CN103177238B - Terminal and user identification method - Google Patents
Terminal and user identification method Download PDFInfo
- Publication number
- CN103177238B CN103177238B CN201110440908.0A CN201110440908A CN103177238B CN 103177238 B CN103177238 B CN 103177238B CN 201110440908 A CN201110440908 A CN 201110440908A CN 103177238 B CN103177238 B CN 103177238B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- active user
- password
- voice
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of terminals, including the acquisition device for acquiring image data and voice data, further includes: mouth images acquisition module acquires oral area dynamic image data when active user inputs password by acquisition device；Voice acquisition module acquires voice data when active user inputs password by acquisition device；And judgment module, the voice data of the oral area dynamic image data of image capture module acquisition and voice acquisition module acquisition is compared with pre-stored data respectively, if all matching, confirms that active user is authorized user.Correspondingly, the present invention also provides a kind of user identification methods.According to the technical solution of the present invention, it can effectively identify that the user characteristics of forgery such as carry out the behavior of recognition of face by photo, strengthen the safety of identification process.
Description
Technical field
The present invention relates to user recognition technologies, in particular to a kind of terminal and a kind of user identification method.
Background technique
In the related art, user knows more and more otherwise, such as by modes such as recognition of face or speech recognitions,
It can be carried out efficiently identifying.But as above-mentioned identification method is used more and more extensive, also gradually manifest these knowledges
The defect of other mode can be passed through by the photo of user and be identified such as the mode of recognition of face, and the side of speech recognition
Formula can also be carried out by the way of recording, this is difficult to ensure for the safety of identification.
Therefore, it is necessary to a kind of new user recognition technologies, can effectively identify that the user characteristics of forgery such as pass through photo
The behavior for carrying out recognition of face, strengthens the safety of identification process.
Summary of the invention
The present invention is based on the above problems, proposes a kind of new user recognition technology, can effectively identify forgery
User characteristics such as by photo carry out recognition of face behavior, strengthen the safety of identification process.
In view of this, the invention proposes a kind of terminals, comprising: mouth images acquisition module is acquired by acquisition device
Active user inputs oral area dynamic image data when password；Voice acquisition module acquires the reality by the acquisition device
When voice data of user when inputting the password；And judgment module, respectively by mouth images acquisition module acquisition
The oral area dynamic image data and the voice data of voice acquisition module acquisition are compared with pre-stored data,
If all matching, confirm that the active user is authorized user.
In the technical scheme, while by voice and image technique user's identification is carried out, wherein voice technology, which refers to, adopts
Collect the sound of user, and after comparing with the sound of former owner, if matching, confirms；Image technique is by acquiring user
Real-time oral area dynamic image data, " dynamic " here also can using recording or photo etc. due in related art scheme
System of out-tricking enough is carried out, identification operation is completed, and if can prove the figure obtained when dynamic change occurs for the oral area of user
Picture and voice etc. avoid said circumstances from real user.Meanwhile in order to avoid using video file to be identified,
Here password can be one section of word, word etc. so that user is when reading the password, on the one hand to voice whether with award
Whether the voice match for weighing user, on the one hand match the language of reading and password on text, on the other hand lip-sync and mouth
It enables and whether being matched on text, judged comprehensively by above-mentioned aspect, to promote the safety of user's identification process.This
Outside, acquisition device here includes: camera, microphone etc., can be adopted to external image data and voice data etc.
Collection.
In the above-mentioned technical solutions, it is preferable that further include: facial image acquisition module is acquired by the acquisition device
The real-time face data of the active user；And the judgment module is also used to: the facial image acquisition module is acquired
The real-time face data be compared with the pre-stored data, if matching, confirm the active user be the authorization
User.In the technical scheme, " recognition of face " can also be carried out to user first, if can not be by identification, without carrying out
Identification step and system resource are saved in the identification of voice or the shape of the mouth as one speaks.
In the above-mentioned technical solutions, it is preferable that further include: Display processing module shows the mouth on the terminal
It enables, and the active user is prompted to read the password in preset time threshold.It in the technical scheme, can be in terminal
A word or a sentence are shown on screen, and user is prompted to read.When user reads the password, then terminal
The language data and mouth shape data of user can be obtained, simultaneously to carry out user's identification.
In the above-mentioned technical solutions, it is preferable that the judgment module specifically includes: phonetic decision submodule, by the reality
When voice data be compared with the voice data in the pre-stored data；Mouth images judging submodule moves the oral area
State image data is compared with the dynamic mouth shape data in the pre-stored data；And processing submodule, in institute's predicate
The judging result of sound judging submodule and the mouth images judging submodule is to confirm described real-time in the case where matching
User is the authorized user.In the technical scheme, preset data can be divided into multiple data, including language data, the shape of the mouth as one speaks
Data, face data etc. acquire voice, image etc. from authorized user, thus by mouth shape data, voice data, facial number
According to etc. various data compare respectively, complete identification to user.
In the above-mentioned technical solutions, it is preferable that further include: password acceptance module can not confirm that the active user is
In the case where the authorized user, the recognition code of the active user input is received；And password judgment module, described in judgement
Whether the recognition code that password acceptance module receives and default recognition code are identical, if they are the same, then confirm described real-time
User is the authorized user.In the technical scheme, terminal can not may effectively identify user for some reason, such as use
Family makes phonetic feature unobvious on account of illness or other reasons or user may wish other use for some reason
Family substitutes it from being obtained under information or some other reasons in terminal, in order to still be able to obtain the information in terminal, Ke Yishe
One or more one or more groups of super codes are set to gather around when other identification methods can not be identified effectively by the password
Some super keepe permissions pass through verifying and obtain the information in terminal.
According to another aspect of the invention, comprising: step 202, when acquiring active user input password by acquisition device
Oral area dynamic image data and voice data；Step 204, respectively by the oral area dynamic image data and the voice data
It is compared with pre-stored data, if all matching, confirms that the active user is authorized user.
In the technical scheme, while by voice and image technique user's identification is carried out, wherein voice technology, which refers to, adopts
Collect the sound of user, and after comparing with the sound of former owner, if matching, confirms；Image technique is by acquiring user
Real-time oral area dynamic image data, " dynamic " here also can using recording or photo etc. due in related art scheme
System of out-tricking enough is carried out, identification operation is completed, and if can prove the figure obtained when dynamic change occurs for the oral area of user
Picture and voice etc. avoid said circumstances from real user.Meanwhile in order to avoid using video file to be identified,
Here password can be one section of word, word etc. so that user is when reading the password, on the one hand to voice whether with award
Whether the voice match for weighing user, on the one hand match the language of reading and password on text, on the other hand lip-sync and mouth
It enables and whether being matched on text, judged comprehensively by above-mentioned aspect, to promote the safety of user's identification process.This
Outside, acquisition device here includes: camera, microphone etc., can be adopted to external image data and voice data etc.
Collection.
In the above-mentioned technical solutions, it is preferable that before the step 202, further includes: described in the acquisition device acquisition
The real-time face data of active user, and the real-time face data are compared with the pre-stored data；If described real-time
Face data matches with the pre-stored data, then confirms that the active user is the authorized user.In the technical scheme,
" recognition of face " can also be carried out to user first, if can not save by identification without carrying out the identification of voice or the shape of the mouth as one speaks
Identification step and system resource.
In the above-mentioned technical solutions, it is preferable that the step 202 further include: the password is shown on the terminal,
And the active user is prompted to read the password in preset time threshold.It in the technical scheme, can be in the screen of terminal
A word or a sentence are shown on curtain, and user is prompted to read.When user reads the password, then terminal can
To obtain the language data and mouth shape data of user simultaneously, to carry out user's identification.
In the above-mentioned technical solutions, it is preferable that the step 204 further include: the pre-stored data refers to and the password
Pronunciation match, dynamic mouth shape data and voice data from the authorized user；If the Real-time voice data with
The voice data in the pre-stored data matches, and the institute in the oral area dynamic image data and the pre-stored data
It states dynamic mouth shape data to match, then confirms that the active user is the authorized user.In the technical scheme, preset data
Multiple data, including language data, mouth shape data, face data etc., voice, image of the acquisition from authorized user can be divided into
Deng to the various data such as mouth shape data, voice data, face data be compared respectively, identification of the completion to user.
In the above-mentioned technical solutions, it is preferable that further include: if can not confirm, the active user is the authorized user,
Recognition code is filled in the terminal by the active user, if the recognition code is identical as default recognition code, really
Recognizing the active user is the authorized user.In the technical scheme, terminal can not may be identified effectively for some reason
User out, as user makes phonetic feature unobvious or other reasons or user may be for some reason on account of illness
And wishes other users and substitute it from being obtained under information or some other reasons in terminal, in order to still be able to obtain in terminal
Information, one or more one or more groups of super codes can be set, when other identification methods can not be identified effectively,
The super keepe permission possessed by the password passes through verifying and obtains the information in terminal.
By above technical scheme, it can effectively identify the user characteristics of forgery as carried out recognition of face by photo
Behavior strengthens the safety of identification process.
Detailed description of the invention
Fig. 1 shows the block diagram of the terminal of embodiment according to the present invention；
Fig. 2 shows the flow charts of the user identification method of embodiment according to the present invention；
Fig. 3 shows the specific flow chart of user's identification of embodiment according to the present invention；
Fig. 4 shows the specific flow chart of user's identification of embodiment according to the present invention；
Fig. 5 shows the specific flow chart of user's identification of embodiment according to the present invention；
Fig. 6 shows the specific flow chart of user's identification of embodiment according to the present invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, the present invention is not limited to following public specific realities
Apply the limitation of example.
Fig. 1 shows the block diagram of the terminal of embodiment according to the present invention.
As shown in Figure 1, the terminal 100 of embodiment according to the present invention, comprising: mouth images acquisition module 102, by adopting
Acquisition means acquire oral area dynamic image data when active user input password；Voice acquisition module 104, is adopted by acquisition device
Collect voice data when active user input password；And judgment module 106, mouth images acquisition module 102 is acquired respectively
Oral area dynamic image data and the voice data that acquires of voice acquisition module 104 be compared with pre-stored data, if all
Match, then confirms that active user is authorized user.
In the technical scheme, while by voice and image technique user's identification is carried out, wherein voice technology, which refers to, adopts
Collect the sound of user, and after comparing with the sound of former owner, if matching, confirms；Image technique is by acquiring user
Real-time oral area dynamic image data, " dynamic " here also can using recording or photo etc. due in related art scheme
System of out-tricking enough is carried out, identification operation is completed, and if can prove the figure obtained when dynamic change occurs for the oral area of user
Picture and voice etc. avoid said circumstances from real user.Meanwhile in order to avoid using video file to be identified,
Here password can be one section of word, word etc. so that user is when reading the password, on the one hand to voice whether with award
Whether the voice match for weighing user, on the one hand match the language of reading and password on text, on the other hand lip-sync and mouth
It enables and whether being matched on text, judged comprehensively by above-mentioned aspect, to promote the safety of user's identification process.This
Outside, acquisition device here includes: camera, microphone etc., can be adopted to external image data and voice data etc.
Collection.
In the above-mentioned technical solutions, further includes: facial image acquisition module 108 acquires active user by acquisition device
Real-time face data；And judgment module 106 is also used to: the real-time face data that facial image acquisition module 108 is acquired
It is compared with pre-stored data, if matching, confirms that active user is authorized user.It in the technical scheme, can also be first
" recognition of face " is carried out to user, if can not by identification, without carrying out the identification of voice or the shape of the mouth as one speaks, save identification step and
System resource.
In the above-mentioned technical solutions, further includes: Display processing module 110 shows password on the terminal 100, and prompts
Active user reads password in preset time threshold.In the technical scheme, one can be shown on the screen of terminal 100
A word or a sentence, and user is prompted to read.When user reads the password, then terminal can obtain use simultaneously
The language data and mouth shape data at family, to carry out user's identification.
In the above-mentioned technical solutions, judgment module 106 specifically includes: phonetic decision submodule 1062, by real-time voice number
It is compared according to the voice data in pre-stored data；Mouth images judging submodule 1064, by oral area dynamic image data with
Dynamic mouth shape data in pre-stored data is compared；And processing submodule 1066, in phonetic decision submodule 1062 and mouth
The judging result of portion's image judging submodule 1064 is in the case where matching, and confirmation active user is authorized user.At this
In technical solution, preset data can be divided into multiple data, including language data, mouth shape data, face data etc., acquire certainly
Voice, image of authorized user etc., so that the various data such as mouth shape data, voice data, face data are compared respectively,
Complete the identification to user.
In the above-mentioned technical solutions, further includes: password acceptance module 112 can not confirm that active user is authorized user
In the case where, receive the recognition code of active user input；And password judgment module 114, judge that password acceptance module 112 connects
Whether the recognition code received is identical as default recognition code, if they are the same, then confirms that active user is authorized user.In the technology
In scheme, terminal 100 can not may effectively identify user for some reason, as user makes phonetic feature on account of illness
Unobvious or other reasons or user may wish other users and substitute it and obtain from terminal 100 for some reason
Under information or some other reasons, in order to still be able to obtain the information in terminal 100, it can be set one group one or more
Or multiple groups super code is weighed when other identification methods can not be identified effectively by the super keepe that the password possesses
Limit, passes through verifying and obtains the information in terminal.
Fig. 2 shows the flow charts of the user identification method of embodiment according to the present invention.
As shown in Fig. 2, the user identification method of embodiment according to the present invention, comprising: step 202, pass through acquisition device
Acquire the oral area dynamic image data and voice data when active user input password；Step 204, respectively by oral area dynamic image
Data and voice data are compared with pre-stored data, if all matching, confirm that active user is authorized user.
In the technical scheme, while by voice and image technique user's identification is carried out, wherein voice technology, which refers to, adopts
Collect the sound of user, and after comparing with the sound of former owner, if matching, confirms；Image technique is by acquiring user
Real-time oral area dynamic image data, " dynamic " here also can using recording or photo etc. due in related art scheme
System of out-tricking enough is carried out, identification operation is completed, and if can prove the figure obtained when dynamic change occurs for the oral area of user
Picture and voice etc. avoid said circumstances from real user.Meanwhile in order to avoid using video file to be identified,
Here password can be one section of word, word etc. so that user is when reading the password, on the one hand to voice whether with award
Whether the voice match for weighing user, on the one hand match the language of reading and password on text, on the other hand lip-sync and mouth
It enables and whether being matched on text, judged comprehensively by above-mentioned aspect, to promote the safety of user's identification process.This
Outside, acquisition device here includes: camera, microphone etc., can be adopted to external image data and voice data etc.
Collection.
In the above-mentioned technical solutions, before step 202, further includes: the real-time face of acquisition device acquisition active user
Data, and real-time face data are compared with pre-stored data；If real-time face data match with pre-stored data, confirm
Active user is authorized user.In the technical scheme, " recognition of face " can also be carried out to user first, if knowledge can not be passed through
Not, then it is not necessarily to carry out the identification of voice or the shape of the mouth as one speaks, saves identification step and system resource.
In the above-mentioned technical solutions, step 202 further include: the password out displayed on the terminals, and prompt active user
Password is read in preset time threshold.In the technical scheme, can be shown on the screen of terminal a word or
One sentence, and user is prompted to read.When user reads the password, then terminal can obtain the language number of user simultaneously
According to and mouth shape data, to carry out user's identification.
In the above-mentioned technical solutions, step 204 further include: pre-stored data refer to it is matching with the pronunciation of password, come from
The dynamic mouth shape data and voice data of authorized user；If Real-time voice data matches with the voice data in pre-stored data,
And oral area dynamic image data matches with the dynamic mouth shape data in pre-stored data, then confirms that active user is authorized user.
In the technical scheme, preset data can be divided into multiple data, including language data, mouth shape data, face data etc., adopt
Collect voice, the image etc. from authorized user, so that the various data such as mouth shape data, voice data, face data be carried out respectively
The identification to user is completed in comparison.
In the above-mentioned technical solutions, further includes: if can not confirm, active user is authorized user, by active user in terminal
In fill in recognition code, if recognition code is identical as default recognition code, confirm active user be authorized user.In the technology
In scheme, terminal can not may effectively identify user for some reason, as user makes phonetic feature not on account of illness
Obvious or other reasons or user may wish that other users substitute it and obtain information from terminal for some reason,
Or under some other reasons, in order to still be able to obtain the information in terminal, it can be set one or more one or more groups of super
Grade password, when other identification methods can not be identified effectively, the super keepe permission possessed by the password is smoothly logical
Cross the information verified and obtained in terminal.
Fig. 3 shows the specific flow chart of user's identification of embodiment according to the present invention.
As shown in figure 3, the detailed process that the user of embodiment according to the present invention identifies is as follows:
Step 302, the screen of terminal is waken up, in this embodiment, be used to be in based on technical solution of the present invention
Terminal under standby mode reenters normal operating status.Certainly, technical solution of the present invention obviously can be also used for it
His a variety of occasions, for example for the unlatching etc. of customer identification device or the terminals such as mobile phone, computer when opening the door, can use in a word
The switching behaviour realized is identified by user in various.
Step 304, judge whether, if so, entering step 306, otherwise to enter step by normal recognition of face
316.By face recognition technology, the facial characteristics of user can be captured, but in actual use, use user's
Photo can also be authenticated by identification, this substantially reduces the safety in utilization of the technology.
Step 306, identifying code is shown on the screen.
Step 308, user reads identifying code.
Step 310A obtains Real-time voice data.
Step 310B obtains real-time mouth shape data.
Step 312, judge whether voice data matching and mouth shape data matches, if matching, enters step 314, otherwise
Enter step 316.Recognition of face only is carried out to user in step 304, it, also can be at using the photo of user but in practical application
Function passes through recognition of face, it is therefore desirable to other technological means is added, such as the reality obtained respectively in step 310A and step 310B
When voice data and real-time mouth shape data.Here the acquisition of real-time mouth shape data is to determine detected " face " no
It is the static images on photo, but from real " people ", it is dynamic that the shape of the mouth as one speaks can change with identifying code is read
Process.Meanwhile really whether the corresponding shape of the mouth as one speaks matches with identifying code to real-time mouth shape data, judgement is the dynamic shadow detected
It seem the video etc. obtained in real time, rather than play.In addition, avoiding using due to other by the detection of Real-time voice data
The facial characteristics at family may be similar with actual user, and has carried out Real-time and Dynamic Detection, and is mistaken for real user.Cause
This, by completing the real knowledge to user to many aspects and angles such as recognition of face, speech recognition, dynamic Mouth-Shape Recognitions
Not, the accuracy rate and safety of identification are improved.
Step 314, it is proved to be successful.
Step 316, super code is inputted.Here super code has highest permission, and others identification process is equal immediately
When failure, it can still be used to pass through verifying.This be in order to prevent due to such as user it is sick after, phonetic feature changes and nothing
Method, which correctly identifies, or user may want to by other users can then pass through from his terminal on behalf of some data are obtained
This mode is realized.
Step 318, judge whether super code is correct.
Step 320, authentication failed.
Fig. 4 shows the specific flow chart of user's identification of embodiment according to the present invention.
As shown in figure 4, the detailed process that the user of embodiment according to the present invention identifies is as follows:
Step 402, the screen of terminal is waken up, in this embodiment, be used to be in based on technical solution of the present invention
Terminal under standby mode reenters normal operating status.Certainly, technical solution of the present invention obviously can be also used for it
His a variety of occasions, for example for the unlatching etc. of customer identification device or the terminals such as mobile phone, computer when opening the door, can use in a word
The switching behaviour realized is identified by user in various.
Step 404, identifying code is shown on the screen.
Step 406, user reads identifying code.
Step 408A obtains Real-time voice data.
Step 408B obtains real-time mouth shape data.
Step 410, judge whether voice data matching and mouth shape data matches, if matching, enters step 412, otherwise
Enter step 414.If only carry out recognition of face to user also can successfully be led to using the photo of user in practical applications
Cross recognition of face, it is therefore desirable to other technological means are added, such as the real-time language obtained respectively in step 408A and step 408B
Sound data and real-time mouth shape data.Here it is to shine that the acquisition of real-time mouth shape data, which is to determine detected " face " not,
Static images of on piece, but from real " people ", the shape of the mouth as one speaks can change with identifying code is read, and be dynamic mistake
Journey.Meanwhile really whether the corresponding shape of the mouth as one speaks matches with identifying code to real-time mouth shape data, judgement is that the dynamic image detected is
The video etc. for obtaining, rather than playing in real time.In addition, being avoided by the detection of Real-time voice data due to other users
Facial characteristics may be similar with actual user, and has carried out Real-time and Dynamic Detection, and is mistaken for real user.Therefore, lead to
The real identification completed to many aspects and angles such as recognition of face, speech recognition, dynamic Mouth-Shape Recognitions to user is crossed, is mentioned
The accuracy rate and safety of identification are risen.
Step 412, judge whether, if so, entering step 418, otherwise to enter step by normal recognition of face
420.In step 410 it is determined that being true man, rather than the recording or video recording used, then further pass through recognition of face
Technology captures the facial characteristics of user, avoids causing to misidentify due to only acoustically similar.
Step 414, super code is inputted.Here super code has highest permission, and others identification process is equal immediately
When failure, it can still be used to pass through verifying.This be in order to prevent due to such as user it is sick after, phonetic feature changes and nothing
Method, which correctly identifies, or user may want to by other users can then pass through from his terminal on behalf of some data are obtained
This mode is realized.
Step 416, judge whether super code is correct.
Step 418, it is proved to be successful.
Step 420, authentication failed.
Fig. 5 shows the specific flow chart of user's identification of embodiment according to the present invention.
As shown in figure 5, the detailed process that the user of embodiment according to the present invention identifies is as follows:
Step 502, the screen of terminal is waken up, in this embodiment, be used to be in based on technical solution of the present invention
Terminal under standby mode reenters normal operating status.Certainly, technical solution of the present invention obviously can be also used for it
His a variety of occasions, for example for the unlatching etc. of customer identification device or the terminals such as mobile phone, computer when opening the door, can use in a word
The switching behaviour realized is identified by user in various.
Step 504, identifying code is shown on the screen.
Step 506, user reads identifying code.
Step 508, real-time mouth shape data is obtained.
Step 510, judge whether mouth shape data matches, if matching, enters step 512, otherwise enter step 514.If
Only carrying out recognition of face to user then in practical applications can also successfully pass recognition of face using the photo of user, therefore
Need to add other technological means, such as the Real-time voice data obtained respectively in step 508 and real-time mouth shape data.Here
The acquisition of real-time mouth shape data is in order to determine the static images on detected " face " not instead of photo, from real
" people ", the shape of the mouth as one speaks can with read identifying code and change, be dynamic process.Meanwhile to real-time mouth shape data with test
Really whether the corresponding shape of the mouth as one speaks matches card code, and judgement is that the dynamic image detected obtains in real time, rather than the view played
Frequency etc..Therefore, by dynamic Mouth-Shape Recognition etc. and angle, completing the real identification to user, identification is improved
Accuracy rate and safety.
Step 512, judge whether, if so, entering step 518, otherwise to enter step by normal recognition of face
520.In step 510 it is determined that being true man, rather than the photo or video recording used, then further pass through recognition of face
Technology captures the facial characteristics of user, avoids causing to misidentify due to only acoustically similar.
Step 514, super code is inputted.Here super code has highest permission, and others identification process is equal immediately
When failure, it can still be used to pass through verifying.This be in order to prevent due to such as user it is sick after, phonetic feature changes and nothing
Method, which correctly identifies, or user may want to by other users can then pass through from his terminal on behalf of some data are obtained
This mode is realized.
Step 516, judge whether super code is correct.
Step 518, it is proved to be successful.
Step 520, authentication failed.
Fig. 6 shows the specific flow chart of user's identification of embodiment according to the present invention.
As shown in fig. 6, the detailed process that the user of embodiment according to the present invention identifies is as follows:
Step 602, the screen of terminal is waken up, in this embodiment, be used to be in based on technical solution of the present invention
Terminal under standby mode reenters normal operating status.Certainly, technical solution of the present invention obviously can be also used for it
His a variety of occasions, for example for the unlatching etc. of customer identification device or the terminals such as mobile phone, computer when opening the door, can use in a word
The switching behaviour realized is identified by user in various.
Step 604, identifying code is shown on the screen.
Step 606, user reads identifying code.
Step 608A obtains Real-time voice data.
Step 608B obtains real-time mouth shape data.
Step 610, judge whether voice data matching and mouth shape data matches, if matching, enters step 616, otherwise
Enter step 612.In practical applications, recognition of face can also be successfully passed using the photo of user, it is therefore desirable to add it
His technological means, such as the Real-time voice data obtained respectively in step 608A and step 608B and real-time mouth shape data.Here
Real-time mouth shape data acquisition, be in order to determine the static images on detected " face " not instead of photo, from true
Positive " people ", the shape of the mouth as one speaks can change with identifying code is read, and be dynamic process.Meanwhile to real-time mouth shape data with
Really whether the corresponding shape of the mouth as one speaks matches identifying code, and judgement is what the dynamic image detected obtained in real time, rather than played
Video etc..In addition, avoiding the facial characteristics due to other users may be with actual user's class by the detection of Real-time voice data
Seemingly, and Real-time and Dynamic Detection has been carried out, and has been mistaken for real user.Therefore, by recognition of face, speech recognition, dynamic
The many aspects such as state Mouth-Shape Recognition and angle complete the real identification to user, improve the accuracy rate and safety of identification.
Step 612, super code is inputted.Here super code has highest permission, and others identification process is equal immediately
When failure, it can still be used to pass through verifying.This be in order to prevent due to such as user it is sick after, phonetic feature changes and nothing
Method, which correctly identifies, or user may want to by other users can then pass through from his terminal on behalf of some data are obtained
This mode is realized.
Step 614, judge whether super code is correct.
Step 616, it is proved to be successful.
Step 618, authentication failed.
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, it is contemplated that in the related art, face is known
Otherwise, can be by the photo of user by identification, and the mode of speech recognition, can also using by the way of recording into
Row, this is difficult to ensure for the safety of identification.It therefore, can the present invention provides a kind of terminal and a kind of user identification method
Effectively to identify that the user characteristics of forgery such as carry out the behavior of recognition of face by photo, the safety of identification process is strengthened
Property.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of terminal characterized by comprising
Mouth images acquisition module acquires oral area dynamic image data when active user inputs password by acquisition device；
Voice acquisition module acquires the voice data when active user inputs the password by the acquisition device；With
And
Judgment module, the oral area dynamic image data and the voice for respectively acquiring the mouth images acquisition module
The voice data of acquisition module acquisition is compared with pre-stored data, if all matching, confirms that the active user is to award
Weigh user；
Wherein, the terminal further include: facial image acquisition module acquires the reality of the active user by the acquisition device
When face data；And
The judgment module is also used to: the real-time face data that the facial image acquisition module acquires are prestored with described
Data are compared, if matching, confirm that the active user is the authorized user.
2. terminal according to claim 1, which is characterized in that further include:
Display processing module shows the password on the terminal, and prompts the active user in preset time threshold
It is interior to read the password.
3. terminal according to claim 1, which is characterized in that the judgment module specifically includes:
The Real-time voice data is compared by phonetic decision submodule with the voice data in the pre-stored data；
Mouth images judging submodule, by the dynamic shape of the mouth as one speaks number in the oral area dynamic image data and the pre-stored data
According to being compared；And
Submodule is handled, is phase in the judging result of the phonetic decision submodule and the mouth images judging submodule
In the case where matching, confirm that the active user is the authorized user.
4. terminal according to claim 1, which is characterized in that further include:
Password acceptance module receives the real-time use in the case where can not confirm the active user is the authorized user
The recognition code of family input；And
Password judgment module, judge the recognition code that the password acceptance module receives and default recognition code whether phase
Together, if they are the same, then confirm that the active user is the authorized user.
5. a kind of user identification method characterized by comprising
Step 202, the oral area dynamic image data and voice data when active user inputs password are acquired by acquisition device；
Step 204, the oral area dynamic image data and the voice data are compared with pre-stored data respectively, if all
Match, then confirms that the active user is authorized user；
Wherein, before the step 202, further includes:
The acquisition device acquires the real-time face data of the active user, and the real-time face data are prestored with described
Data are compared；
If the real-time face data match with the pre-stored data, confirm that the active user is the authorized user.
6. user identification method according to claim 5, which is characterized in that the step 202 further include:
The password out displayed on the terminals, and the active user is prompted to read the password in preset time threshold.
7. user identification method according to claim 5, which is characterized in that the step 204 further include:
The pre-stored data refer to dynamic mouth shape data matching with the pronunciation of the password, from the authorized user and
Voice data；
If the Real-time voice data matches with the voice data in the pre-stored data, and the oral area dynamic image
Data match with the dynamic mouth shape data in the pre-stored data, then confirm the active user for authorization use
Family.
8. user identification method according to claim 5, which is characterized in that further include:
If can not confirm, the active user is the authorized user, fills in recognition code in the terminal by the active user,
If the recognition code is identical as default recognition code, confirm that the active user is the authorized user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110440908.0A CN103177238B (en) | 2011-12-26 | 2011-12-26 | Terminal and user identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110440908.0A CN103177238B (en) | 2011-12-26 | 2011-12-26 | Terminal and user identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103177238A CN103177238A (en) | 2013-06-26 |
| CN103177238B true CN103177238B (en) | 2019-01-15 |
Family
ID=48637081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110440908.0A Active CN103177238B (en) | 2011-12-26 | 2011-12-26 | Terminal and user identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103177238B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348621A (en) * | 2013-08-02 | 2015-02-11 | 成都林海电子有限责任公司 | Authentication system based on voiceprint recognition and method thereof |
| CN103841108B (en) * | 2014-03-12 | 2018-04-27 | 北京天诚盛业科技有限公司 | The authentication method and system of user biological feature |
| CN104217212A (en) * | 2014-08-12 | 2014-12-17 | 优化科技（苏州）有限公司 | Real person identity verification method |
| CN104157015A (en) * | 2014-08-20 | 2014-11-19 | 优化科技（苏州）有限公司 | Self-service card dispenser control system |
| CN106911630A (en) * | 2015-12-22 | 2017-06-30 | 上海仪电数字技术股份有限公司 | Terminal and the authentication method and system of identity identifying method, terminal and authentication center |
| CN108573131B (en) * | 2017-03-09 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Method and device for controlling verification in terminal equipment |
| CN108427874A (en) * | 2018-03-12 | 2018-08-21 | 平安科技（深圳）有限公司 | Identity identifying method, server and computer readable storage medium |
| CN110348466A (en) * | 2018-04-08 | 2019-10-18 | 北京京东尚科信息技术有限公司 | The method and apparatus of identification |
| CN108830153A (en) * | 2018-05-07 | 2018-11-16 | 平安普惠企业管理有限公司 | For the auth method of recognition of face, device, equipment and storage medium |
| CN109377995B (en) * | 2018-11-20 | 2021-06-01 | 珠海格力电器股份有限公司 | Method and device for controlling equipment |
| CN109815806B (en) * | 2018-12-19 | 2024-06-28 | 平安科技（深圳）有限公司 | Face recognition method and device, computer equipment and computer storage medium |
| CN109547641B (en) * | 2018-12-21 | 2021-06-18 | 深圳市九州华科通讯有限公司 | Mode-controllable smart phone and corresponding method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070083375A1 (en) * | 2005-09-02 | 2007-04-12 | Delta Electronics, Inc. | Method and system for template inquiry dialogue system |
| CN102023703A (en) * | 2009-09-22 | 2011-04-20 | 现代自动车株式会社 | Combined lip reading and voice recognition multimodal interface system |
-
2011
- 2011-12-26 CN CN201110440908.0A patent/CN103177238B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070083375A1 (en) * | 2005-09-02 | 2007-04-12 | Delta Electronics, Inc. | Method and system for template inquiry dialogue system |
| CN102023703A (en) * | 2009-09-22 | 2011-04-20 | 现代自动车株式会社 | Combined lip reading and voice recognition multimodal interface system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103177238A (en) | 2013-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103177238B (en) | Terminal and user identification method | |
| TWI706268B (en) | Identity authentication method and device | |
| CN104598796B (en) | Personal identification method and system | |
| JP6096333B2 (en) | Method, apparatus and system for verifying payment | |
| US6107935A (en) | Systems and methods for access filtering employing relaxed recognition constraints | |
| US20070038460A1 (en) | Method and system to improve speaker verification accuracy by detecting repeat imposters | |
| US9311546B2 (en) | Biometric identity verification for access control using a trained statistical classifier | |
| US20160148012A1 (en) | System, method and apparatus for voice biometric and interactive authentication | |
| US10257191B2 (en) | Biometric identity verification | |
| CN105940407A (en) | Systems and methods for evaluating strength of an audio password | |
| US20060293898A1 (en) | Speech recognition system for secure information | |
| WO2010047817A1 (en) | Speaker verification methods and systems | |
| CN111611568A (en) | Face voiceprint rechecking terminal and identity authentication method thereof | |
| WO2010047816A1 (en) | Speaker verification methods and apparatus | |
| CN103678977A (en) | Method and electronic device for protecting information security | |
| CN106156575A (en) | A kind of user interface control method and terminal | |
| US20240185860A1 (en) | Methods and systems for processing audio signals containing speech data | |
| CN109670836A (en) | Account verification method, unit and computer readable storage medium | |
| CN107464562A (en) | Speech interactive charging system | |
| KR20140076056A (en) | Voice based CAPTCHA method and voice based CAPTCHA apparatus | |
| CN112417412A (en) | Bank account balance inquiry method, device and system | |
| KR20180049422A (en) | Speaker authentication system and method | |
| CN108985035B (en) | Control method and device for user operation authority, storage medium and electronic equipment | |
| CN110516426A (en) | Identity identifying method, certification terminal, device and readable storage medium storing program for executing | |
| CN111611569A (en) | Face voiceprint rechecking terminal and identity authentication method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |