CN105450664B

CN105450664B - A kind of information processing method and terminal

Info

Publication number: CN105450664B
Application number: CN201511020306.4A
Authority: CN
Inventors: 倪辉; 李季檩
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2015-12-29
Filing date: 2015-12-29
Publication date: 2019-04-12
Anticipated expiration: 2035-12-29
Also published as: CN105450664A

Abstract

The invention discloses a kind of information processing method and terminals, wherein the described method includes: terminal initiates the first request；The specified first information is shown or played in the display area；The first information is responded, acquisition of the triggering to terminal user face dynamic image when detecting that terminal user reads the first information generates the first multimedia messages according to the terminal user face dynamic image collected；The first reference area and the first reference zone corresponding with first reference area in first multimedia messages are extracted, analysis obtains the second motion change parameter for the first motion change parameter of the first reference area and for the first reference zone；It when detecting that the first motion change parameter is matched with the second motion change parameter, is verified by information security, so that first request that server receiving terminal is initiated.

Description

A kind of information processing method and terminal

Technical field

The present invention relates to mechanics of communication more particularly to a kind of information processing method and terminals.

Background technique

Present inventor at least has found exist in the related technology during realizing the embodiment of the present application technical solution Following technical problem:

With the development of internet technology, intelligent terminal is more more and more universal, cannot before may be implemented by intelligent terminal The many convenient services realized, for example water rate is paid on the net, the electricity charge, gas charge, communication expense etc. online payment service, for example lease Service can also realize that the various users such as intelligent terminal booting identification verification verify service, these services are all by online payment Belong to information security field, therefore, to assure that it is the operation of user, reflects the true intention of user, it otherwise, can be to use Various losses, including economic loss are brought in family, these can all influence information security, in the information based on oriented Internet Architecture In interaction, how to ensure that the information security of user is the technical issues that need to address, however, in the related technology, for the problem, It there is no effective solution.

Summary of the invention

In view of this, the embodiment of the present invention is desirable to provide a kind of information processing method and terminal, existing skill is solved at least Art there are the problem of, can ensure that the information security of user.

The technical solution of the embodiment of the present invention is achieved in that

A kind of information processing method of the embodiment of the present invention, the method are applied to terminal, and the terminal has viewing area Domain, which comprises

Terminal initiates the first request；

The specified first information is shown or played in the display area；

The first information is responded, triggering is to terminal user face when detecting that terminal user reads the first information The acquisition of dynamic image generates the first multimedia messages according to the terminal user face dynamic image collected；

Extract the first reference area in first multimedia messages and with first reference area corresponding first Reference zone, analysis obtain the first motion change parameter for the first reference area and the second fortune for the first reference zone Dynamic running parameter；

When detecting that the first motion change parameter is matched with the second motion change parameter, pass through information security school It tests, so that first request that server receiving terminal is initiated.

In above scheme, the first information includes: the information of static attribute and/or the information of dynamic attribute.

In above scheme, first reference area extracted in first multimedia messages and with first benchmark Corresponding first reference zone in region, analysis are obtained for the first motion change parameter of the first reference area and for the first ginseng The second motion change parameter in examination district domain, comprising:

First multimedia messages are parsed, at least X multi-medium data frame is obtained, X is the positive integer greater than 2；

From each frame of at least X multi-medium data frame, X first in terminal user face is oriented respectively Reference area and X the first reference zone corresponding with the X the first reference areas；

The first motion change parameter for the X the first reference areas is obtained according to the first preset rules；

The second motion change parameter for the X the first reference zones is obtained according to the second preset rules；

First preset rules and second preset rules are identical rule or different rule.

It is described to obtain the first movement for the X the first reference areas according to the first preset rules in above scheme Running parameter, comprising:

Based on first preset rules, in the first frame for obtaining at least X multi-medium data frame, the first reference region The corresponding direction of motion in domain and speed, as the first parameter value；

In the i-th frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the i-th reference area and speed, As the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

Motion change trace information is obtained according to i-th parameter value and first parameter value；

It is displaced on specified angle or assigned direction according to the motion change trace information superimposed motion, obtains described the One motion change parameter.

In above scheme, when first preset rules and second preset rules are identical rule, the basis Second preset rules obtain the second motion change parameter for the X the first reference zones, comprising:

Based on second preset rules, in the first frame for obtaining at least X multi-medium data frame, the first reference area The corresponding direction of motion in domain and speed, as the first parameter value；

In the i-th frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the i-th reference zone and speed, As the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

It is displaced on specified angle or assigned direction according to the motion change trace information superimposed motion, obtains described the Two motion change parameters.

It is described to detect that the first motion change parameter is matched with the second motion change parameter in above scheme When, it is verified by information security, comprising:

Correlation models are constructed according to the first motion change parameter and the second motion change parameter, according to institute It states correlation models and obtains relevance parameter, when the relevance parameter is greater than first threshold, determine that movement is consistent, by described Information security verification.

A kind of terminal of the embodiment of the present invention, the terminal have display area, and the terminal includes:

Request initiating cell, for initiating the first request；

Display unit, for showing or playing the specified first information in the display area；

Response unit, for responding the first information, the triggering when detecting that terminal user reads the first information Acquisition to terminal user face dynamic image generates more than first according to the terminal user face dynamic image collected Media information；

Extraction unit, for extract the first reference area in first multimedia messages and with first reference region Corresponding first reference zone in domain, analysis are obtained for the first motion change parameter of the first reference area and for the first reference The second motion change parameter in region；

Detection unit, when for detecting that the first motion change parameter is matched with the second motion change parameter, It is verified by information security, so that first request that server receiving terminal is initiated.

In above scheme, the extraction unit further comprises: parsing subunit, for parsing first multimedia Information, obtains at least X multi-medium data frame, and X is the positive integer greater than 2；

Locator unit, for orienting terminal user respectively from each frame of at least X multi-medium data frame X the first reference areas and X the first reference zone corresponding with the X the first reference areas in face；

First processing subelement, for obtaining first for the X the first reference areas according to the first preset rules Motion change parameter；

Second processing subelement, for obtaining second for the X the first reference zones according to the second preset rules Motion change parameter；

In above scheme, the first processing subelement is further used for:

In above scheme, the second processing subelement is further used for:

When first preset rules and second preset rules are identical rule, based on the described second default rule Then, in the first frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the first reference zone and speed are made For the first parameter value；

In above scheme, the detection unit is further used for:

The information processing method of the embodiment of the present invention includes: that terminal initiates the first request；Show in the display area or Play the specified first information；The first information is responded, the triggering pair when detecting that terminal user reads the first information The acquisition of terminal user face dynamic image generates more than first matchmaker according to the terminal user face dynamic image collected Body information；Extract the first reference area in first multimedia messages and the first ginseng corresponding with first reference area Examination district domain, analysis obtain the first motion change parameter for the first reference area and the second movement for the first reference zone Running parameter；When detecting that the first motion change parameter is matched with the second motion change parameter, pass through information security Verification, so that first request that server receiving terminal is initiated.

Using the embodiment of the present invention, after terminal initiates the first request, show or plays the specified in terminal display area One information；The first information is responded, triggering is to terminal user face when detecting that terminal user reads the first information The acquisition of dynamic image generates the first multimedia messages according to the terminal user face dynamic image collected；It extracts The first reference area and the first reference zone corresponding with first reference area in first multimedia messages compare The first motion change parameter for the first reference area and for the first reference zone the second motion change parameter whether one It causes, if unanimously, verified by information security, enables the server to first request of receiving terminal initiation, thus It is verified by this information security, can ensure that the information security of user, initiate to disguise oneself as user's to avoid counterfeit user Spurious requests improve information security grade.

Detailed description of the invention

Fig. 1 is the schematic diagram that each side's hardware entities of information exchange are carried out in the embodiment of the present invention；

Fig. 2 is an implementation process schematic diagram of the embodiment of the present invention one；

Fig. 3 is the display schematic diagram of prompt information in display interface of mobile phone of the embodiment of the present invention；

Fig. 4 is an implementation process schematic diagram of the embodiment of the present invention two；

Fig. 5 is a composed structure schematic diagram of the embodiment of the present invention five；

Fig. 6 is a hardware composed structure schematic diagram of the embodiment of the present invention ten；

Fig. 7 is the mobile phone interface display schematic diagram using one application scenarios of the embodiment of the present invention；

Fig. 8 is the implementation flow chart of mask of scratching a hole using the judgement of one application scenarios of the embodiment of the present invention；

Fig. 9 is the schematic diagram using one application scenarios lip motion direction and speed of the embodiment of the present invention；

Figure 10 is the lower lip that true man are simulated using one application scenarios of the embodiment of the present invention and the fluctuation of chin motion change Change curve；

Figure 11 is the fluctuating change curve of the lower lip and chin motion change using mask of scratching a hole.

Specific embodiment

The implementation of technical solution is described in further detail with reference to the accompanying drawing.

Fig. 1 is the schematic diagram that each side's hardware entities of information exchange are carried out in the embodiment of the present invention, includes: service in Fig. 1 Device 11-1n, terminal device 21-24, service for life platform or payment platform 31, terminal device 21-24 by cable network or Wireless network and server carry out information exchange, and terminal device includes the types such as mobile phone, desktop computer, PC machine, all-in-one machine, server (for example, pay water rate on the net, the electricity charge, gas charge is communicated for the first request for apply for service that 11-1n issues terminal device Take etc. online payment service；For example, the lease service realized by online payment；For example, intelligent terminal booting identification verification Verify and service etc. various users) safety check processing is carried out, safety check result is fed back into terminal device, if safety check knot Fruit passes through for safety check, then the first request of server 11-1n receiving terminal apparatus, directly accepts the first request and carry out institute First request can also be transmitted to service for life platform/payment platform 31 by the processing or server 11-1n for applying for service, First request is accepted by service for life platform/payment platform 31 and apply that the processing of service (pays water rate as realized, electricity Take, gas charge, lease service is realized in the service such as communication expense, realizes intelligent terminal booting identification service etc.).

Using the embodiment of the present invention, it is based on above-mentioned system shown in FIG. 1, terminal initiates the first request；In the viewing area Domain shows or plays the specified first information；The first information is responded, is detecting terminal user's reading first information When acquisition of the triggering to terminal user face dynamic image, generated according to the terminal user face dynamic image collected First multimedia messages；Extract the first reference area in first multimedia messages and corresponding with first reference area The first reference zone, analysis obtain for the first reference area the first motion change parameter and for the first reference zone Second motion change parameter；When detecting that the first motion change parameter is matched with the second motion change parameter (for example, Matching include it is identical, similar, opposite, etc. various rules be consistent), verified by information security, so that server receiving terminal First request initiated, to verify by this information security, can ensure that the information security of user, to avoid counterfeit use The spurious requests of user of disguising oneself as are initiated at family, improve information security grade.

The example of above-mentioned Fig. 1 is a system architecture example for realizing the embodiment of the present invention, and the embodiment of the present invention is not It is limited to system structure described in above-mentioned Fig. 1, is based on the system architecture, proposes each embodiment of the present invention.

Embodiment one:

A kind of information processing method of the embodiment of the present invention, the method are applied to terminal, and the terminal has viewing area Domain, as shown in Figure 2, which comprises

Step 101, terminal initiate the first request.

Here, first request for applying for service includes: to pay water rate on the net, the electricity charge, gas charge, and communication expense etc. props up on the net Pay service；Alternatively, the lease service realized by online payment；Alternatively, the various user schools such as intelligent terminal booting identification verification The service of testing；Alternatively, the account Sign-On services of social networks.

Step 102 shows or plays the specified first information in the display area.

Here, the first information can be information either statically or dynamically, shows static information or plays dynamic information.

When to be illustrated in figure 3 intelligent terminal be mobile phone, show passage in display interface of mobile phone, user is prompted to read Passage out, this section of text are identified with A11, to verify for information security.

Alternatively, one section of small video can be played in display interface of mobile phone, prompt user according to the list of characters in small video Feelings do same movement, to verify for information security；Alternatively, the personage in display interface of mobile phone small video can be followed to pronounce It is dubbed together to audio video synchronization, to be verified for information security；Alternatively, can also be pressed in a figure in display interface of mobile phone Multiple phrases in the image are found out in as requested, are practiced into a complete sentence, and read out the sentence, to be used for information security school It tests, alternatively, can also be in display interface of mobile phone according to the multiple phrases found out in the image as requested；Alternatively, can be with The song played in display interface of mobile phone according to one section synchronizes singing etc..It is not limited to citing description here, user It only needs to carry out corresponding operation according to the prompt on display interface of mobile phone, for example, executing according to prompt user a series of Voice operating.

Step 103, the response first information, when detecting that terminal user reads the first information, triggering is to terminal The acquisition of user face dynamic image generates the first multimedia letter according to the terminal user face dynamic image collected Breath.

Here, the first information is responded, when intelligent terminal is mobile phone, according to showing or broadcast in display interface of mobile phone The information alert put executes corresponding operation, for executing voice operating, (for example presses at this point it is possible to receive the first operation By way of this physical button on mobile phone of volume key as video record shutter triggers or tapping mobile phone screen is this What is shown in triggering mode, or click mobile phone screen starts recording this triggering mode of button etc. various modes) start afterwards Whether detection user starts the first information in read step 102, to trigger Image Acquisition, specifically: detecting terminal Acquisition of the triggering to terminal user face dynamic image when user reads the first information, according to the terminal collected User face dynamic image generates the first multimedia messages.

Step 104, extract the first reference area in first multimedia messages and with first reference area pair The first reference zone answered, analysis are obtained for the first motion change parameter of the first reference area and for the first reference zone The second motion change parameter.

Here, first reference area can be lip region, and first reference zone can be chin area, under Bar region is by being obtained after positioning lip region according to the positional relationship between each organ.

Step 105 when detecting that the first motion change parameter is matched with the second motion change parameter, passes through letter Safety check is ceased, so that first request that server receiving terminal is initiated.

Here, terminal judges whether are the first motion change parameter and the second motion change parameter by detecting Unanimously, if it is, being verified by information security, otherwise first request that server receiving terminal is initiated, does not pass through letter Safety check is ceased, server refuses the first request that terminal is initiated.

In one embodiment of the embodiment of the present invention, the first information includes: that the information of static attribute and/or dynamic belong to The information of property.

Embodiment two:

A kind of information processing method of the embodiment of the present invention, the method are applied to terminal, and the terminal has viewing area Domain, as shown in Figure 4, which comprises

Step 201, terminal initiate the first request.

Step 202 shows or plays the specified first information in the display area.

Step 203, the response first information, when detecting that terminal user reads the first information, triggering is to terminal The acquisition of user face dynamic image generates the first multimedia letter according to the terminal user face dynamic image collected Breath.

Here, the first information is responded, when intelligent terminal is mobile phone, according to showing or broadcast in display interface of mobile phone The information alert put executes corresponding operation, for executing voice operating, (for example presses at this point it is possible to receive the first operation By way of this physical button on mobile phone of volume key as video record shutter triggers or tapping mobile phone screen is this What is shown in triggering mode, or click mobile phone screen starts recording this triggering mode of button etc. various modes) start afterwards Whether detection user starts the first information in read step 202, to trigger Image Acquisition, specifically: detecting terminal Acquisition of the triggering to terminal user face dynamic image when user reads the first information, according to the terminal collected User face dynamic image generates the first multimedia messages.

Step 204, parsing first multimedia messages, obtain at least X multi-medium data frame, and X is just whole greater than 2 Number.

Step 205, from each frame of at least X multi-medium data frame, oriented in terminal user face respectively X the first reference areas and X the first reference zone corresponding with the X the first reference areas.

Step 206 is obtained according to the first preset rules (such as optical flow method analysis rule) for the X the first reference areas The first motion change parameter.

Step 207 obtains joining for the second motion change of the X the first reference zones according to the second preset rules Number.

Here, first preset rules and second preset rules are identical rule (as being all optical flow method analysis Rule) or different rule.

Here, 204-207 through the above steps, parses first multimedia messages, obtains at least X multimedia number According to frame, X is the positive integer greater than 2, obtains X the first reference areas and X first reference corresponding with X the first reference areas Region, analysis are obtained for the first motion change parameter of a first reference area of X and for the second of X the first reference zones Motion change parameter.

Here, the X the first reference areas can be lip region, and the X the first reference zones can be chin Region, chin area are by being obtained after positioning lip region according to the positional relationship between each organ.

Step 208 when detecting that the first motion change parameter is matched with the second motion change parameter, passes through letter Safety check is ceased, so that first request that server receiving terminal is initiated.

Embodiment three:

It is described to be obtained according to the first preset rules in the information processing method of the embodiment of the present invention based on embodiment one-bis- To the first motion change parameter for the X the first reference areas, comprising:

Step 301 is based on first preset rules, in the first frame for obtaining at least X multi-medium data frame, the The corresponding direction of motion of one reference area and speed, as the first parameter value；

Step 302 obtains in the i-th frame of at least X multi-medium data frame, the corresponding movement side of the i-th reference area To and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

Step 303 obtains motion change trace information according to i-th parameter value and first parameter value；

Step 304, in the specified coordinate axis direction (such as Y-axis in vertical direction) of coordinate system, according to the movement Variation track information superposition moving displacement obtains the first motion change parameter.

In the specified coordinate axis direction (such as Y-axis in vertical direction) of coordinate system, only the one of the embodiment of the present invention Specific implementation, the embodiment of the present invention on any direction that specified angle is identified or can be arbitrarily designated basis on direction The motion change trace information superimposed motion displacement, to obtain the first motion change parameter, such as can be at 45 degree of angles It is displaced on the direction identified according to the motion change trace information superimposed motion.Moreover, this superimposed motion is displaced institute's base In direction can convert at any time, by taking multi-medium data frame is video frame as an example, video frame is 300 frames, and preceding 150 frame can be Y-axis in vertical direction carries out moving displacement superposition, and it is folded that rear 150 frame can be the progress moving displacement of X-axis in the horizontal direction Add, naturally it is also possible to which in 150 frames, partial video frame is that moving displacement superposition, portion are carried out on the direction identified according to angle Point video frame is according to carrying out moving displacement superposition on assigned direction.

It is described to detect the first motion change parameter and described the in the information processing method of the embodiment of the present invention When two motion change parameters match, verified by information security, comprising: according to the first motion change parameter and described second Motion change parameter constructs correlation models, to obtain relevance parameter, the relevance parameter according to the correlation models When greater than first threshold (such as T), determines that movement is consistent, verified by the information security.

Example IV:

Based on embodiment one-tri-, in the information processing method of the embodiment of the present invention, first preset rules with it is described It is described to be obtained according to the second preset rules for a first reference zone of the X when second preset rules are identical rule Second motion change parameter, comprising:

Step 401 is based on second preset rules, in the first frame for obtaining at least X multi-medium data frame, the The corresponding direction of motion of one reference zone and speed, as the first parameter value；

Step 402 obtains in the i-th frame of at least X multi-medium data frame, the corresponding movement side of the i-th reference zone To and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

Step 403 obtains motion change trace information according to i-th parameter value and first parameter value；

Step 404, in the specified coordinate axis direction of coordinate system, according to the motion change trace information superimposed motion position It moves, obtains the second motion change parameter.

Embodiment five:

A kind of terminal of the embodiment of the present invention, as shown in figure 5, the terminal has display area, the terminal includes:

Request initiating cell 41, for initiating the first request；

Display unit 42, for showing or playing the specified first information in the display area；

Response unit 43, for responding the first information, the touching when detecting that terminal user reads the first information The acquisition to terminal user face dynamic image is sent out, generates first according to the terminal user face dynamic image collected Multimedia messages；

Extraction unit 44, for extract the first reference area in first multimedia messages and with first benchmark Corresponding first reference zone in region, analysis are obtained for the first motion change parameter of the first reference area and for the first ginseng The second motion change parameter in examination district domain；

Detection unit 45, for detecting that the first motion change parameter is matched with the second motion change parameter When, it is verified by information security, so that first request that server receiving terminal is initiated.

In one practical application of the embodiment of the present invention, apply for that first request of service includes: to pay water rate on the net, the electricity charge, Gas charge, communication expense etc. online payment service；Alternatively, the lease service realized by online payment；Alternatively, intelligent terminal is opened The various users such as machine identification verification verify service；Alternatively, the account Sign-On services of social networks.

In one practical application of the embodiment of the present invention, the first information can be information either statically or dynamically, show static state Information plays dynamic information.Be illustrated in figure 3 intelligent terminal be mobile phone when, a Duan Wen is shown in display interface of mobile phone Word prompts user to read out passage, this section of text is identified with A11, to verify for information security.Alternatively, can be in mobile phone One section of small video is played in display interface, user is prompted to do same movement according to the facial expression in small video, for believing Cease safety check；Alternatively, personage in display interface of mobile phone small video can be followed to pronounce to dub to audio video synchronization together, with It is verified in information security；Alternatively, can also be found out as requested in a figure in display interface of mobile phone more in the image A phrase is practiced into a complete sentence, and reads out the sentence, to verify for information security, alternatively, can also be aobvious in mobile phone Show in interface according to the multiple phrases found out in the image as requested；Alternatively, can also be in display interface of mobile phone according to one The song that section plays synchronizes singing etc..It is not limited to citing description here, user only needs according to display interface of mobile phone On prompt carry out corresponding operation, for example, executing a series of voice operatings according to prompt user.

In one practical application of the embodiment of the present invention, the first information is responded, when intelligent terminal is mobile phone, in mobile phone According to display or the information alert played in display interface, corresponding operation is executed, for executing voice operating, at this point, can (for example press what this physical button by mobile phone of volume key as video record shutter triggered to receive the first operation What is shown in mode or tapping this triggering mode of mobile phone screen, or click mobile phone screen starts recording this triggering of button The various modes of mode etc.) after start detect user whether start to read the first information, to trigger Image Acquisition, specifically: Acquisition of the triggering to terminal user face dynamic image when detecting that terminal user reads the first information, according to acquiring The terminal user face dynamic image arrived generates the first multimedia messages.

In one practical application of the embodiment of the present invention, first reference area can be lip region, first ginseng Examination district domain can be chin area, and chin area is by being obtained after positioning lip region according to the positional relationship between each organ It arrives.

In one practical application of the embodiment of the present invention, terminal judges the first motion change parameter and institute by detecting Whether consistent state the second motion change parameter, if it is, verifying by information security, server receiving terminal is initiated described Otherwise first request is not verified by information security, server refuses the first request that terminal is initiated.

In one embodiment of the embodiment of the present invention, the extraction unit further comprises: parsing subunit, for solving First multimedia messages are analysed, at least X multi-medium data frame is obtained, X is the positive integer greater than 2；And locator unit, it uses In each frame from at least X multi-medium data frame, X the first reference regions in terminal user face are oriented respectively Domain and X the first reference zone corresponding with the X the first reference areas；And first processing subelement, be used for basis First preset rules obtain the first motion change parameter for the X the first reference areas；And second processing subelement, it uses In obtaining the second motion change parameter for the X the first reference zone according to the second preset rules.Wherein, described first Preset rules and second preset rules are identical rule or different rule.

In one embodiment of the embodiment of the present invention, the first processing subelement is further used for: based on described first Preset rules, in the first frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the first reference area and speed Degree, as the first parameter value；In the i-th frame for obtaining at least X multi-medium data frame, the corresponding movement of the i-th reference area Direction and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；According to i-th parameter value and First parameter value obtains motion change trace information；In the specified coordinate axis direction of coordinate system, become according to the movement Change the displacement of trace information superimposed motion, obtains the first motion change parameter.

In one embodiment of the embodiment of the present invention, the second processing subelement is further used for: described first is default When regular and second preset rules are identical rule, it is based on second preset rules, at least X described in acquisition more matchmakers In the first frame of volume data frame, the corresponding direction of motion of the first reference zone and speed, as the first parameter value；Described in obtaining extremely In i-th frame of few X multi-medium data frame, the corresponding direction of motion of the i-th reference zone and speed, as the i-th parameter value；It is described I is the positive integer greater than 2 and less than or equal to X；Motion change track is obtained according to i-th parameter value and first parameter value Information；It in the specified coordinate axis direction of coordinate system, is displaced, is obtained described according to the motion change trace information superimposed motion Second motion change parameter.

In one embodiment of the embodiment of the present invention, the detection unit is further used for: being become according to first movement Change parameter and the second motion change parameter constructs correlation models, to obtain correlation ginseng according to the correlation models Number when the relevance parameter is greater than first threshold, determines that movement is consistent, is verified by the information security.

Above-described embodiment one-is fifth is that execute two parts operation in terminal: 1) executing image acquisition operation to obtain more than first Media information (such as one section of video)；2) the analysis processing for the first multimedia messages (such as video information) is executed in terminal, with It obtains for corresponding first motion change of the first reference area (mouth region) in the first multimedia messages (such as one section of video) Parameter, and for corresponding second fortune of the first reference zone (chin area) in the first multimedia messages (such as one section of video) Dynamic running parameter, constructs correlation models by this 2 parameters, to obtain relevance parameter according to the correlation models, When the relevance parameter is greater than first threshold, determines that movement is consistent, then verified by the information security.

Subsequent embodiment is different from above-described embodiment one-five, in above-mentioned two parts operation, the 1) part operation in terminal Middle execution, and 2) part operation execute in the server.

Embodiment six:

A kind of information processing method of the embodiment of the present invention, which is characterized in that the method is applied to terminal, the terminal Have display area, which comprises

Step 501, terminal initiate the first request；

Step 502 shows or plays the specified first information in the display area of terminal；

Step 503 responds the first information in terminal side, the touching when detecting that terminal user reads the first information The acquisition to terminal user face dynamic image is sent out, generates first according to the terminal user face dynamic image collected Multimedia messages；

Step 504, terminal send first multimedia messages to server, to carry out information security verification；

Step 505, terminal receive the safety check of server feedback as a result, if the safety check result is information security Verification passes through, then first request that terminal is initiated is received and accepted by server, if the safety check result is information Safety check does not pass through, then first request that terminal is initiated is refused to receive and refuses to accept by server.

Embodiment seven:

A kind of terminal of the embodiment of the present invention, the method are applied to terminal, and the terminal has display area, the end End includes:

Request initiating cell, for initiating the first request；

Request unit is verified, for sending first multimedia messages to server, to carry out information security verification；

Check results receiving unit, for receiving the safety check of server feedback as a result, if the safety check result Pass through for information security verification, then first request that terminal is initiated is received and accepted by server, if the safety check As a result do not pass through for information security verification, then first request that terminal is initiated is refused to receive and refuses to accept by server.

Embodiment eight:

A kind of information processing method of the embodiment of the present invention, the method are applied to server, which comprises

The first multimedia messages that step 601, server receiving terminal are sent；

Step 602, extract the first reference area in first multimedia messages and with first reference area pair The first reference zone answered, analysis are obtained for the first motion change parameter of the first reference area and for the first reference zone The second motion change parameter；

Step 603 when detecting that the first motion change parameter is matched with the second motion change parameter, passes through letter Safety check is ceased, to terminal, what receiving terminal was initiated described first requests and accept described first to ask feedback security check results It asks；At this point, safety check result information passes through for safety check；

Step 604, when detecting that the first motion change parameter and the second motion change parameter mismatch, it is obstructed Cross information security verification, feedback security check results to terminal, refuse receiving terminal is initiated described first request and refuse by Manage first request；At this point, safety check result information is that safety check does not pass through.

In one embodiment of the embodiment of the present invention, first reference area extracted in first multimedia messages And the first reference zone corresponding with first reference area, analysis obtain the first motion change for the first reference area Parameter and the second motion change parameter for the first reference zone, comprising:

Step 701, parsing first multimedia messages, obtain at least X multi-medium data frame, and X is just whole greater than 2 Number；

Step 702, from each frame of at least X multi-medium data frame, oriented in terminal user face respectively X the first reference areas and X the first reference zone corresponding with the X the first reference areas；

Step 703 obtains joining for the first motion change of the X the first reference areas according to the first preset rules Number；

Step 704 obtains joining for the second motion change of the X the first reference zones according to the second preset rules Number；

Step 705, first preset rules and second preset rules are identical rule or different rule Then.

It is described to be obtained according to the first preset rules for the X the first bases in one embodiment of the embodiment of the present invention The first motion change parameter in quasi- region, comprising:

Step 801 is based on first preset rules, in the first frame for obtaining at least X multi-medium data frame, the The corresponding direction of motion of one reference area and speed, as the first parameter value；

Step 802 obtains in the i-th frame of at least X multi-medium data frame, the corresponding movement side of the i-th reference area To and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

Step 803 obtains motion change trace information according to i-th parameter value and first parameter value；

Step 804, in the specified coordinate axis direction of coordinate system, according to the motion change trace information superimposed motion position It moves, obtains the first motion change parameter.

In one embodiment of the embodiment of the present invention, first preset rules are identical with second preset rules It is described to obtain the second motion change parameter for the X the first reference zones, packet according to the second preset rules when regular It includes:

Step 901 is based on second preset rules, in the first frame for obtaining at least X multi-medium data frame, the The corresponding direction of motion of one reference zone and speed, as the first parameter value；

Step 902 obtains in the i-th frame of at least X multi-medium data frame, the corresponding movement side of the i-th reference zone To and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

Step 903 obtains motion change trace information according to i-th parameter value and first parameter value；

Step 904, in the specified coordinate axis direction of coordinate system, according to the motion change trace information superimposed motion position It moves, obtains the second motion change parameter.

It is described to detect the first motion change parameter and second fortune in one embodiment of the embodiment of the present invention It when dynamic running parameter matching, is verified by information security, comprising: according to the first motion change parameter and second movement Running parameter constructs correlation models, and to obtain relevance parameter according to the correlation models, the relevance parameter is greater than When first threshold, determines that movement is consistent, verified by the information security.

Embodiment nine:

A kind of server of the embodiment of the present invention, the server include:

Receiving unit, for receiving the first multimedia messages of terminal transmission；

Detection unit is used for: when detecting that the first motion change parameter is matched with the second motion change parameter, It is verified by information security, feedback security check results are requested and accepted described to terminal, described the first of receiving terminal initiation First request；At this point, safety check result information passes through for safety check；Alternatively, detecting the first motion change parameter It when being mismatched with the second motion change parameter, is not verified by information security, feedback security check results are to terminal, refusal Described the first of receiving terminal initiation requests and refuses to accept first request；At this point, safety check result information is safety Verification does not pass through.

In one embodiment of the embodiment of the present invention, the extraction unit further comprises: parsing subunit, for solving First multimedia messages are analysed, at least X multi-medium data frame is obtained, X is the positive integer greater than 2；And locator unit, it uses In each frame from at least X multi-medium data frame, X the first reference regions in terminal user face are oriented respectively Domain and X the first reference zone corresponding with the X the first reference areas；And first processing subelement, be used for basis First preset rules obtain the first motion change parameter for the X the first reference areas；And second processing subelement, it uses In obtaining the second motion change parameter for the X the first reference zone according to the second preset rules；Described first is default Regular and second preset rules are identical rule or different rule.

In one embodiment of the embodiment of the present invention, the first subprocessing unit is further used for: being based on described first Preset rules, in the first frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the first reference area and speed Degree, as the first parameter value；In the i-th frame for obtaining at least X multi-medium data frame, the corresponding movement of the i-th reference area Direction and speed, as the i-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；According to i-th parameter value and First parameter value obtains motion change trace information；In the specified coordinate axis direction of coordinate system, become according to the movement Change the displacement of trace information superimposed motion, obtains the first motion change parameter.

In one embodiment of the embodiment of the present invention, the second subprocessing unit is further used for: described first is default When regular and second preset rules are identical rule, it is based on second preset rules, at least X described in acquisition more matchmakers In the first frame of volume data frame, the corresponding direction of motion of the first reference zone and speed, as the first parameter value；Described in obtaining extremely In i-th frame of few X multi-medium data frame, the corresponding direction of motion of the i-th reference zone and speed, as the i-th parameter value；It is described I is the positive integer greater than 2 and less than or equal to X；Motion change track is obtained according to i-th parameter value and first parameter value Information；It in the specified coordinate axis direction of coordinate system, is displaced, is obtained described according to the motion change trace information superimposed motion Second motion change parameter.

Embodiment ten:

, can also be for such as PAD it is to be herein pointed out above-mentioned terminal can be this electronic equipment of PC, tablet computer, This mancarried electronic aid of laptop computer can also be the intelligent mobile terminal such as mobile phone, be not limited to description here；It is described Server can be through group system composition, merge into one or each unit function split settings to realize each unit function Electronic equipment, client and server all includes at least database for storing data and the processing for data processing Device, or including the storage medium being set in server or the storage medium being independently arranged.

Wherein, for the processor for data processing, when executing processing, microprocessor, center can be used Processor (CPU, Central Processing Unit), digital signal processor (DSP, Digital Singnal Processor) or programmable logic array (FPGA, Field-Programmable Gate Array) is realized；For storage It include operational order for medium, which can be computer-executable code, be realized by the operational order Each step in embodiments of the present invention information processing method process.

The terminal and the server are as shown in Figure 6 as an example of hardware entities S11.Described device includes processor 61, storage medium 62 and at least one external communication interface 63；The processor 61, storage medium 62 and PERCOM peripheral communication connect Mouth 63 is connected by bus 64.

It need to be noted that: above is referred to the descriptions of client and server item, are similar with above method description , the beneficial effect with method describes, and does not repeat them here.For undisclosed technology in client and server embodiment of the present invention Details please refers to the description of embodiment of the present invention method.

The embodiment of the present invention is described below by taking a practical application scene as an example:

This application scene, which is reached for disguiser by this tool of mask of scratching a hole, usurps user's true identity, counterfeit use Family (attacker) issues the case where spurious requests, moves living systems to cheat lip, carries out living body attack, information security is caused to exist Risk.Wherein, an example of the mask of scratching a hole is: the photo taken to true user, by scratching figure work After tool scratches the photo upper lip part, cover on the mouth of camouflage user with the true user that disguises oneself as；The lip is dynamic to live System system refers to: the activity of lip being detected, is the operation of true people with determination, or the operation of simulation people；The work Body attack refers to: if replacing the operation of true people with the operation of simulation people, can be considered to attack living body.

For the application scenarios, face inspection and face method for registering can be used to position mouth region, extract mouth Characteristics of image such as obtains image spy by histograms of oriented gradients (HOG, Histogram of Oriented Gradient) Sign, or the image is obtained by scale invariant feature conversion (SIFT, Scale-invariant feature transform) Feature, or the characteristics of image etc. is obtained by local binary patterns (LBP, Local Binary Patterns), use branch It holds vector machine (SVM, Support Vector Machine) and carries out the opening one's mouth of confidence level, state classification of shutting up, SVM output Think that mouth has lip dynamic when closing the big Mr. Yu's threshold value T2 of maximum difference of amplitude, shows non-photograph, In vivo detection passes through.But Using this detection mode, there are attackers can scratch a hole in the eye portion and mouth of human face photo, covers on the face, mouth Expose, simulation true man speak, and cheat the problem of lip moves living systems.That is: robber can be reached by this tool of mask of scratching a hole With user's true identity.

Wherein, for HOG, HOG feature is that one kind is used to carry out object inspection in computer vision and image procossing The Feature Descriptor of survey.It is by calculating the gradient orientation histogram with statistical picture regional area come constitutive characteristic.Hog feature It has been widely used in image recognition in conjunction with SVM classifier, has implemented are as follows: divide the image into small connected region first Domain, referred to as cell factory, then acquire cell factory in each pixel gradient or edge direction histogram.Finally this A little set of histograms can be formed by profiler altogether.

For SIFT, SIFT is for that can detect key point in the picture, be a kind of office in field of image processing The description of portion's feature, this description have scale invariability.SIFT feature detection mainly includes 4 basic steps: 1) scale is empty Between extremum extracting: search for the picture position on all scales.It is identified by gaussian derivative function potentially for scale and rotation Turn constant point of interest；2) on the position of each candidate, position crucial point location: is determined by the fine model of a fitting It sets and scale.The selection gist of key point is in their degree of stability；3) direction determines: the gradient direction based on image local, Distribute to each key point position one or more direction.All subsequent operations to image data are both relative to key point Direction, scale and position are converted, to provide the invariance for these transformation；4) key point describes: in each key In neighborhood around point, the gradient of image local is measured on selected scale.These gradients are transformed into a kind of expression, this Indicate the deformation and illumination variation that allow bigger local shape.

For LBP, it is applied to Digital Image Processing and area of pattern recognition, is calculated as a kind of effective texture description Son, measurement and the texture information for extracting image local have invariance to illumination.LBP has many mutation or says improvement.It is a kind of LBP specific implementation are as follows: the comparative information of record pixel and its surrounding pixel point, or say difference.Certain is detected in original image Certain information of a pixel, such as original image are the image being made of 9 grids, for the intermediate grid in 9 grids (number in grid is pixel gray value size) is done a thresholding processing, more than or equal to central point pixel, is then marked It is 1, what is be less than is then labeled as 0.11110001 binary numbers around central pixel point are finally turned into decimal number, are obtained LBP value.The sequence of binary number 11110001 has no rigid requirement, as long as keeping identical sequence in same processing.

This application scene use the embodiment of the present invention, detect lip move situation under, from can tell automatically whether be The case where mask of scratching a hole is attacked, and issues spurious requests so as to avoid counterfeit user (attacker), avoids passing through mask of scratching a hole and takes advantage of It deceives lip and moves living systems, carry out living body attack, leading to information security, there are risks.To be mentioned significantly using the embodiment of the present invention High information security grade.

First: user's interactive mode.

The text of user's reading is indicated a need on mobile phone interface and starts to record a video, and user reads word, shoots the video certainly, such as schemes Shown in 7.

Second: user reads text according to the text for needing user to read gone out shown by mobile phone interface as shown in Figure 7 And shoot video.

Third analyzes video after shooting obtains video, to confirm that the video is the operation of user, without It is the operation for pretending user.

Here, concrete processing procedure is as shown in Figure 8, comprising:

Step 1001, Face datection and registration.

Step 1002, positioning mouth region.

Here, by step 1001-1002, mouth region is positioned using Face datection and face method for registering.

Step 1003, analysis lower lip movement.

Step 1004, estimation chin area.

Here, according to size of mouth and organ site relationship, the chin area of face is estimated, chin area is just in mouth Immediately below bar, region is big as mouth.

Step 1005, analysis chin movement.

Step 1006, analysis Movement consistency.

Here, this step includes following content:

A goes out the direction of motion and speed of lower lip region and chin area using optical flow method rule analysis, as shown in Figure 9 The numerous small arrows small arrow of mark (such as A12) represent current kinetic direction and displacement at this.The mouth of user is closing When conjunction, can be found that by the optical flow analysis figure of lower lip and chin as shown in Figure 9: the motion conditions with true man are consistent 's.

B obtains the moving displacement of every interframe of lower lip and chin in video and adds up in vertical direction (Y-axis), under In lip region, the Y-axis displacement component of all optical flow analysis points is cumulative, the motion bit in the vertical direction current as lower lip Move deltaY.If initial displacement SY0=0, for video since the second frame, SYn=SY (n-1)+deltaY records all SYn values Motion change as lower lip.Chin is similarly.

C calculates the correlation of the motion excursion curve fluctuating change of lower lip and chin, uses the distance metric side cosine Method calculates correlation.Because there are noise jamming in practical application, therefore, it is necessary to calculate lower lip and chin wave by formula (2) Before dynamic change curve, optionally, the noise jamming of interframe is excluded by formula (1).It is removed by formula (2) overall inclined It moves, retains localized variation.Relevance parameter sim is calculated by the cosine distance metric method of formula (3).

Removal shake D=gaussianblur (SYn), kernelsize=5 (1)

Fluctuating change curve C=D-gaussianblur (D), kernelsize=51 (2)

Correlation sim=cosine_similarity (C lower lip, C chin) (3)

Analysis chart 10-11, Figure 10 are the lower lip of true man and fluctuating change the curve C, Figure 11 of chin motion change are to adopt With the lower lip and chin motion change C of mask of scratching a hole, it will thus be seen that the lower lip of true man and the fluctuation of chin motion change become Change, the two is much like；Using the lower lip for mask of scratching a hole and the fluctuating change of chin motion change, the two is dissimilar 's.

When step 1007, Movement consistency, judge to scratch a hole that mask is attacked currently employed.

Here, by obtaining correlation sim in step 1006, when judging the whether big Mr. Yu threshold value T of correlation sim, if Greater than T, then it is assumed that movement is consistent, then being detected as true man's operation, otherwise, is detected as mask attack of scratching a hole.

In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only A kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can combine, or It is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each composition portion Mutual coupling or direct-coupling or communication connection is divided to can be through some interfaces, the INDIRECT COUPLING of equipment or unit Or communication connection, it can be electrical, mechanical or other forms.

Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit The component shown can be or may not be physical unit, it can and it is in one place, it may be distributed over multiple network lists In member；Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.

In addition, each functional unit in various embodiments of the present invention can be fully integrated in one processing unit, it can also To be each unit individually as a unit, can also be integrated in one unit with two or more units；It is above-mentioned Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.

Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned include: movable storage device, it is read-only Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or The various media that can store program code such as person's CD.

If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented Substantially the part that contributes to existing technology can be embodied in the form of software products the technical solution of example in other words, The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention. And storage medium above-mentioned includes: that movable storage device, ROM, RAM, magnetic or disk etc. are various can store program code Medium.

The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.

Claims

1. a kind of information processing method, which is characterized in that the method is applied to terminal, and the terminal has display area, institute The method of stating includes:

Terminal initiates the first request；

The specified first information is shown or played in the display area；

The first information is responded, triggering is to terminal user face dynamic when detecting that terminal user reads the first information The acquisition of image generates the first multimedia messages according to the terminal user face dynamic image collected；

Extract the first reference area in first multimedia messages and the first reference corresponding with first reference area Region, analysis obtains the first motion change parameter for the first reference area and the second movement for the first reference zone becomes Change parameter；Wherein, first reference area is lip region；First reference zone is chin area；

Detect that the degree of correlation between the first motion change parameter and the second motion change parameter is greater than first threshold When, it is verified by information security, so that first request that server receiving terminal is initiated.

2. the method according to claim 1, wherein the first information include: static attribute information and/or The information of dynamic attribute.

3. the method according to claim 1, wherein first base extracted in first multimedia messages Quasi- region and the first reference zone corresponding with first reference area, analysis obtain the first fortune for the first reference area Dynamic running parameter and the second motion change parameter for the first reference zone, comprising:

From each frame of at least X multi-medium data frame, X the first benchmark in terminal user face are oriented respectively Region and X the first reference zone corresponding with the X the first reference areas；

4. according to the method described in claim 3, it is characterized in that, described obtain according to the first preset rules for the X First motion change parameter of the first reference area, comprising:

Based on first preset rules, in the first frame for obtaining at least X multi-medium data frame, the first reference area pair The direction of motion and speed answered, as the first parameter value；

In the i-th frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the i-th reference area and speed, as I-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

It is displaced on specified angle or assigned direction according to the motion change trace information superimposed motion, obtains first fortune Dynamic running parameter.

5. according to the method described in claim 3, it is characterized in that, first preset rules are with second preset rules It is described to obtain joining for the second motion change of the X the first reference zones according to the second preset rules when identical rule Number, comprising:

Based on second preset rules, in the first frame for obtaining at least X multi-medium data frame, the first reference zone pair The direction of motion and speed answered, as the first parameter value；

In the i-th frame for obtaining at least X multi-medium data frame, the corresponding direction of motion of the i-th reference zone and speed, as I-th parameter value；The i is the positive integer greater than 2 and less than or equal to X；

It is displaced on specified angle or assigned direction according to the motion change trace information superimposed motion, obtains second fortune Dynamic running parameter.

6. method according to any one of claims 1 to 4, which is characterized in that described to detect first motion change When parameter is matched with the second motion change parameter, verified by information security, comprising:

Correlation models are constructed according to the first motion change parameter and the second motion change parameter, according to the phase Closing property model obtains relevance parameter, when the relevance parameter is greater than first threshold, determines that movement is consistent, passes through the information Safety check.

7. a kind of terminal, which is characterized in that the terminal has display area, and the terminal includes:

Request initiating cell, for initiating the first request；

Response unit, for responding the first information, when detecting that terminal user reads the first information, triggering is to end The acquisition of end subscriber face dynamic image generates the first multimedia according to the terminal user face dynamic image collected Information；

Extraction unit, for extract the first reference area in first multimedia messages and with first reference area pair The first reference zone answered, analysis are obtained for the first motion change parameter of the first reference area and for the first reference zone The second motion change parameter；Wherein, first reference area is lip region；First reference zone is chin area Domain；

Detection unit, for detecting the degree of correlation between the first motion change parameter and the second motion change parameter It when greater than first threshold, is verified by information security, so that first request that server receiving terminal is initiated.

8. terminal according to claim 7, which is characterized in that the first information include: static attribute information and/or The information of dynamic attribute.

9. terminal according to claim 7, which is characterized in that the extraction unit further comprises: parsing subunit, For parsing first multimedia messages, at least X multi-medium data frame is obtained, X is the positive integer greater than 2；

Locator unit, for orienting terminal user face respectively from each frame of at least X multi-medium data frame In X the first reference areas and X the first reference zone corresponding with the X the first reference areas；

First processing subelement, for obtaining the first movement for the X the first reference areas according to the first preset rules Running parameter；

Second processing subelement, for obtaining the second movement for the X the first reference zones according to the second preset rules Running parameter；

10. terminal according to claim 9, which is characterized in that the first processing subelement is further used for:

11. terminal according to claim 9, which is characterized in that the second processing subelement is further used for:

When first preset rules and second preset rules are identical rule, second preset rules are based on, are obtained In the first frame for taking at least X multi-medium data frame, the corresponding direction of motion of the first reference zone and speed, as first Parameter value；

12. according to the described in any item terminals of claim 7 to 11, which is characterized in that the detection unit is further used for: