WO2016173453A1 - 活体鉴别方法、信息生成方法和终端 - Google Patents

活体鉴别方法、信息生成方法和终端 Download PDF

Info

Publication number
WO2016173453A1
WO2016173453A1 PCT/CN2016/079893 CN2016079893W WO2016173453A1 WO 2016173453 A1 WO2016173453 A1 WO 2016173453A1 CN 2016079893 W CN2016079893 W CN 2016079893W WO 2016173453 A1 WO2016173453 A1 WO 2016173453A1
Authority
WO
WIPO (PCT)
Prior art keywords
lip
target characters
images
prompt information
characters
Prior art date
Application number
PCT/CN2016/079893
Other languages
English (en)
French (fr)
Inventor
李季檩
汪铖杰
黄飞跃
吴永坚
倪辉
张睿欣
谭国富
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2016173453A1 publication Critical patent/WO2016173453A1/zh
Priority to US15/462,423 priority Critical patent/US10607066B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G06V40/176—Dynamic expression
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • the embodiments of the present invention relate to the field of biometric identification, and in particular, to a living body identification method, an information generating method, and a terminal.
  • biometrics face recognition has become one of the commonly used techniques for confirming user identity.
  • biometric authentication has become a common method for face recognition.
  • the related living body identification method is: the terminal provides lip language prompt information for the identified object; collects at least two frames of images, and detects whether the lip change of the identified object in at least two frames of images matches the lip change in the lip language prompt information. If it matches, it is determined that the object to be identified is a living body.
  • the lip shape may be different when different users issue the same character (for example, when using the Mandarin to read and use the dialect, the lip shape is different, and reading in Chinese is used. It is different from the lip shape when reading in English, so this causes the terminal to misjudge the object to be identified as being inactive even if the object to be authenticated operates according to the lip prompt information.
  • the embodiments of the present invention provide a living body identification method, an information generating method, and a terminal.
  • the technical solution is as follows:
  • a living body identification method comprising:
  • the lip prompt information includes at least two target characters, and the at least two target characters are characters of at least one of the same lip shape, the opposite lip shape, and the lip similarity in a preset range;
  • the preset condition is met, it is determined that the identified object is a living body.
  • a living body identification device comprising:
  • the information providing module is configured to provide lip language prompt information, wherein the lip language prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip shape similarity in a preset range. character of;
  • An image acquisition module configured to collect at least two frames of images
  • a detecting module configured to detect, when at least two target characters are read by the identified object in at least two frames of images collected by the image capturing module, whether the lip change of the identified object meets a preset condition
  • the result determining module is configured to determine that the identified object is a living body when the detection result of the detecting module is that the preset condition is met.
  • a terminal where the terminal includes:
  • One or more processors are One or more processors.
  • the memory stores one or more programs, the one or more programs being configured to be executed by the one or more processors, the one or more programs including instructions for:
  • the lip language prompt information comprising at least two target characters, the at least two target characters being at least one of a lip shape, a lip shape, and a lip shape similarity in a preset range ;
  • the preset condition is met, it is determined that the identified object is a living body.
  • a method for generating lip language prompt information for living body identification comprising:
  • the lip hint information comprising at least two target characters, the at least two target characters being at least the same lip shape, the opposite lip shape, and at least the lip similarity in a preset range A character
  • the lip prompt information is used to instruct the terminal to identify, according to the lip prompt information, whether the identified object is a living body.
  • the terminal may misjudge the object to be identified as not a living body; the terminal can accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination. effect.
  • FIG. 1 is a flow chart of a method for identifying a living body according to an embodiment of the present invention
  • FIG. 2A is a flowchart of a method for identifying a living body according to another embodiment of the present invention.
  • 2B is a schematic diagram of lip language prompt information according to another embodiment of the present invention.
  • 2C is a schematic diagram of a terminal displaying lip language prompt information according to another embodiment of the present invention.
  • 2D is a schematic view of various model points of a lip according to another embodiment of the present invention.
  • 2E is a flowchart of another method for a living body identification method according to another embodiment of the present invention.
  • FIG. 3 is a block diagram showing the structure of a living body identification device according to an embodiment of the present invention.
  • FIG. 4 is a block diagram showing the structure of a living body identification device according to another embodiment of the present invention.
  • FIG. 5 is a structural block diagram of a terminal according to an embodiment of the present invention.
  • the terminal mentioned in the embodiment of the present invention may be: a mobile phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert compression) Standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV), a recordable terminal such as a player, a laptop portable computer, and a desktop computer.
  • MP3 player Moving Picture Experts Group Audio Layer III, dynamic image expert compression
  • MP4 Moving Picture Experts Group Audio Layer IV
  • a recordable terminal such as a player, a laptop portable computer, and a desktop computer.
  • the lip changes mentioned in the embodiments of the present invention include any one of a lip shape change, a lip texture change, and a lip color change;
  • the lip image sequence includes a lip shape sequence, a lip texture sequence, and a lip color. Any of the sequences; when the lip change is a change in the shape of the lip, the sequence of the lip image is a sequence of lip shapes; when the change in the lip is a change in the texture of the lip, the sequence of the lip image is a sequence of lip texture;
  • the lip image sequence is the lip color sequence.
  • FIG. 1 is a flowchart of a method for identifying a living body according to an embodiment of the present invention.
  • the method comprises:
  • lip language prompt information is provided.
  • the lip language prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip shape similarity in a preset range.
  • step 102 at least two frames of images are acquired.
  • Step 103 Detect whether the lip change of the identified object meets a preset condition when at least two target characters are read by the identified object in at least two frames of images.
  • Step 104 If the preset condition is met, it is determined that the identified object is a living body.
  • the living body identification method detects that at least two target characters in the collected at least two frames of images are detected when at least two target characters are read by setting at least two target characters in the lip prompt information. Identifying whether the lip change of the object meets the preset condition, and then determining that the identified object is a living body when the detection result is in accordance with the preset condition; wherein at least two target characters are the same lip shape, opposite lip shape, and lip similarity At least one character in a preset range; solving the problem in the related art that even if the identified object operates according to the lip prompt information, the terminal may misjudge the identified object as not a living body; Accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination.
  • FIG. 2A a flowchart of a method for identifying a living body according to another embodiment of the present invention is shown.
  • the method comprises:
  • Step 201 Obtain lip language prompt information.
  • the terminal can obtain the lip prompt information first.
  • the lip prompt message is a random string, a random character
  • the string includes at least two target characters, and the at least two target characters are characters of at least one of the same lip shape, opposite lip shape, and lip similarity in a preset range.
  • the lip-shaped characters may include the same character appearing at least twice, or different characters having the same lip shape or lip similarity higher than a preset threshold, or both.
  • the lip prompt message includes the same lip shape, and the same lip shape includes the same character appearing at least twice. Please refer to (1) in FIG. 2B, which shows a possible lip. Language prompt information.
  • the lip prompt information may include at least two sets of lips having the same character, and the number of characters of each set of lips may be two or more.
  • the lip hint information may be '102410134'.
  • the lip prompt message includes the same lip shape, and the same lip shape includes different characters whose lip shape is the same or the lip similarity is higher than the preset threshold, for example, '1' and '7', '6' And '9', '8' and 'Dad', 'B' and 'P' and 'D' and 'E' are all different characters of the same lip shape, so please refer to (2) in Figure 2B, A possible lip language prompt message is shown.
  • the lip prompt information may include at least two sets of the same lip shape, and the number of the same lip characters may be two or more, which is not limited in this embodiment.
  • the opposite lip character refers to a character with a different literal and opposite lip pronunciation. Since 'solid' and 'ah', 'fu' and 'sea', 'picture' and 'help', 'me' and 'no' and 'five' and 'eight' are all opposite lips, so please Referring to the (3) diagram in Fig. 2B, a possible lip language prompt information is shown.
  • the lip-speech information may include at least two sets of opposite-shaped characters, and the number of the opposite-faced characters may be two or more, which is not limited in this embodiment.
  • the lip prompt information may further include at least two target characters whose lip similarity is within a preset range, that is, the lip prompt information may include at least two characters having a stable similarity relationship of the lip change.
  • the preset range is a range formed by the first threshold and the second threshold.
  • the first threshold is a value greater than 0, and the second threshold is a value less than 1.
  • the default range is 0.4-0.6.
  • the lip language prompt information can be 'Furu Donghai Shoubi Nanshan' and other information including 'Fu' and ' ⁇ '.
  • the ellipses in FIG. 2B represent any number of arbitrary characters, which is not limited in this embodiment.
  • the above only uses the lip language prompt information to include only the same lip shape or the opposite lip shape or the character whose lip similarity is within the preset range, and optionally, the lip prompt information. It can also include any two or three of the above characters.
  • the lip prompt information can be '13572468' ('1' and '7' are lip-shaped characters, and '5' and '8' are lip shapes. The opposite character).
  • the lip prompt information may be information generated by the terminal
  • the information obtained by the terminal from the server may also be used. So this step can include the following two possible implementations:
  • the terminal can randomly generate the lip prompt information.
  • the terminal may store the pre-generated lip prompt information into the information base, and randomly select the lip prompt information from the information base.
  • the lip prompt information containing at least two target characters is obtained from the server, and the lip prompt information is information generated by the server in advance.
  • the terminal may send the information acquisition request to the server, and receive the lip prompt information randomly returned by the server.
  • the lip prompt information may be information randomly generated by the server.
  • the terminal may obtain the lip prompt information when detecting that the captured image includes a human face. For example, when detecting that the collected image includes a human face, the terminal randomly generates a lip prompt information, or selects a pre-stored set of lip language prompt information from the information base; for example, the terminal detects the captured image.
  • the information acquisition request is sent to the server, and the information acquisition request is used to request to acquire a set of lip language prompt information, and receive the lip language prompt information returned by the server.
  • Step 202 providing lip language prompt information.
  • the terminal displays the lip prompt information in text form
  • the terminal can display the lip prompt information shown in the figure.
  • the terminal displays the lip prompt information in a video format
  • the terminal plays the lip prompt information in an audio form.
  • the terminal may provide the information for prompting the identified object to read the lip prompt information while providing the lip prompt information.
  • step 203 at least two frames of images are acquired.
  • the terminal can acquire at least two frames of the image of the identified object by taking a photo.
  • the terminal can also collect at least the identified object by taking a video. Two frames of image.
  • Step 204 Acquire, according to at least two frames of images, a lip change when the identified object reads at least two target characters.
  • the terminal may acquire a lip change of the identified object when reading at least two target characters according to at least two frames of images.
  • the reading of the character to be authenticated in the embodiment may be a reading of the sound, or a reading of only the lip motion, which is not limited in this embodiment.
  • this step may include:
  • an image of the at least two frames of images in which at least two target characters are read is determined.
  • the terminal may select an image corresponding to each target character according to a location where the target character is located in the lip prompt information.
  • the terminal may know the location of each target character in advance according to the generation rule when generating the lip prompt information; and when the lip prompt information is the information obtained by the terminal from the server.
  • the location of each target character in the lip prompt information may be obtained from the server, which is not limited in this embodiment.
  • the terminal may select the first of the at least two frames of images.
  • a sequence of lip images when the at least two target characters are read by the authenticated object is extracted from the determined image, and the sequence of lip images is used to characterize the lip change of the identified subject.
  • the terminal can detect whether there is a face in the determined image.
  • the position of the lips in the face can be determined by the difference between the color of the lips and the skin color.
  • the terminal can determine whether there is a lip change in the identified object in the image by using a model point method.
  • the model point refers to a corner point on the curve of the edge of the lip.
  • the upper edge of the lip may include 5 model points 222, and the lower edge of the lip may also include 5 Model point 222.
  • the terminal can determine the position of each point of the lip by using a model point method to form a state of the lip image at a certain moment. In chronological order, the terminal extracts the lip image in the image corresponding to each target character to form a lip image sequence. The sequence of lip images is used to characterize the lip change of the identified subject as the target character is read.
  • Step 205 Detect whether the lip change of the identified object meets a preset condition.
  • this step may include:
  • the terminal may detect whether the sequence of lip images of the identified object when reading the same lip shape is the same. If they are the same, it is judged that the lip change of the identified object meets the preset condition; otherwise, the preset condition is not met.
  • the terminal may sequentially detect whether the same lip image sequence of each set of lips is the same.
  • the terminal may further select a lip image sequence of at least one set of lips of the same set of two or more lip-shaped identical characters, and detect whether each selected set of lip image sequences is the same.
  • the terminal may select a lip image sequence corresponding to the n characters, and detect whether the selected lip sequence of the n characters is the same. Where n is an integer greater than or equal to 2.
  • the terminal can also detect whether the number of identical sequences in the lip image sequence of each set of lip-shaped characters reaches a preset threshold. For example, if there are four characters with the same lip shape, the terminal can detect whether the number of the same sequence of the four-character lip image sequence reaches three. If it is reached, the determination meets the preset condition, and vice versa. Meet the preset conditions.
  • the target characters include characters having opposite lips, it is detected whether the lip change of the identified object when reading the opposite lip character is reversed.
  • the at least two target characters include characters whose lip similarity is within a preset range, detecting whether the similarity of the lip change of the identified object when reading the lip similarity in the preset range is within a preset range .
  • the terminal may input the lip image sequence of the at least two target characters into the hidden Markov model, and the hidden Markov model calculates the matching degree of the received respective lip image sequences, and detects whether the matching degree is in advance. Set within the scope. If it is within the preset range, it confirms that it meets the preset condition; otherwise, it does not match Preset conditions.
  • Step 206 If the preset condition is met, it is determined that the identified object is a living body.
  • the terminal determines that the identified object is not a living body.
  • the living body identification method detects that at least two target characters in the collected at least two frames of images are detected when at least two target characters are read by setting at least two target characters in the lip prompt information. Identifying whether the lip change of the object meets the preset condition, and then determining that the identified object is a living body when the detection result is in accordance with the preset condition; wherein at least two target characters are the same lip shape, opposite lip shape, and lip similarity At least one character in a preset range; solving the problem in the related art that even if the identified object operates according to the lip prompt information, the terminal may misjudge the identified object as not a living body; Accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination.
  • the lip prompt information in this embodiment is information randomly generated by the terminal, or information randomly generated by the server obtained from the server, and when the information is fixed, the terminal determines that the video containing the lip prompt information is also determined to be a living body. Furthermore, the problem of misjudgment has reached an effect that the accuracy of the determination can be improved.
  • the above embodiment is only used to detect whether the lip change of the identified object meets the preset condition when the at least two target characters are read by the identified object in at least two frames of images by the terminal.
  • the detection may be performed by the server.
  • step 204 and step 205 in the foregoing embodiment may be replaced by step 207 to step 210.
  • FIG. 2E the method for identifying the living body at this time is shown. Method flow chart.
  • Step 207 The terminal sends at least two frames of image and lip prompt information to the server.
  • Step 208 The server detects whether the lip change of the identified object meets a preset condition when at least two target characters are read by the identified object in at least two frames of images.
  • the server may detect whether the lip change of the identified object meets the preset condition when the at least two target characters are read by the identified object in the at least two frames of images.
  • the detection method of the server is similar to the detection method of the terminal. For detailed technical details, refer to step 204 and step 205 in the foregoing embodiment, and details are not described herein again.
  • step 209 the server feeds back the detection result to the terminal.
  • Step 210 The terminal receives the detection result fed back by the server.
  • step 206 may be: determining that the identified object is a living body when the detection result indicates that the lip change of the identified object meets the preset condition; and when the detection result indicates that the lip change of the identified object does not meet the preset condition , to determine that the object being identified is not a living body.
  • the terminal may also send only at least two frames of images to the server in step 207.
  • the lip prompt information in the foregoing embodiments may be generated by the terminal itself or may be generated by the server. Therefore, the embodiment of the present invention further provides a method for generating lip prompt information for living body identification, and the method includes :
  • the lip prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip similarity in a preset range, and the lip prompt information is used to indicate
  • the terminal identifies whether the identified object is a living body based on the lip prompt information.
  • the method can be used in the terminal or in the server. and:
  • the terminal may generate the lip prompt information according to the preset rule when detecting the included image, and optionally, the terminal may generate the lip language at any time. Prompt information and save the generated lip language prompt information.
  • the server may generate the lip prompt information in advance and provide the lip prompt information to the terminal.
  • the server may automatically send the lip prompt information to the terminal after generating the lip prompt information; or the server returns the lip prompt information to the terminal after receiving the information acquisition request sent by the terminal.
  • the server may further generate the lip prompt information after receiving the trigger request sent by the terminal, and send the lip prompt information to the terminal.
  • the lip prompt information may be randomly generated, which is not limited in this embodiment.
  • the method for generating lip prompt information for living body identification provides a lip-shaped prompt information including at least two target characters, wherein the at least two target characters have the same lip shape and a lip shape.
  • a lip-shaped prompt information including at least two target characters, wherein the at least two target characters have the same lip shape and a lip shape.
  • at least one character whose lip similarity is in a preset range so that the terminal can perform the living body identification according to the lip prompt information, and the lip shape change when the at least two target characters are read according to the identified object
  • the terminal may misjudge the identified object as not The problem of living body; the terminal can accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination.
  • FIG. 3 shows a structural block diagram of a living body identification device according to an embodiment of the present invention.
  • This embodiment is exemplified by the application of the living body identification device to the terminal.
  • the biometric authentication device can be implemented as a whole or a part of the terminal by software, hardware or a combination of the two.
  • the device includes: an information providing module 310, an image collecting module 320, a detecting module 330, and a result determining module 340.
  • the information providing module 310 is configured to provide lip prompt information, where the lip prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip similarity in a preset range.
  • the lip prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip similarity in a preset range.
  • the image acquisition module 320 is configured to collect at least two frames of images
  • the detecting module 330 is configured to detect, when at least two target characters are read by the identified object in the at least two frames of images collected by the image capturing module 320, whether the lip change of the identified object meets a preset condition;
  • the result determining module 340 is configured to determine that the identified object is a living body when the detection result of the detecting module 330 is that the preset condition is met.
  • the living body discriminating device detects that at least two target characters in the collected at least two frames of images are detected when at least two target characters are read by setting at least two target characters in the lip prompt information. Identifying whether the lip change of the object meets the preset condition, and then determining that the identified object is a living body when the detection result is in accordance with the preset condition; wherein at least two target characters are the same lip shape, opposite lip shape, and lip similarity At least one character in a preset range; solving the problem in the related art that even if the identified object operates according to the lip prompt information, the terminal may misjudge the identified object as not a living body; Accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination.
  • FIG. 4 is a structural block diagram of a living body discriminating device according to another embodiment of the present invention.
  • This embodiment is exemplified by the application of the living body identification device to the terminal.
  • the biometric authentication device can be implemented as a whole or a part of the terminal by software, hardware or a combination of the two.
  • the device includes: an information providing module 410, an image collecting module 420, a detecting module 440, and a result determining module 440.
  • the information providing module 410 is configured to provide lip prompt information, where the lip prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip similarity in a preset range.
  • the lip prompt information includes at least two target characters, and the at least two target characters are at least one of a lip shape, a lip shape, and a lip similarity in a preset range.
  • the image acquisition module 420 is configured to collect at least two frames of images
  • the detecting module 430 is configured to detect, when at least two target characters are read by the identified object in the at least two frames of images collected by the image capturing module 420, whether the lip change of the identified object meets a preset condition;
  • the result determining module 440 is configured to determine that the identified object is a living body when the detection result of the detecting module 430 is that the preset condition is met.
  • the detecting module 430 includes:
  • the obtaining unit 431 is configured to acquire, according to the at least two frames of images, a lip change when the at least two target characters are read by the identified object;
  • the detecting unit 432 is configured to detect, when the at least two target characters include the same lip shape, whether the lip change of the identified object when reading the same lip shape is the same; at least two target characters include the opposite lip shape Detecting whether the lip change of the identified object when reading the opposite lip character is reversed; detecting that the identified object is reading when at least two target characters include characters whose lip variation range belongs to a preset range Whether the similarity of the lip change when the lip similarity is in the preset range of characters is within a preset range.
  • the obtaining unit 431 includes:
  • the image determining sub-unit 431a is configured to determine an image of the at least two target images in the at least two frames of images when the at least two target characters are read out;
  • the sequence extracting sub-unit 431b is configured to extract, from the image determined by the image determining sub-unit 431a, a lip image sequence when the at least two target characters are read by the authenticated object, and the lip image sequence is used to represent the lip of the identified object Variety.
  • the detecting module 430 is further configured to send at least two frames of image and lip prompt information to the server, where the server is configured to detect that the identified object in the at least two frames of images is identified when at least two target characters are read. Whether the lip change of the subject meets the preset conditions.
  • the device further includes:
  • a generating module 450 configured to generate lip prompt information including at least two target characters
  • the obtaining module 460 is configured to obtain, from the server, a lip prompt message including at least two target characters Information, the lip prompt information is pre-generated information of the server.
  • the living body discriminating device detects that at least two target characters in the collected at least two frames of images are detected when at least two target characters are read by setting at least two target characters in the lip prompt information. Identifying whether the lip change of the object meets the preset condition, and then determining that the identified object is a living body when the detection result is in accordance with the preset condition; wherein at least two target characters are the same lip shape, opposite lip shape, and lip similarity At least one character in a preset range; solving the problem in the related art that even if the identified object operates according to the lip prompt information, the terminal may misjudge the identified object as not a living body; Accurately determine whether the object to be identified is a living body, and improve the accuracy of the discrimination.
  • FIG. 5 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
  • the terminal is used to implement the living body identification method provided in the above embodiment or a method of generating lip language prompt information for living body identification. Specifically:
  • the terminal 500 may include an RF (Radio Frequency) circuit 510, a memory 520 including one or more computer readable storage media, an input unit 530, a display unit 540, a sensor 550, an audio circuit 560, and a WiFi (wireless fidelity, wireless).
  • the fidelity module 570 includes a processor 580 having one or more processing cores, and a power supply 590 and the like. It will be understood by those skilled in the art that the terminal structure shown in FIG. 5 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements. among them:
  • the RF circuit 510 can be used for receiving and transmitting signals during and after receiving or transmitting information, in particular, after receiving downlink information of the base station, and processing it by one or more processors 580; in addition, transmitting data related to the uplink to the base station.
  • the RF circuit 510 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier). , duplexer, etc.
  • SIM Subscriber Identity Module
  • RF circuitry 510 can also communicate with the network and other devices via wireless communication.
  • the wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access). , Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), e-mail, SMS (Short Messaging Service), and the like.
  • GSM Global System of Mobile communication
  • GPRS General Packet Radio Service
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • LTE Long Term Evolution
  • e-mail Short Messaging Service
  • the memory 520 can be used to store software programs and modules, and the processor 580 executes various functional applications and data processing by running software programs and modules stored in the memory 520.
  • the memory 520 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to The data created by the use of the terminal 500 (such as audio data, phone book, etc.) and the like.
  • memory 520 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 520 may also include a memory controller to provide access to memory 520 by processor 580 and input unit 530.
  • Input unit 530 can be used to receive input numeric or character information, as well as to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.
  • the input unit 530 may include an image input device 531 and other input devices 532.
  • the image input device 531 may be a camera or an optical scanning device.
  • the input unit 530 may also include other input devices 532.
  • other input devices 532 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.
  • Display unit 540 can be used to display information entered by the user or information provided to the user and various graphical user interfaces of terminal 500, which can be composed of graphics, text, icons, video, and any combination thereof.
  • the display unit 540 can include a display panel 541.
  • the display panel 541 can be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like.
  • Terminal 500 can also include at least one type of sensor 550, such as a light sensor, motion sensor, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 541 according to the brightness of the ambient light, and the proximity sensor may close the display panel 541 when the terminal 500 moves to the ear. / or backlight.
  • the gravity acceleration sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity.
  • the terminal 500 can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, here Let me repeat.
  • An audio circuit 560, a speaker 561, and a microphone 562 can provide a sound between the user and the terminal 500. Frequency interface.
  • the audio circuit 560 can transmit the converted electrical data of the received audio data to the speaker 561, and convert it into a sound signal output by the speaker 561.
  • the microphone 562 converts the collected sound signal into an electrical signal, and the audio circuit 560 is used by the audio circuit 560. After receiving, it is converted into audio data, and then processed by the audio data output processor 580, transmitted to the terminal, for example, via the RF circuit 510, or outputted to the memory 520 for further processing.
  • the audio circuit 560 may also include an earbud jack to provide communication of the peripheral earphones with the terminal 500.
  • WiFi is a short-range wireless transmission technology
  • the terminal 500 can help users to send and receive emails, browse web pages, and access streaming media through the WiFi module 570, which provides wireless broadband Internet access for users.
  • FIG. 5 shows the WiFi module 570, it can be understood that it does not belong to the essential configuration of the terminal 500, and may be omitted as needed within the scope of not changing the essence of the invention.
  • Processor 580 is the control center of terminal 500, which connects various portions of the entire handset using various interfaces and lines, by running or executing software programs and/or modules stored in memory 520, and recalling data stored in memory 520, The various functions and processing data of the terminal 500 are performed to perform overall monitoring of the mobile phone.
  • the processor 580 may include one or more processing cores; preferably, the processor 580 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like.
  • the modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 580.
  • the terminal 500 also includes a power source 590 (such as a battery) that supplies power to the various components.
  • a power source 590 such as a battery
  • the power source can be logically coupled to the processor 580 through a power management system to manage functions such as charging, discharging, and power management through the power management system.
  • Power supply 590 may also include any one or more of a DC or AC power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
  • the terminal 500 may further include a Bluetooth module or the like, and details are not described herein again.
  • terminal 500 further includes a memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors.
  • the one or more programs described above include a method for performing a living body identification method as provided in the above embodiments or generating lip language prompt information for living body identification.
  • a non-transitory computer readable storage medium comprising instructions, such as a memory comprising instructions executable by a processor of a mobile terminal to perform a biometric authentication method or for generating a living body A method of identifying lip-speech information.
  • the temporal computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • biometric identification device provided in the above embodiment is only exemplified by the division of the above functional modules when performing biometric authentication. In actual applications, the above functional assignments may be completed by different functional modules as needed. The internal structure of the device is divided into different functional modules to complete all or part of the functions described above.
  • embodiment of the present invention is the same as the method embodiment of the living body identification method, and the specific implementation process is described in detail in the method embodiment, and details are not described herein again.
  • a person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium.
  • the storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明公开了一种活体鉴别方法、信息生成方法和终端，属于生物特征识别领域。所述方法包括：提供唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；采集至少两帧图像；检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件；若符合所述预设条件，则确定所述被鉴别对象是活体；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。

Description

活体鉴别方法、信息生成方法和终端
本申请要求于2015年04月30日提交中国专利局、申请号为2015102189012、发明名称为“活体鉴别方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及生物特征识别领域，特别涉及一种活体鉴别方法、信息生成方法和终端。
背景技术
随着生物特征识别技术的发展，人脸识别已经成为确认用户身份时常用的技术之一。然而，为了避免不法分子盗用用户照片，进而使用照片进行非法验证，活体鉴别已经成为人脸识别时常用的方法。
相关的活体鉴别方法为：终端为被鉴别对象提供唇语提示信息；采集至少两帧图像，检测至少两帧图像中的被鉴别对象的唇部变化是否与唇语提示信息中的唇部变化匹配；若匹配，则确定被鉴别对象为活体。
在实现本发明的过程中，发明人发现相关技术至少存在以下问题：不同用户发出同一字符时唇形可能会有所不同(如使用普通话读出与使用方言读出时唇形不同，使用中文读出与使用英文读出时唇形不同)，所以这就导致即使被鉴别对象按照唇语提示信息进行操作，终端也可能会将被鉴别对象误判为不是活体。
发明内容
为了解决相关技术中存在的问题，本发明实施例提供了一种活体鉴别方法、信息生成方法和终端。所述技术方案如下：
第一方面，提供了一种活体鉴别方法，该方法包括：
提供唇语提示信息，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
采集至少两帧图像；
检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件；
若符合预设条件，则确定被鉴别对象是活体。
第二方面，提供了一种活体鉴别装置，该装置包括：
信息提供模块，用于提供唇语提示信息，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
图像采集模块，用于采集至少两帧图像；
检测模块，用于检测图像采集模块采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件；
结果确定模块，用于在检测模块的检测结果为符合预设条件时，确定被鉴别对象是活体。
第三方面，提供了一种终端，所述终端包括：
一个或多个处理器；和
存储器；
所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，所述一个或多个程序包含用于进行以下操作的指令：
提供唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
采集至少两帧图像；
检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件；
若符合所述预设条件，则确定所述被鉴别对象是活体。
第四方面，提供了一种生成用于活体鉴别的唇语提示信息的方法，该方法包括：
根据预设规则生成唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符，所述唇语提示信息用于指示终端根据所述唇语提示信息鉴别被鉴别对象是否为活体。
本发明实施例提供的技术方案的有益效果是：
通过在唇语提示信息中设置至少两个目标字符，检测采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时被鉴别对象的唇部变化是否符合预设条件，进而在检测结果为符合预设条件时，确定被鉴别对象为活体；其中，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明一个实施例提供的活体鉴别方法的方法流程图；
图2A是本发明另一实施例提供的活体鉴别方法的方法流程图；
图2B是本发明另一实施例提供的唇语提示信息的示意图；
图2C是本发明另一实施例提供的终端展示唇语提示信息的示意图；
图2D是本发明另一实施例提供的唇部的各个模型点的示意图；
图2E是本发明另一实施例提供的活体鉴别方法的另一方法流程图；
图3是本发明一个实施例提供的活体鉴别装置的结构方框图；
图4是本发明另一实施例提供的活体鉴别装置的结构方框图；
图5是本发明一个实施例提供的终端的结构方框图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部份实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
本发明实施例中提到的终端可以是：手机、平板电脑、电子书阅读器、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩 标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等可拍摄的终端。
本发明实施例中提到的唇部变化包括唇部形状变化、唇部纹理变化和唇部颜色变化中的任意一种；唇部图像序列包括唇部形状序列、唇部纹理序列和唇部颜色序列中的任意一种；当唇部变化是唇部形状变化时，唇部图像序列是唇部形状序列；当唇部变化是唇部纹理变化时，唇部图像序列是唇部纹理序列；当唇部变化为唇部颜色变化时，唇部图像序列是唇部颜色序列。
请参考图1，其示出了本发明一个实施例提供的活体鉴别方法的方法流程图。该方法，包括：
步骤101，提供唇语提示信息，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符。
步骤102，采集至少两帧图像。
步骤103，检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件。
步骤104，若符合预设条件，则确定被鉴别对象是活体。
综上所述，本实施例提供的活体鉴别方法，通过在唇语提示信息中设置至少两个目标字符，检测采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时被鉴别对象的唇部变化是否符合预设条件，进而在检测结果为符合预设条件时，确定被鉴别对象为活体；其中，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
请参考图2A，其示出了本发明另一实施例提供的活体鉴别方法的方法流程图。该方法，包括：
步骤201，获取唇语提示信息。
终端可以先获取唇语提示信息。该唇语提示信息为随机字符串，随机字符 串中包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符。
其中，唇形相同的字符可以包括出现至少两次的同一个字符，或者，唇形相同或者唇形相似度高于预设阈值的不同字符，或者，同时包括上述两者。
以唇语提示信息包括唇形相同的字符，且唇形相同的字符包括出现至少两次的同一个字符为例，请参考图2B中的(1)图，其示出了一种可能的唇语提示信息。
可选地，唇语提示信息可以包括至少两组唇形相同的字符，且每一组唇形相同的字符的个数可以有两个或者两个以上。比如，以唇语提示信息中包括3个‘1’和2个‘4’为例，唇语提示信息可以为‘102410134’。
以唇语提示信息包括唇形相同的字符，且唇形相同的字符包括唇形相同或者唇形相似度高于预设阈值的不同字符为例，由于‘1’和‘7’、‘6’和‘9’、‘8’和‘爸’、‘B’和‘P’以及‘D’和‘E’均属于唇形相同的不同字符，所以请参考图2B中的(2)图，其示出了一种可能的唇语提示信息。可选地，唇语提示信息可以包括至少两组唇形相同的字符，且每一组唇形相同的字符的个数可以有两个或者两个以上，本实施例对此并不做限定。
唇形相反的字符是指字面不同且唇语发音规律相反的字符。由于‘固’和‘啊’、‘福’和‘海’、‘图’和‘帮’、‘我’和‘不’以及‘五’和‘八’均属于唇形相反的字符，所以请参考图2B中的(3)图，其示出了一种可能的唇语提示信息。可选地，唇语提示信息可以包括至少两组唇形相反的字符，且每一组唇形相反的字符的个数可以有两个或者两个以上，本实施例对此并不做限定。
当然，唇语提示信息还可以包括唇形相似度在预设范围内的至少两个目标字符，也即唇语提示信息可以包括唇形变化存在稳定的相似度关系的至少两个字符。其中，预设范围为第一阈值和第二阈值所构成的范围，第一阈值为大于0的数值，第二阈值为小于1的数值。比如，预设范围为0.4-0.6。具体的，由于‘福’和‘如’的唇形不完全相同也不完全相反，两者的唇形变化比较稳定，相似度在预设的0.4-0.6之间，则请参考图2B中的(4)图，唇语提示信息可以为‘福如东海寿比南山’等包含‘福’和‘如’的信息。
需要说明的是，图2B中省略号代表任意个数的任意字符，本实施例对此并不做限定。并且，上述只是以唇语提示信息只包括唇形相同的字符或者唇形相反的字符或者唇形相似度在预设范围内的字符为例，可选地，唇语提示信息 还可以同时包括上述任意两种或者三种的字符，比如，唇语提示信息可以为‘13572468’(‘1’和‘7’为唇形相同的字符，‘5’和‘8’为唇形相反的字符)。
此外，由于该唇语提示信息可以为终端生成的信息，也可以为终端从服务器中获取的信息。所以该步骤可以包括如下两种可能的实现方式：
第一种，生成包含至少两个目标字符的唇语提示信息。
终端可以随机生成该唇语提示信息。可选地，终端可以将预先生成的唇语提示信息存储至信息库中，从信息库中随机选择该唇语提示信息。
第二种，从服务器中获取包含至少两个目标字符的唇语提示信息，唇语提示信息为服务器预先生成的信息。
当唇语提示信息为服务器生成的信息时，终端可以发送信息获取请求至服务器，接收服务器随机返回的唇语提示信息。其中，该唇语提示信息可以为服务器随机生成的信息。
可选的，终端可以在检测到采集到的图像中包括人脸时，获取该唇语提示信息。比如，终端在检测到采集到的图像中包括人脸时，随机生成唇语提示信息，或者从信息库中选择预先存储的一组唇语提示信息；又比如，终端在检测到采集到的图像中包括人脸时，发送信息获取请求至服务器，该信息获取请求用于请求获取一组唇语提示信息，接收服务器返回的该唇语提示信息。
步骤202，提供唇语提示信息。
可选地，在第一种可能的实现方式中，终端以文本形式显示该唇语提示信息；
比如，以唇语提示信息为‘13572468’为例，请参考图2C，终端可以展示图图中所示的唇语提示信息。
可选地，在第二种可能的实现方式中，终端以视频形式显示该唇语提示信息；
可选地，在第三种可能的实现方式中，终端以音频形式播放该唇语提示信息。
为了提示被鉴别对象获知唇语提示信息执行何种操作，终端在提供该唇语提示信息的同时，还可以提供用于提示被鉴别对象读出唇语提示信息的信息。
步骤203，采集至少两帧图像。
当终端具有前置摄像头时，终端可以通过拍摄照片的方式采集到被鉴别对象的至少两帧图像。终端还可以通过拍摄视频的方式采集到被鉴别对象的至少 两帧图像。
步骤204，根据至少两帧图像获取被鉴别对象在读出至少两个目标字符时的唇部变化。
终端采集到至少两帧图像之后，终端可以根据至少两帧图像获取被鉴别对象在读出至少两个目标字符时的唇部变化。其中，本实施例中的被鉴别对象读出字符可以是发出声音的读出，也可以是只有唇部动作的读出，本实施例对此并不做限定。
可选地，本步骤可以包括：
第一，确定至少两帧图像中被鉴别对象在读出至少两个目标字符时的图像。
具体的，被鉴别对象在读出各个字符时，相邻字符之间通常会存在一定的停顿，也即相邻字符之间被鉴别对象的唇形会保持不变，所以终端可以依据该停顿确定被鉴别对象读出各个字符时所对应的图像，选择其中每个目标字符所对应的图像。具体的，终端可以根据目标字符在唇语提示信息中所处的位置来选择每个目标字符所对应的图像。其中，当唇语提示信息为终端自身生成时，终端可以根据生成唇语提示信息时的生成规则来预先获知每个目标字符的位置；而当唇语提示信息为终端从服务器中获取到的信息时，终端从服务器中获取唇语提示信息的同时，还可以从服务器中获取该唇语提示信息中的每个目标字符的位置，本实施例对此并不做限定。
比如，当唇语提示信息为图2C展示的信息时，由于目标字符分别位于字符串中第一位和第四位以及第三位和第八位，所以终端可以选择至少两帧图像中第一位和第四位以及第三位和第八位字符所对应的图像。
第二，从确定的图像中提取被鉴别对象在读出至少两个目标字符时的唇部图像序列，唇部图像序列用于表征被鉴别对象的唇部变化。
终端通过人脸识别技术，可以检测确定的图像中是否存在人脸。当存在人脸时，可以通过唇部颜色与肤色的区别确定人脸中的唇部的位置。在获取到唇部的位置之后，终端可以采用模型点的方法确定该图像中的被鉴别对象是否存在唇部变化。
模型点是指位于唇部边缘曲线上的角点，请参考图2D，一种可能的实施方式中，唇部的上边缘可以包括5个模型点222，唇部的下边缘也可以包括5个模型点222。
终端可以采用模型点的方法确定唇部各点的位置，构成某一时刻的唇部图像的一个状态。按照时间顺序，终端提取每个目标字符所对应的图像中的唇部图像，构成一个唇部图像序列。该唇部图像序列用于表征被鉴别对象在读出该目标字符时的唇部变化。
步骤205，检测被鉴别对象的唇部变化是否符合预设条件。
终端获取到被鉴别对象读出每个目标字符时的唇部变化之后，终端检测该被鉴别对象的唇部变化是否符合预设条件。具体的，本步骤可以包括：
若至少两个目标字符包括唇形相同的字符，则检测被鉴别对象在读出唇形相同的字符时的唇部变化是否相同。可选地，终端可以检测被鉴别对象在读出唇形相同的字符时的唇部图像序列是否相同。若相同，则判断被鉴别对象的唇部变化符合预设条件；反之，则不符合预设条件。
可选地，若唇部相同的字符有两组或者两组以上，则终端可以依次检测每组唇部相同的唇部图像序列是否相同。可选地，终端还可以选择两组或者两组以上唇形相同的字符中的至少一组唇部相同的字符的唇部图像序列，检测选择的每组唇部图像序列是否相同。
可选地，若每组唇形相同的字符有三个或者三个以上，则终端可以选择其中n个字符所对应的唇部图像序列，检测选择的n个字符的唇部图像序列是否相同。其中，n为大于等于2的整数。终端还可以检测每组唇形相同的字符的唇部图像序列中序列相同的个数是否达到预设阈值。比如，唇形相同的字符的个数有4个，终端可以检测4个字符的唇部图像序列中序列相同的个数是否达到3个，若达到，则判定符合预设条件，反之，则不符合预设条件。
若至少两个目标字符包括唇形相反的字符，则检测被鉴别对象在读出唇形相反的字符时的唇部变化是否相反。
这与唇形相同的字符的检测方法类似，详细技术细节请参考上述描述，在此不再赘述。
若至少两个目标字符包括唇形相似度在预设范围的字符，则检测被鉴别对象在读出唇形相似度在预设范围的字符时的唇部变化的相似度是否在预设范围内。
可选地，终端可以将至少两个目标字符的唇部图像序列输入至隐马尔科夫模型，隐马尔科夫模型计算接收到的各个唇部图像序列的匹配度，检测该匹配度是否在预设范围内。若在预设范围内，则确认符合预设条件；反之，则不符 合预设条件。
步骤206，若符合预设条件，则确定被鉴别对象是活体。
而如果检测结果为不符合预设条件，则终端确定被鉴别对象不是活体。
综上所述，本实施例提供的活体鉴别方法，通过在唇语提示信息中设置至少两个目标字符，检测采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时被鉴别对象的唇部变化是否符合预设条件，进而在检测结果为符合预设条件时，确定被鉴别对象为活体；其中，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
本实施例中的唇语提示信息为终端随机生成的信息，或者从服务器中获取的服务器随机生成的信息，避免了信息固定时，终端将包含读出唇语提示信息的视频也判定为活体，进而发生误判的问题，达到了可以提高判定准确率的效果。
需要补充说明的是，上述实施例只是以通过终端检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件来举例说明。可选地，还可以通过服务器来进行检测，此时，上述实施例中的步骤204和步骤205可以替换为步骤207至步骤210，请参考图2E，其示出了此时的活体鉴别方法的方法流程图。
步骤207，终端将至少两帧图像和唇语提示信息发送给服务器。
步骤208，服务器检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件。
相应的，服务器接收到至少两帧图像以及唇语提示信息之后，服务器可以检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件。其中，服务器的检测方法与终端的检测方法类似，详细技术细节请参考上述实施例中的步骤204和步骤205，本实施例在此不再赘述。
步骤209，服务器反馈检测结果至终端。
步骤210，终端接收服务器反馈的检测结果。
相应的，终端可以接收服务器反馈的检测结果。相应的，步骤206可以为：在检测结果表示被鉴别对象的唇部变化符合预设条件时，确定被鉴别对象为活体；而在检测结果表示被鉴别对象的唇部变化不符合预设条件时，确定被鉴别对象不是活体。
当唇语提示信息为终端从服务器中获取的信息时，在步骤207中终端还可以只发送至少两帧图像至服务器即可。
上述各个实施例中所说的唇语提示信息可以由终端自身生成，也可以由服务器生成，所以本发明实施例还提供了一种用于活体鉴别的唇语提示信息的生成方法，该方法包括：
根据预设规则生成唇语提示信息。其中，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符，唇语提示信息用于指示终端根据唇语提示信息鉴别被鉴别对象是否为活体。
可选的，该方法可以用于终端中，也可以用于服务器中。并且：
当该方法用于终端中时，终端可以在检测到采集到的图像中包括人脸时，根据该预设规则生成该唇语提示信息，可选的，终端还可以在任意时刻生成该唇语提示信息，并保存生成的该唇语提示信息。
当该方法用于服务器中时，服务器可以预先生成该唇语提示信息，并提供该唇语提示信息至终端。可选的，服务器可以在生成该唇语提示信息之后，可以自动发送该唇语提示信息至终端；或者，服务器在接收到终端发送的信息获取请求之后，返回该唇语提示信息至终端。另外，服务器还可以在接收到终端发送的触发请求之后，生成该唇语提示信息，并发送该唇语提示信息至终端。
另外，终端或者服务器在生成该唇语提示信息时，可以随机生成该唇语提示信息，本实施例对此并不做限定。
综上所述，本实施例提供的生成用于活体鉴别的唇语提示信息的方法，通过生成包括至少两个目标字符的唇语提示信息，该至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符，使得终端可以根据该唇语提示信息进行活体鉴别时，可以依据被鉴别对象读出该至少两个目标字符时的唇形变化来鉴别被鉴别对象是否为活体，解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是 活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
请参考图3，其示出了本发明一个实施例提供的活体鉴别装置的结构方框图。本实施例以该活体鉴别装置应用于终端中来举例说明。该活体鉴别装置可以通过软件、硬件或者两者的结合实现成为终端的全部或者一部分，该装置，包括：信息提供模块310、图像采集模块320、检测模块330和结果确定模块340。
信息提供模块310，用于提供唇语提示信息，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
图像采集模块320，用于采集至少两帧图像；
检测模块330，用于检测图像采集模块320采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件；
结果确定模块340，用于在检测模块330的检测结果为符合预设条件时，确定被鉴别对象是活体。
综上所述，本实施例提供的活体鉴别装置，通过在唇语提示信息中设置至少两个目标字符，检测采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时被鉴别对象的唇部变化是否符合预设条件，进而在检测结果为符合预设条件时，确定被鉴别对象为活体；其中，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
请参考图4，其示出了本发明另一实施例提供的活体鉴别装置的结构方框图。本实施例以该活体鉴别装置应用于终端中来举例说明。该活体鉴别装置可以通过软件、硬件或者两者的结合实现成为终端的全部或者一部分，该装置，包括：信息提供模块410、图像采集模块420、检测模块440和结果确定模块440。
信息提供模块410，用于提供唇语提示信息，唇语提示信息包括至少两个目标字符，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
图像采集模块420，用于采集至少两帧图像；
检测模块430，用于检测图像采集模块420采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件；
结果确定模块440，用于在检测模块430的检测结果为符合预设条件时，确定被鉴别对象是活体。
可选地，该检测模块430，包括：
获取单元431，用于根据至少两帧图像获取被鉴别对象在读出至少两个目标字符时的唇部变化；
检测单元432，用于在至少两个目标字符包括唇形相同的字符时，检测被鉴别对象在读出唇形相同的字符时的唇部变化是否相同；在至少两个目标字符包括唇形相反的字符时，检测被鉴别对象在读出唇形相反的字符时的唇部变化是否相反；在至少两个目标字符包括唇部变化范围属于预设范围的字符时，检测被鉴别对象在读出唇形相似度在预设范围的字符时的唇部变化的相似度是否在预设范围内。
可选地，该获取单元431，包括：
图像确定子单元431a，用于确定至少两帧图像中被鉴别对象在读出至少两个目标字符时的图像；
序列提取子单元431b，用于从图像确定子单元431a确定的图像中提取被鉴别对象在读出至少两个目标字符时的唇部图像序列，唇部图像序列用于表征被鉴别对象的唇部变化。
可选地，该检测模块430，还用于将至少两帧图像和唇语提示信息发送给服务器，服务器用于检测至少两帧图像中被鉴别对象在读出至少两个目标字符时，被鉴别对象的唇部变化是否符合预设条件。
可选地，该装置还包括：
生成模块450，用于生成包含至少两个目标字符的唇语提示信息；
或者，
获取模块460，用于从服务器中获取包含至少两个目标字符的唇语提示信 息，唇语提示信息为服务器预先生成的信息。
综上所述，本实施例提供的活体鉴别装置，通过在唇语提示信息中设置至少两个目标字符，检测采集到的至少两帧图像中被鉴别对象在读出至少两个目标字符时被鉴别对象的唇部变化是否符合预设条件，进而在检测结果为符合预设条件时，确定被鉴别对象为活体；其中，至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；解决了相关技术中即使被鉴别对象按照唇语提示信息进行操作时，终端也可能会将被鉴别对象误判为不是活体的问题；达到了终端可以准确判断被鉴别对象是否为活体，提高判别准确率的效果。
请参考图5，其示出了本发明一个实施例提供的终端的结构示意图。该终端用于实施上述实施例中提供的活体鉴别方法或者生成用于活体鉴别的唇语提示信息的方法。具体来讲：
终端500可以包括RF(Radio Frequency，射频)电路510、包括有一个或一个以上计算机可读存储介质的存储器520、输入单元530、显示单元540、传感器550、音频电路560、WiFi(wireless fidelity，无线保真)模块570、包括有一个或者一个以上处理核心的处理器580、以及电源590等部件。本领域技术人员可以理解，图5中示出的终端结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
RF电路510可用于收发信息或通话过程中，信号的接收和发送，特别地，将基站的下行信息接收后，交由一个或者一个以上处理器580处理；另外，将涉及上行的数据发送给基站。通常，RF电路510包括但不限于天线、至少一个放大器、调谐器、一个或多个振荡器、用户身份模块(SIM)卡、收发信机、耦合器、LNA(Low Noise Amplifier，低噪声放大器)、双工器等。此外，RF电路510还可以通过无线通信与网络和其他设备通信。所述无线通信可以使用任一通信标准或协议，包括但不限于GSM(Global System of Mobile communication，全球移动通讯***)、GPRS(General Packet Radio Service，通用分组无线服务)、CDMA(Code Division Multiple Access，码分多址)、WCDMA(Wideband Code Division Multiple Access,宽带码分多址)、LTE(Long Term Evolution,长期演进)、电子邮件、SMS(Short Messaging Service，短消息服务)等。
存储器520可用于存储软件程序以及模块，处理器580通过运行存储在存储器520的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器520可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作***、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据终端500的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器520可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器520还可以包括存储器控制器，以提供处理器580和输入单元530对存储器520的访问。
输入单元530可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。具体地，输入单元530可包括图像输入设备531以及其他输入设备532。图像输入设备531可以是摄像头，也可以是光电扫描设备。除了图像输入设备531，输入单元530还可以包括其他输入设备532。具体地，其他输入设备532可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
显示单元540可用于显示由用户输入的信息或提供给用户的信息以及终端500的各种图形用户接口，这些图形用户接口可以由图形、文本、图标、视频和其任意组合来构成。显示单元540可包括显示面板541，可选的，可以采用LCD(Liquid Crystal Display，液晶显示器)、OLED(Organic Light-Emitting Diode,有机发光二极管)等形式来配置显示面板541。
终端500还可包括至少一种传感器550，比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示面板541的亮度，接近传感器可在终端500移动到耳边时，关闭显示面板541和/或背光。作为运动传感器的一种，重力加速度传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于识别手机姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等；至于终端500还可配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
音频电路560、扬声器561，传声器562可提供用户与终端500之间的音 频接口。音频电路560可将接收到的音频数据转换后的电信号，传输到扬声器561，由扬声器561转换为声音信号输出；另一方面，传声器562将收集的声音信号转换为电信号，由音频电路560接收后转换为音频数据，再将音频数据输出处理器580处理后，经RF电路510以发送给比如另一终端，或者将音频数据输出至存储器520以便进一步处理。音频电路560还可能包括耳塞插孔，以提供外设耳机与终端500的通信。
WiFi属于短距离无线传输技术，终端500通过WiFi模块570可以帮助用户收发电子邮件、浏览网页和访问流式媒体等，它为用户提供了无线的宽带互联网访问。虽然图5示出了WiFi模块570，但是可以理解的是，其并不属于终端500的必须构成，完全可以根据需要在不改变发明的本质的范围内而省略。
处理器580是终端500的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在存储器520内的软件程序和/或模块，以及调用存储在存储器520内的数据，执行终端500的各种功能和处理数据，从而对手机进行整体监控。可选的，处理器580可包括一个或多个处理核心；优选的，处理器580可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作***、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器580中。
终端500还包括给各个部件供电的电源590(比如电池)，优选的，电源可以通过电源管理***与处理器580逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。电源590还可以包括一个或一个以上的直流或交流电源、再充电***、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
尽管未示出，终端500还可以包括蓝牙模块等，在此不再赘述。
具体在本实施例中，终端500还包括有存储器，以及一个或者一个以上的程序，其中一个或者一个以上程序存储于存储器中，且经配置以由一个或者一个以上处理器执行。上述一个或者一个以上程序包含用于执行如上述实施例所提供的活体鉴别方法或者生成用于活体鉴别的唇语提示信息的方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器，上述指令可由移动终端的处理器执行以完成活体鉴别方法或者上述生成用于活体鉴别的唇语提示信息的方法。例如，所述非临 时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
需要说明的是：上述实施例提供的活体鉴别装置在进行活体鉴别时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的活体鉴别装置与活体鉴别方法的方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅为本发明的较佳实施例，并不用以限制本发明，凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (11)

  1. 一种活体鉴别方法，其特征在于，所述方法包括：
    提供唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
    采集至少两帧图像；
    检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件；
    若符合所述预设条件，则确定所述被鉴别对象是活体。
  2. 根据权利要求1所述的方法，其特征在于，所述检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件，包括：
    根据所述至少两帧图像获取所述被鉴别对象在读出所述至少两个目标字符时的唇部变化；
    若所述至少两个目标字符包括唇形相同的字符，则检测所述被鉴别对象在读出唇形相同的字符时的唇部变化是否相同；
    若所述至少两个目标字符包括唇形相反的字符，则检测所述被鉴别对象在读出唇形相反的字符时的唇部变化是否相反；
    若所述至少两个目标字符包括唇形相似度在所述预设范围的字符，则检测所述被鉴别对象在读出所述唇形相似度在所述预设范围的字符时的唇部变化的相似度是否在所述预设范围内。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述至少两帧图像获取所述被鉴别对象在读出所述至少两个目标字符时的唇部变化，包括：
    确定所述至少两帧图像中所述被鉴别对象在读出所述至少两个目标字符时的图像；
    从确定的所述图像中提取所述被鉴别对象在读出所述至少两个目标字符时的唇部图像序列，所述唇部图像序列用于表征所述被鉴别对象的唇部变化。
  4. 根据权利要求1所述的方法，其特征在于，所述检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件，包括：
    将所述至少两帧图像和所述唇语提示信息发送给服务器，所述服务器用于检测所述至少两帧图像中所述被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件。
  5. 根据权利要求1至4任一所述的方法，其特征在于，所述提供唇语提示信息之前，所述方法还包括：
    生成包含所述至少两个目标字符的所述唇语提示信息；
    或者，
    从服务器中获取包含所述至少两个目标字符的所述唇语提示信息，所述唇语提示信息为所述服务器预先生成的信息。
  6. 一种生成用于活体鉴别的唇语提示信息的方法，其特征在于，所述方法包括：
    根据预设规则生成唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符，所述唇语提示信息用于指示终端根据所述唇语提示信息鉴别被鉴别对象是否为活体。
  7. 一种终端，其特征在于，所述终端包括：
    一个或多个处理器；和
    存储器；
    所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，所述一个或多个程序包含用于进行以下操作的指令：
    提供唇语提示信息，所述唇语提示信息包括至少两个目标字符，所述至少两个目标字符为唇形相同、唇形相反和唇形相似度在预设范围中的至少一种的字符；
    采集至少两帧图像；
    检测所述至少两帧图像中被鉴别对象在读出所述至少两个目标字符时，所 述被鉴别对象的唇部变化是否符合预设条件；
    若符合所述预设条件，则确定所述被鉴别对象是活体。
  8. 根据权利要求7所述的终端，其特征在于，所述一个或多个程序还包含用于进行以下操作的指令：
    根据所述至少两帧图像获取所述被鉴别对象在读出所述至少两个目标字符时的唇部变化；
    若所述至少两个目标字符包括唇形相同的字符，则检测所述被鉴别对象在读出唇形相同的字符时的唇部变化是否相同；
    若所述至少两个目标字符包括唇形相反的字符，则检测所述被鉴别对象在读出唇形相反的字符时的唇部变化是否相反；
    若所述至少两个目标字符包括唇形相似度在所述预设范围的字符，则检测所述被鉴别对象在读出所述唇形相似度在所述预设范围的字符时的唇部变化的相似度是否在所述预设范围内。
  9. 根据权利要求8所述的终端，其特征在于，所述一个或多个程序还包含用于进行以下操作的指令：
    确定所述至少两帧图像中所述被鉴别对象在读出所述至少两个目标字符时的图像；
    从确定的所述图像中提取所述被鉴别对象在读出所述至少两个目标字符时的唇部图像序列，所述唇部图像序列用于表征所述被鉴别对象的唇部变化。
  10. 根据权利要求7所述的终端，其特征在于，所述一个或多个程序还包含用于进行以下操作的指令：
    将所述至少两帧图像和所述唇语提示信息发送给服务器，所述服务器用于检测所述至少两帧图像中所述被鉴别对象在读出所述至少两个目标字符时，所述被鉴别对象的唇部变化是否符合预设条件。
  11. 根据权利要求7至10任一所述的终端，其特征在于，所述一个或多个程序还包含用于进行以下操作的指令：
    在提供唇语提示信息之前，生成包含所述至少两个目标字符的所述唇语提 示信息；
    或者，
    在提供唇语提示信息之前，从服务器中获取包含所述至少两个目标字符的所述唇语提示信息，所述唇语提示信息为所述服务器预先生成的信息。
PCT/CN2016/079893 2015-04-30 2016-04-21 活体鉴别方法、信息生成方法和终端 WO2016173453A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/462,423 US10607066B2 (en) 2015-04-30 2017-03-17 Living body identification method, information generation method, and terminal

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510218901.2A CN106203235B (zh) 2015-04-30 2015-04-30 活体鉴别方法和装置
CN201510218901.2 2015-04-30

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/462,423 Continuation US10607066B2 (en) 2015-04-30 2017-03-17 Living body identification method, information generation method, and terminal

Publications (1)

Publication Number Publication Date
WO2016173453A1 true WO2016173453A1 (zh) 2016-11-03

Family

ID=57198162

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/079893 WO2016173453A1 (zh) 2015-04-30 2016-04-21 活体鉴别方法、信息生成方法和终端

Country Status (3)

Country Link
US (1) US10607066B2 (zh)
CN (1) CN106203235B (zh)
WO (1) WO2016173453A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111753854A (zh) * 2020-07-28 2020-10-09 腾讯科技（深圳）有限公司 图像处理方法、装置、电子设备及存储介质
CN114330332A (zh) * 2021-12-28 2022-04-12 中国农业银行股份有限公司 表单数据的处理方法、装置、电子设备及存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107506687B (zh) * 2017-07-17 2020-01-21 Oppo广东移动通信有限公司 活体检测方法及相关产品
CN107832714B (zh) * 2017-11-14 2020-07-07 腾讯科技（上海）有限公司 活体鉴别方法、装置及存储设备
CN109409204B (zh) * 2018-09-07 2021-08-06 北京市商汤科技开发有限公司 防伪检测方法和装置、电子设备、存储介质
CN109376592B (zh) * 2018-09-10 2021-04-27 创新先进技术有限公司 活体检测方法、装置和计算机可读存储介质
CN109492585B (zh) * 2018-11-09 2023-07-25 联想(北京)有限公司 一种活体检测方法和电子设备
CN111611825B (zh) * 2019-02-25 2024-04-23 北京嘀嘀无限科技发展有限公司 一种唇语内容识别方法及装置
CN110765869B (zh) * 2019-09-18 2024-05-07 平安科技（深圳）有限公司 分渠道采集数据的唇语活体检测方法、***和计算机设备
CN112270288A (zh) * 2020-11-10 2021-01-26 深圳市商汤科技有限公司 活体识别、门禁设备控制方法和装置、电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080192980A1 (en) * 2007-02-14 2008-08-14 Samsung Electronics Co., Ltd. Liveness detection method and apparatus of video image
EP2546782A1 (en) * 2011-07-11 2013-01-16 Accenture Global Services Limited Liveness detection
CN104348778A (zh) * 2013-07-25 2015-02-11 信帧电子技术（北京）有限公司 一种在手机端进行人脸初步验证的远程身份认证的***、终端和方法
CN104376250A (zh) * 2014-12-03 2015-02-25 优化科技（苏州）有限公司 基于音型像特征的真人活体身份验证方法

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN86103658A (zh) * 1986-05-30 1987-01-14 潘之凯 利用嘴形及发音特点的汉字输入装置
CN1246793C (zh) * 2002-06-17 2006-03-22 中国科学院计算技术研究所 通过中间模式语言进行手语翻译的方法
US7702506B2 (en) * 2004-05-12 2010-04-20 Takashi Yoshimine Conversation assisting device and conversation assisting method
JP4286860B2 (ja) * 2004-05-21 2009-07-01 旭化成株式会社 動作内容判定装置
CN101482976B (zh) * 2009-01-19 2010-10-27 腾讯科技（深圳）有限公司 语音驱动嘴唇形状变化的方法、获取嘴唇动画的方法及装置
KR101092820B1 (ko) * 2009-09-22 2011-12-12 현대자동차주식회사 립리딩과 음성 인식 통합 멀티모달 인터페이스 시스템
CN102542280B (zh) * 2010-12-26 2016-09-28 上海量明科技发展有限公司 针对同一内容的不同唇语口型的识别方法及***
KR20130022607A (ko) * 2011-08-25 2013-03-07 삼성전자주식회사 입술 이미지를 이용한 음성 인식 장치 및 이의 음성 인식 방법
CN103092329A (zh) * 2011-10-31 2013-05-08 南开大学 一种基于唇读技术的唇语输入方法
KR101971697B1 (ko) * 2012-02-24 2019-04-23 삼성전자주식회사 사용자 디바이스에서 복합 생체인식 정보를 이용한 사용자 인증 방법 및 장치
US9159321B2 (en) * 2012-02-27 2015-10-13 Hong Kong Baptist University Lip-password based speaker verification system
CN103067460A (zh) * 2012-12-14 2013-04-24 厦门天聪智能软件有限公司 面向司法社区矫正的生物识别远程身份验证方法
CN104219371A (zh) * 2013-05-31 2014-12-17 中国电信股份有限公司 使用唇语识别技术进行电话拨号的方法和装置
CN103324918B (zh) * 2013-06-25 2016-04-27 浙江中烟工业有限责任公司 一种人脸识别与唇形识别相配合的身份认证方法
CN103425987B (zh) * 2013-09-03 2016-09-28 重庆邮电大学 基于双混合唇形特征提取的智能轮椅人机交互方法
US9626575B2 (en) * 2015-08-07 2017-04-18 International Business Machines Corporation Visual liveness detection

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080192980A1 (en) * 2007-02-14 2008-08-14 Samsung Electronics Co., Ltd. Liveness detection method and apparatus of video image
EP2546782A1 (en) * 2011-07-11 2013-01-16 Accenture Global Services Limited Liveness detection
CN104348778A (zh) * 2013-07-25 2015-02-11 信帧电子技术（北京）有限公司 一种在手机端进行人脸初步验证的远程身份认证的***、终端和方法
CN104376250A (zh) * 2014-12-03 2015-02-25 优化科技（苏州）有限公司 基于音型像特征的真人活体身份验证方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111753854A (zh) * 2020-07-28 2020-10-09 腾讯科技（深圳）有限公司 图像处理方法、装置、电子设备及存储介质
CN111753854B (zh) * 2020-07-28 2023-12-22 腾讯医疗健康(深圳)有限公司 图像处理方法、装置、电子设备及存储介质
CN114330332A (zh) * 2021-12-28 2022-04-12 中国农业银行股份有限公司 表单数据的处理方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
US20170193287A1 (en) 2017-07-06
CN106203235B (zh) 2020-06-30
US10607066B2 (en) 2020-03-31
CN106203235A (zh) 2016-12-07

Similar Documents

Publication Publication Date Title
WO2016173453A1 (zh) 活体鉴别方法、信息生成方法和终端
CN107944380B (zh) 身份识别方法、装置及存储设备
WO2018103525A1 (zh) 人脸关键点跟踪方法和装置、存储介质
US20170255767A1 (en) Identity Authentication Method, Identity Authentication Device, And Terminal
WO2019101015A1 (zh) 音频信号处理方法、装置和存储介质
CN109213732B (zh) 一种改善相册分类的方法、移动终端及计算机可读存储介质
CN108885614B (zh) 一种文本和语音信息的处理方法以及终端
US10353883B2 (en) Method, device and storage medium for providing data statistics
CN104852885B (zh) 一种进行验证码验证的方法、装置和***
WO2015127825A1 (zh) 表情输入方法、装置及电子设备
CN108494947B (zh) 一种图像分享方法及移动终端
WO2015078151A1 (zh) 一种图像处理的方法、装置及终端设备
CN106528545B (zh) 一种语音信息的处理方法及装置
WO2019105237A1 (zh) 图像处理方法、计算机设备和计算机可读存储介质
CN109003194B (zh) 评论分享方法、终端以及存储介质
US11086975B2 (en) Input method and electronic device
CN105630846B (zh) 头像更新方法及装置
WO2018107580A1 (zh) 一种信息提示的方法及装置
WO2018161540A1 (zh) 指纹注册方法及相关产品
WO2017050090A1 (zh) 生成gif文件的方法、设备及计算机可读存储介质
WO2018094911A1 (zh) 一种多媒体文件的分享方法及终端设备
TW201512987A (zh) 應用程式的啓動控制方法與裝置及電腦可讀取儲存介質
WO2017088434A1 (zh) 人脸模型矩阵训练方法、装置及存储介质
CN110555171A (zh) 一种信息处理方法、装置、存储介质及***
CN105513098B (zh) 一种图像处理的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16785884

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12/04/2018)

122 Ep: pct application non-entry in european phase

Ref document number: 16785884

Country of ref document: EP

Kind code of ref document: A1