable device via wireless communication.

The wearable type wearable device includes a first camera (121); A wireless communication unit 250; A control unit 210; And an output unit 300.

The first camera 121 is provided at one side of the front portion of the glass-type wearable device, and acquires a video or an image of a face of the user.

The wireless communication unit 250 performs a function of exchanging information with the external server 400. That is, the wireless communication unit 250 transmits the feature information of the face of the other party extracted in the image or image to the external server 400. In addition, it performs a function of receiving, from the external server 400, information such as a photograph or name of an acquaintance corresponding to the other party to be output to the user.

The control unit 210 includes a face area extracting unit 211; And a feature extraction unit 211. The face region extracting unit 211 extracts a face region of the opposite face in the image or image. The feature extraction unit 211 extracts feature information from the extracted face region of the other party.

The output unit 300 functions to inform the user of an acquaintance corresponding to the other party. The output unit 300 may include a display unit 310 or an audio output unit 320. The display unit 310 displays a picture or name of an acquaintance corresponding to the other party. The sound output unit 320 performs a function of notifying the name of an acquaintance corresponding to the other party.

The wearable wearable device includes an audio input unit 113; And a speech recognition unit 220. The voice input unit 113 receives a voice command for the operation of the first camera 121. The voice recognition unit 220 recognizes the meaning of the user voice command input by the voice input unit 113. [ For example, the user may make a general statement pretending to know the other party, and the reminder may be a voice command that causes the first camera 121 to acquire images or images. Accordingly, it is possible to recognize that the voice is input to the voice input unit 113, and the voice recognition unit 220 grasps the meaning of the voice, and commands the operation of the first camera 121.

The wearable wearable device may further include a touch unit 114 for operating the first camera 121; Or a second camera 122, as shown in FIG. The touch unit 114 functions to provide an operation interface for receiving a touch command of a user. The second camera 122 is provided at one side of the glass-type wearable device and acquires images or images in the pupil direction of the user. The second camera 122 functions to receive an operation command by blinking the user's eyes. For example, when the user touches the touch part 114 provided on one side of the glass-type wearable device three times, the user acquires the image or the image including the face of the other party through the first camera 121, It is possible to search for an acquaintance. In addition, if the user blinks five consecutive times, the second camera 122 recognizes the blinking of the eyes, and the first camera 121 can acquire an image or an image including the face of the other party.

In addition, the external server 400 of the embodiment of the present invention includes a storage unit 410; A wireless communication unit 420; And a face recognition unit 430. [

The storage unit 410 stores a face image of the user. In addition, the storage unit 410 may store information on a user's acquaintance. The information on the acquaintance may include a job, a school, an age, a background in acquaintance, interest, common knowledge, and the like. That is, the user can input the face image, name, and other personal information of the acquaintance in advance in the storage unit 410 of the external server 400. The user is provided with the effect of hiding what he did not memorize the acquaintance.

The wireless communication unit 420 performs a function of exchanging information with the glass-type wearable device. That is, the face type feature information is received from the wearable device, and a name or a photograph of an acquaintance grasped based on the received information is transmitted to the wearable device.

The face recognizing unit 430 recognizes an acquaintance corresponding to the other party based on the received facial feature information. That is, the feature information received through the wireless communication from the glass-like wearable device is compared with the feature information extracted from the face photograph of the acquaintance stored in the storage unit 410 to search for an acquaintance corresponding to the other party.

6 is a configuration diagram of a recognition system using a wearable device of a glass type according to an embodiment of the present invention. In FIG. 6, a detailed description of the configuration described above will be omitted.

Referring to FIG. 6, a recognition system using a glass-like wearable device according to another embodiment of the present invention includes a first camera 121; A control unit 210; A storage unit 260; And an output unit 300.

The first camera 121 performs a function of acquiring an image or an image including a face of the other party.

The control unit 210 includes a face area extracting unit 211; A feature extraction unit 211; And a face recognition unit 213.

The face region extracting unit 211 extracts a face region of the opposite face in the image or image. The facial region extracting unit 211 extracts a specific facial component such as eyes, nose, mouth, and the like from each input image or image and then extracts a predetermined facial region have.

For example, if the position of two eyes is detected, the distance between the two eyes can be obtained. The face region extraction unit 211 may extract the face region from the input image or image based on the distance between the two eyes as a face image, .

However, the method of extracting the face region of the face region extraction unit 211 is not limited to this, and various methods such as the template matching method, the knowledge based method, and the outline based face recognition method may be applied.

The feature extraction unit 211 extracts feature information from the extracted face region. The face recognition unit 213 performs a function of recognizing an acquaintance corresponding to the other party based on the feature information.

The storage unit 260 stores a face image of the user.

The output unit 300 functions to inform the user of an acquaintance corresponding to the other party. The output unit 300 includes a display unit 310; Or an audio output unit 320. [0033] FIG.

In addition, the storage unit 260 may store information on the acquaintance of the user. The output unit 300 may provide the user with information about the acquaintance corresponding to the other party. The information on the acquaintances may include a job, a school, an age, a background where acquaintances are known, interests, common knowledge, and the like.

According to the present invention, when the user suddenly does not remember who pretends to know the user, the present invention can inform the user of who the other party is and can eliminate the situation of being sorry or embarrassed because they can not remember their acquaintances.

In addition, even if the face of the other party is remembered but the name is not remembered, the name information of the other party can be quickly provided, thereby preventing a problem that may occur due to the failure to memorize the name.

Also, on the streets, it is often unclear whether you are a person you know and can not pretend to know. In this case, it is possible to judge whether the user knows only if the image or the image including the face of the other party is obtained in the vicinity of the other party.

That is, if a face photograph and personal information of an acquaintance are stored in advance in the storage unit of the glass-like wearable device or the storage unit of the external server, the present invention can recognize the other party in real time by the present invention.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

100: system 110: user input
111: Application 112: Keyboard
113: voice input unit 114: touch pad
115: GPS signal unit 116: Local area communication
120: camera unit 121: first camera
122: second camera 123: third camera
130: sensing unit 131: gyro sensor
132: acceleration sensor 133: pressure sensor
134: iris recognition sensor 135: heart rate detection sensor
136: EMG sensor
210: control unit 211: face region extracting unit
212: Feature extraction unit 213: Face recognition unit
220: voice recognition unit
230: situation evaluation module 240: voice-to-text conversion module
250: wireless communication unit 260: memory
270:
300: output unit 310: display unit
320: Acoustic output unit 330:
340: Haptic module
400: external server 410: storage unit
420: wireless communication unit 430: face recognition unit

Claims (14)

Obtaining an image or an image including a face of the other party;
Extracting a face region from the image or image;
Extracting feature information from the extracted face region;
Comparing the extracted feature information with feature information of a face of a user and recognizing an acquaintance corresponding to the partner; And
And informing the user of an acquaintance corresponding to the other party. The method according to claim 1,
Comparing the extracted feature information with feature information of a face of a user and determining an acquaintance corresponding to the partner,
Wherein the recognition is performed by a controller of the glass-type wearable device or an external server. The method according to claim 1,
The step of informing the user of an acquaintance corresponding to the other party,
A method of displaying a photograph or name of an acquaintance corresponding to the opponent on a display, a method of announcing the name of an acquaintance corresponding to the opponent with an acoustic output, a method of acquiring an acquaintance And a method of displaying a photograph or a name of the wearable device. The method according to claim 1,
The feature information of the face,
Characterized in that the feature is extracted from a photograph of an acquaintance stored in an external server or a storage unit of the glass-like wearable device,
The recognition of an acquaintance corresponding to the other party,
Wherein the acquaintance searching unit searches for an acquaintance including the same feature information as the feature information of the extracted facial face photograph in the external server or the glass wearable device. The method according to claim 1,
And providing information on an acquaintance corresponding to the other party to a user. And transmits the extracted feature information to the external server. The external information is received from the external server, and the received information is displayed on a glass Wearable device; And
And an external server that stores a face image of the user and acquires an acquaintance corresponding to the partner on the basis of the extracted feature information and provides the acquaintance to the wearable device through wireless communication, Identification system using device. The method according to claim 6,
The wearable wearable device of claim 1,
A first camera for acquiring an image or an image including a face of the other party;
A wireless communication unit for exchanging information with the external server;
A face region extracting unit for extracting a face region of the opposite side in the image or the image, and a feature extracting unit extracting the feature information from the extracted face region; And
And an output unit for informing the user of an acquaintance corresponding to the other party. 8. The method of claim 7,
The output unit includes:
A display unit for displaying a picture or name of an acquaintance corresponding to the other party; And a sound output unit for notifying a name of an acquaintance corresponding to the other party. The method according to claim 6,
The external server comprises:
A storage unit for storing a face photograph of the user;
A wireless communication unit for exchanging information with the wearable device; And
And a face recognizing unit for recognizing an acquaintance corresponding to the other party on the basis of the received facial feature information. The method according to claim 6,
Wherein,
And the information about the acquaintance of the user is stored. A first camera for acquiring an image or an image including a face of the other party;
A face region extracting unit for extracting a face region of the opposite side in the image or image, a feature extracting unit for extracting the feature information from the extracted face region, and a face recognizing unit for recognizing an acquaintance corresponding to the opposite side based on the feature information ;
A storage unit for storing a face photograph of the user; And
And an output unit for informing the user of an acquaintance corresponding to the other party. 12. The method of claim 11,
The output unit includes:
A display unit for displaying a picture or name of an acquaintance corresponding to the other party; And a sound output unit for notifying a name of an acquaintance corresponding to the other party. 12. The method of claim 11,
Wherein,
And stores information on the acquaintance of the user;
The output unit includes:
And provides the user with information on an acquaintance corresponding to the other party to the user. 14. The method of claim 13,
The information on the acquaintance may be,
A wearable recognition system using a wearable wearable device including at least one of a job, a school, an age, an acquaintance's background, interests, and common knowledge.

Images