Invention content
The embodiment of the invention discloses a kind of image processing methods applied to instant communication client session log, can
In the case of the non-screen locking of the electronic equipment where instant communication client, prevent include in instant communication client session log
Important image by other people pry through to, reduce instant communication client session log in include important image reveal
Risk.
Wherein, a kind of image processing method applied to instant communication client session log, the instant messaging client
Hold loading on an electronic device, the method includes:
The electronic equipment detects
Target image first touch operation;
The electronic equipment response described first touches operation, exports the corresponding image level menu of the target image;
Described image rank menu includes important image level and insignificant image level;
If the important image level that described image rank menu includes is selected, the electronic device prompts are from described
First telephone voice signal and second telephone voice signal are selected in session log;
The first telephone voice signal and second dialogue that the electronic equipment detection is selected from the session log
Voice signal;Wherein, issuing time of the first telephone voice signal in the session log is earlier than the target figure
Issuing time of the picture in the session log, and publication of the second telephone voice signal in the session log
The time also issuing time earlier than the target image in the session log;Wherein, in the session log described in publication
One side of dialogue of first telephone voice signal is different from issuing second telephone voice signal in the session log
Talk with another party;
The electronic equipment closes first telephone voice signal and second telephone voice signal
At being verified voice signal;
The verification voice signal is associated by the electronic equipment with the target image, and is remembered in the dialogue
In record the target image is covered using default insignificant picture;Wherein, the verification voice signal is used as has covered for removing
Cover the foundation for presetting insignificant picture of the target image.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment is by the verification voice signal
It is associated with the target image, and the target image is covered using default insignificant picture in the session log
Later, the method further includes:
The electronic equipment detection presets insignificant figure to having covered the described of the target image in the session log
The second of piece touches operation;
The electronic equipment response described second touches operation, prompts to select third dialogue sound from the session log
Sound signal and the 4th telephone voice signal;
The third telephone voice signal and the 4th dialogue that the electronic equipment detection is selected from the session log
Voice signal;
Whether the electronic equipment judges issuing time of the third telephone voice signal in the session log
Earlier than issuing time of the target image in the session log and the 4th telephone voice signal described right
The issuing time whether also issuing time earlier than the target image in the session log in words record;
If issuing time of the third telephone voice signal in the session log exists earlier than the target image
Issuing time in the session log and the 4th issuing time of the telephone voice signal in the session log
Also the issuing time earlier than the target image in the session log judges to issue the third in the session log
Whether one side of dialogue of telephone voice signal is another with the dialogue of issuing the 4th telephone voice signal in the session log
One side is identical;
If one side of dialogue for issuing the third telephone voice signal in the session log remembers different from the dialogue
Dialogue another party of the 4th telephone voice signal is issued in record, the electronic equipment believes the third telephone voice
Number and the 4th telephone voice signal synthesized to obtain synthetic video signal;
The electronic equipment judges whether the synthetic video signal matches with the verification voice signal, will if matching
The default insignificant picture for having covered the target image is removed, to show the target image.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment is to the third dialogue sound
Sound signal and the 4th telephone voice signal are synthesized to obtain synthetic video signal, including:
The electronic equipment determines between the third telephone voice signal and the 4th telephone voice signal
Snap point;Wherein, the snap point refers to the third telephone voice signal and the 4th telephone voice signal synthesis
Starting position;
The electronic equipment is according to the snap point by the third telephone voice signal and the 4th dialogue sound
Sound signal synthesizes synthetic video signal.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment determines the third dialogue
Snap point between voice signal and the 4th telephone voice signal, including:
The electronic equipment calculates the first duration of the third telephone voice signal and the 4th dialogue sound
Second duration of sound signal;Wherein, first duration indicates the time of the sound go of the third telephone voice signal;
Second duration indicates the time of the sound go of the 4th telephone voice signal;
The electronic equipment calculates the difference between first duration and second duration;
The electronic equipment judges whether the difference is less than or equal to default value, if so, talking with to the third
Any telephone voice signal in voice signal and the 4th telephone voice signal carries out the scaling on the period, to obtain most
The whole identical third telephone voice signal of duration and the 4th telephone voice signal, then with the final duration phase
The first audio frame of same third telephone voice signal and the 4th telephone voice signal is as snap point.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment is to the third dialogue sound
Any telephone voice signal in sound signal and the 4th telephone voice signal carries out the scaling on the period, including:
If the first duration of the third telephone voice signal relative to the 4th telephone voice signal second
Duration is shorter, when the electronic equipment determines that the difference accounts for the first of the third telephone voice signal according to the difference
Long ratio X;
The electronic equipment calculates the audio frame number Y of the third telephone voice signal;
The electronic equipment calculates amplification coefficient Z, the Z=X* (Y/ (Y-1));
The electronic equipment according to the amplification coefficient, in the third telephone voice signal in addition to first audio frame
Except other audio frames carry out equal proportion amplification so that the final duration of amplified third telephone voice signal
It is identical as the 4th second duration of telephone voice signal.
As an alternative embodiment, in the embodiment of the present invention, it is described if the difference is more than the default value
Method further includes:
The electronic equipment is using identical default sample frequency to the third telephone voice signal and described the
Four telephone voice signals are sampled respectively, obtain the first set of samples and the second set of samples;
The electronic equipment according to the default sample frequency, first set of samples, second set of samples and mutually
Related weights generate cross-correlation group;Wherein, the cross-correlation weights and the difference positive correlation include in the cross-correlation group
Multiple numerical value;
Multiple numerical value in the cross-correlation group are compared by the electronic equipment, find out maximum numerical value;
The electronic equipment uses the corresponding audio frame position of the maximum numerical value as snap point.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment is according to default sample frequency
Rate, first set of samples, second set of samples and cross-correlation weights generate cross-correlation group, including:
Wherein, Sn[t] indicates that cross-correlation group, x [m] indicate m-th of sampled data in first set of samples, y [m-t]
Indicate (m-t) a sampled data in second set of samples, t indicates the offset of time, and t is integer, value be from 0 to
M, WtIndicate that window function, wherein n=l*f, l are cross-correlation weights, f is the default sample frequency.
As an alternative embodiment, in the embodiment of the present invention, the electronic equipment judges the synthetic sound message
Number whether matched with the verification voice signal, including:
The electronic equipment pre-processes the synthetic video signal, and pretreatment includes preemphasis, framing and adding window
Processing;Vocal print feature MFCC, LPCC, △ MFCC, △ LPCC, energy, energy are extracted from pretreated synthetic video signal
First-order difference and GFCC collectively constitute the first multidimensional characteristic vectors, wherein:MFCC is mel-frequency cepstrum coefficient, and LPCC is
Linear prediction residue error, △ MFCC are the first-order difference of MFCC, and △ LPCC are the first-order difference of LPCC, and GFCC is
Gammatone filter cepstrum coefficients;Judge the first multidimensional characteristic vectors whether with it is described verification voice signal vocal print feature
Corresponding second multi-C vector matching, if it does, then determining that the synthetic video signal is matched with the verification voice signal.
In the embodiment of the present invention, when the session log in a certain dialog interface in instant communication client include it is important
When the target image of image level is selected, what detection was selected from session log comes from two different dialogue sides and issuing time
Earlier than first telephone voice signal of the issuing time of target image and second telephone voice signal, first is talked with
Voice signal and second telephone voice signal carry out after synthesis is verified voice signal, will verification voice signal and target
Image is associated, and default insignificant picture coverage goal image is utilized in session log;Wherein, voice signal is verified
As the foundation for presetting insignificant picture for removing coverage goal image.As it can be seen that implementing the embodiment of the present invention, Ke Yi
In the case of the non-screen locking of electronic equipment where instant communication client, prevent include in instant communication client session log
Important image is pried through by other people to the important image for including in reduction instant communication client session log is revealed
Risk.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that the term " comprising " and " having " of the embodiment of the present invention and their any deformation, it is intended that
Be to cover it is non-exclusive include, for example, containing the process of series of steps or unit, method, system, product or equipment not
Those of be necessarily limited to clearly to list step or unit, but may include not listing clearly or for these processes, side
The intrinsic other steps of method, product or equipment or unit.
The embodiment of the invention discloses a kind of image processing methods applied to instant communication client session log, can
In the case of the non-screen locking of the electronic equipment where instant communication client, prevent include in instant communication client session log
Important image by other people pry through to, reduce instant communication client session log in include important image reveal
Risk.Attached drawing is combined below to be described in detail.
Referring to Fig. 1, a kind of Fig. 1 images applied to instant communication client session log disclosed by the embodiments of the present invention
The flow diagram of processing method.In image processing method applied to instant communication client session log shown in Fig. 1,
Instant communication client loads on an electronic device.Wherein, instant communication client includes but not limited to wechat, QQ;Electronics is set
Standby including but not limited to cell phone, tablet computer.As shown in Figure 1, should be applied to the figure of instant communication client session log
As processing method may comprise steps of:
101, the electronic equipment detection is to the session log in a certain dialog interface in the instant communication client
Including target image first touch operation.
As an alternative embodiment, the electronic equipment executes after step 101 and the electronic equipment is held
Before row step 102, following steps can also be performed:
The electronic equipment acquires the color information of the facial image of the currently used person of the electronic equipment;
The electronic equipment carries out binary conversion treatment to the color information of the facial image of the currently used person;
The facial image of the currently used person after binary conversion treatment is divided into multiple block of pixels by the electronic equipment, and
The corresponding pixel value of all pixels in each block of pixels is carried out or operation, obtain each block of pixels or operation result composition institute
State the down-sampling picture of the facial image of currently used person;
Obtained down-sampling picture is divided into multiple pixel regions by the electronic equipment, by each pixel region
All pixels point or operation result summation, obtain the spy for each pixel region for forming the facial image of the currently used person
Reference ceases;
The electronic equipment judges according to the characteristic information of each pixel region of the facial image of the currently used person
Whether the facial image of the currently used person and the facial image of the pre-stored validated user of the electronic equipment match,
If matching executes step 102;If mismatching, terminate this flow.Wherein, this embodiment accurately can identify institute
The currently used person for stating electronic equipment just executes subsequent image procossing when being the pre-stored validated user of the electronic equipment,
It prevents disabled user from triggering the electronic equipment wantonly and image procossing is carried out to the target image that the session log includes, promoted
The safety for the target image that the session log includes.
As another optional embodiment, the electronic equipment is according to the every of the facial image of the currently used person
The characteristic information of a pixel region judges facial image and the pre-stored conjunction of the electronic equipment of the currently used person
After the facial image of method user matches and before electronic equipment execution step 102, following step can also be performed
Suddenly:
The electronic equipment touches the corresponding fingerprint image that touches of operation to described first and pre-processes, the pretreatment packet
It includes respectively to the image segmentation for touching fingerprint image, image enhancement, image binaryzation and micronization processes, obtains input refinement
Fingerprint image;
The electronic equipment takes the fingerprint minutiae point in the input refines fingerprint image, and refines and refer to the input
Print image extracts the sampled point in the input refinement fingerprint image on crestal line into line trace, and the extraction input is thin
Change the convex closure of the sampled point of fingerprint image, generates the convex closure containing fingerprint minutiae, all crestal lines up-sampling point and sampled point
Input fingerprint characteristic;
The electronic equipment identifies the finger of the input fingerprint characteristic and the pre-stored validated user of the electronic equipment
Whether line feature matches, if matched, just executes step 102;If mismatched, terminate this flow.Wherein, this implementation
Mode can be the pre-stored conjunction of the electronic equipment in the currently used person for more accurately identifying the electronic equipment
Subsequent image procossing is just executed when method user, prevents disabled user from triggering the electronic equipment wantonly to the session log packet
The target image contained carries out image procossing, promotes the safety for the target image that the session log includes.
102, the electronic equipment response described first touches operation, exports the corresponding image level dish of the target image
It is single;Described image rank menu includes important image level and insignificant image level.
If 103, the important image level that described image rank menu includes is selected, the electronic device prompts from
First telephone voice signal and second telephone voice signal are selected in the session log.
Wherein, when the important image level that described image rank menu includes is selected, illustrate the target image
For important image;If the insignificant image level that described image rank menu includes is selected, illustrate the target figure
As being insignificant image.
104, the electronic equipment detects the first telephone voice signal selected from the session log and second
Telephone voice signal;Wherein, issuing time of the first telephone voice signal in the session log is earlier than the mesh
Issuing time of the logo image in the session log, and second telephone voice signal is in the session log
The issuing time also issuing time earlier than the target image in the session log;Wherein, it is issued in the session log
One side of dialogue of first telephone voice signal is different from issuing second telephone voice letter in the session log
Number dialogue another party.
105, the electronic equipment to first telephone voice signal and second telephone voice signal into
Row synthesis is verified voice signal.
106, the verification voice signal is associated by the electronic equipment with the target image, and described right
In words record the target image is covered using default insignificant picture;Wherein, the verification voice signal is used as removing
The foundation for presetting insignificant picture of the target image is covered.
In the method described in Fig. 1, when the session log in a certain dialog interface in instant communication client includes
Important image level target image it is selected when, detect selected from session log come from two different dialogue sides and hair
The cloth time earlier than first telephone voice signal of the issuing time of target image and second telephone voice signal, to first
A telephone voice signal and second telephone voice signal carry out synthesis be verified voice signal after, voice signal will be verified
It is associated with target image, and utilizes default insignificant picture coverage goal image in session log;Wherein, verification sound
Sound signal is as the foundation for presetting insignificant picture for removing coverage goal image.As it can be seen that implementing side described in Fig. 1
Method can prevent instant communication client dialogue note in the case of the non-screen locking of the electronic equipment where instant communication client
The important image for including in record is pried through by other people to the important image for including in reduction instant communication client session log
The risk revealed.
Referring to Fig. 2, a kind of Fig. 2 images applied to instant communication client session log disclosed by the embodiments of the present invention
The flow diagram of processing method.In image processing method applied to instant communication client session log shown in Fig. 1,
Instant communication client loads on an electronic device.Wherein, instant communication client includes but not limited to wechat, QQ;Electronics is set
Standby including but not limited to cell phone, tablet computer.As shown in Fig. 2, should be applied to the figure of instant communication client session log
As processing method may comprise steps of:
201, the electronic equipment detection is to the session log in a certain dialog interface in the instant communication client
Including target image first touch operation.
202, the electronic equipment response described first touches operation, exports the corresponding image level dish of the target image
It is single;Described image rank menu includes important image level and insignificant image level.
If 203, the important image level that described image rank menu includes is selected, the electronic device prompts from
First telephone voice signal and second telephone voice signal are selected in the session log.
Wherein, when the important image level that described image rank menu includes is selected, illustrate the target image
For important image;If the insignificant image level that described image rank menu includes is selected, illustrate the target figure
As being insignificant image.
204, the electronic equipment detects the first telephone voice signal selected from the session log and second
Telephone voice signal;Wherein, issuing time of the first telephone voice signal in the session log is earlier than the mesh
Issuing time of the logo image in the session log, and second telephone voice signal is in the session log
The issuing time also issuing time earlier than the target image in the session log;Wherein, it is issued in the session log
One side of dialogue of first telephone voice signal is different from issuing second telephone voice letter in the session log
Number dialogue another party.
205, the electronic equipment to first telephone voice signal and second telephone voice signal into
Row synthesis is verified voice signal.
206, the verification voice signal is associated by the electronic equipment with the target image, and described right
In words record the target image is covered using default insignificant picture;Wherein, the verification voice signal is used as removing
The foundation for presetting insignificant picture of the target image is covered.
It is a kind of change schematic diagram of dialog interface disclosed by the embodiments of the present invention also referring to Fig. 3, Fig. 3.Such as Fig. 3 A
Shown, the electronic equipment can be detected includes to the session log in a certain dialog interface in the instant communication client
Target image first touch operation;Correspondingly, as shown in Figure 3B, the electronic equipment can respond described first and touch behaviour
Make, exports the corresponding image level menu of the target image;Described image rank menu includes important image level and non-heavy
Want image level;As shown in Fig. 3 B, (hook is made when the important image level that described image rank menu includes is selected
It is selected), the electronic equipment can prompt to select first telephone voice signal and second from the session log
Telephone voice signal;As shown in Figure 3 C, the electronic equipment can detect first dialogue selected from the session log
Voice signal and second telephone voice signal (playing hook expression);Wherein, first telephone voice signal is in the dialogue
Issuing time of the issuing time earlier than the target image in the session log in record, and second dialogue
Issuing time of the voice signal in the session log is also earlier than the target image when publication in the session log
Between;Wherein, one side of dialogue that first telephone voice signal is issued in the session log is different from the session log
Dialogue another party of middle publication second telephone voice signal;As shown in Figure 3D, the electronic equipment can be to described
One telephone voice signal and second telephone voice signal carry out synthesis and are verified voice signal, and are tested described
Card voice signal is associated with the target image, and covers institute using default insignificant picture in the session log
State target image;Wherein, the verification voice signal has covered the described default non-heavy of the target image as removing
Want the foundation of picture.
207, the electronic equipment detection is to having covered the described default non-heavy of the target image in the session log
The second of picture is wanted to touch operation.
208, the electronic equipment response described second touches operation, prompts to select third right from the session log
Talk about voice signal and the 4th telephone voice signal.
209, the electronic equipment detects the third telephone voice signal selected from the session log and the 4th
Telephone voice signal.
210, the electronic equipment judges issuing time of the third telephone voice signal in the session log
Whether earlier than issuing time of the target image in the session log and the 4th telephone voice signal in institute
State issuing time in the session log whether also issuing time earlier than the target image in the session log;If described
Issuing time of the third telephone voice signal in the session log is earlier than the target image in the session log
Issuing time and the 4th issuing time of the telephone voice signal in the session log also earlier than the target
Issuing time of the image in the session log executes step 211;If conversely, the third telephone voice signal is in institute
It states the issuing time in session log and is later than issuing time of the target image in the session log, and/or, it is described
4th issuing time of the telephone voice signal in the session log is also later than the target image in the session log
In issuing time, terminate this flow.
211, the electronic equipment judges to issue the dialogue one of the third telephone voice signal in the session log
Whether side is identical as described 4th dialogue another party of telephone voice signal is issued in the session log;If the dialogue note
One side of dialogue that the third telephone voice signal is issued in record is right different from issuing described 4th in the session log
Dialogue another party of voice signal is talked about, step 212- steps 213 are executed;If conversely, issuing the third in the session log
One side of dialogue of a telephone voice signal and the dialogue that the 4th telephone voice signal is issued in the session log are another
Fang Xiangtong, one side of dialogue that the third telephone voice signal is issued in the even described session log in the session log
The dialogue another party for issuing the 4th telephone voice signal is same dialogue side, terminates this flow.
212, the electronic equipment to the third telephone voice signal and the 4th telephone voice signal into
Row synthesis obtains synthetic video signal.
213, the electronic equipment judges whether the synthetic video signal matches with the verification voice signal, if
Match, the default insignificant picture for having covered the target image is removed, to show the target image.
As an alternative embodiment, in above-mentioned steps 212, the electronic equipment is to the third telephone voice
Signal and the 4th telephone voice signal are synthesized to obtain synthetic video signal, including:
The electronic equipment determines between the third telephone voice signal and the 4th telephone voice signal
Snap point;Wherein, the snap point refers to the third telephone voice signal and the 4th telephone voice signal synthesis
Starting position;In other words, if the third telephone voice signal will be synthesized with the 4th telephone voice signal,
It needs to find and be synthesized since which audio frame, this audio frame is it can be understood that be snap point;
The electronic equipment is according to the snap point by the third telephone voice signal and the 4th dialogue sound
Sound signal synthesizes synthetic video signal.
As an alternative embodiment, the electronic equipment determines the third telephone voice signal and described the
Snap point between four telephone voice signals, including:
The electronic equipment calculates the first duration of the third telephone voice signal and the 4th dialogue sound
Second duration of sound signal;Wherein, first duration indicates the time of the sound go of the third telephone voice signal;
Second duration indicates the time of the sound go of the 4th telephone voice signal;
The electronic equipment calculates the difference between first duration and second duration;
The electronic equipment judges whether the difference is less than or equal to default value, if so, talking with to the third
Any telephone voice signal in voice signal and the 4th telephone voice signal carries out the scaling on the period, to obtain most
The whole identical third telephone voice signal of duration and the 4th telephone voice signal, then with the final duration phase
The first audio frame of same third telephone voice signal and the 4th telephone voice signal is as snap point.
In the embodiment of the present invention, if the difference is less than or equal to default value, illustrate two telephone voice signals (i.e.
Second telephone voice signal described in first telephone voice signal) input when gap it is smaller, at this time can be to it
In a telephone voice signal (such as described first telephone voice signal) carry out the scaling on the period, such as it is longer to duration
Telephone voice signal carry out the compression (F.F. being namely commonly called as) on the period, and/or the shorter telephone voice of duration is believed
Number carry out the period on amplification (slow-motion being namely commonly called as) so that the final duration of two telephone voice signals is identical,
It is aligned again using the first audio frame of two telephone voice signals as snap point.
Wherein, the value range of the default value can be 0 to 0.1 second.
As an alternative embodiment, the electronic equipment is to the third telephone voice signal and the described 4th
Any telephone voice signal in a telephone voice signal carries out the scaling on the period, including:
If the first duration of the third telephone voice signal relative to the 4th telephone voice signal second
Duration is shorter, when the electronic equipment determines that the difference accounts for the first of the third telephone voice signal according to the difference
Long ratio X;
The electronic equipment calculates the audio frame number Y of the third telephone voice signal;
The electronic equipment calculates amplification coefficient Z, the Z=X* (Y/ (Y-1));
The electronic equipment according to the amplification coefficient, in the third telephone voice signal in addition to first audio frame
Except other audio frames carry out equal proportion amplification so that the final duration of amplified third telephone voice signal
It is identical as the 4th second duration of telephone voice signal.
For example, first telephone voice signal is 1 second, has 100 audio frames, then each audio frame 0.01
Second, second telephone voice signal is 1.1 seconds, and first telephone voice signal is needed to be amplified to 1.1 seconds.First
Frame is motionless, amplifies subsequent 99 frame, first determines that the coefficient Z of amplification is=0.101, i.e., 10.1% 0.1* (100/ (100-1));This
When subsequent 99 frame, need amplification 10.1% per frame, amplified per frame is 0.01* (1+10.1%)=0.01101, after amplification
The length of this 99 frame is 1.09 seconds, is just 1.1 seconds along with the first frame that do not move 0.01 second, i.e., first amplified
The final duration of telephone voice signal is identical as the second duration of second telephone voice signal.
In the embodiment of the present invention, if the difference is more than default value, illustrate that two telephone voice signals are (i.e. described
First telephone voice signal and second telephone voice signal) input when gap it is larger, if still right at this time
One of telephone voice signal carries out the scaling on the period, then can cause more serious distortion, subsequent school after scaling
It tests and will appear problem, it is possible to which snap point is determined using cross correlation algorithm.That is, when the difference is more than default value, it should
Method further includes:
The electronic equipment is using identical default sample frequency to the third telephone voice signal and described the
Four telephone voice signals are sampled respectively, obtain the first set of samples and the second set of samples;
The electronic equipment according to the default sample frequency (such as 8000Hz to 10000Hz), first set of samples,
Second set of samples and cross-correlation weights generate cross-correlation group;Wherein, the cross-correlation weights and the difference positive correlation
(such as the cross-correlation weights can be 1.5 times of the difference) includes multiple numerical value in the cross-correlation group;
Multiple numerical value in the cross-correlation group are compared by the electronic equipment, find out maximum numerical value;
The electronic equipment uses the corresponding audio frame position of the maximum numerical value as snap point.
Wherein, the electronic equipment according to the default sample frequency, first set of samples, second set of samples with
And cross-correlation weights generate cross-correlation group, including:
Wherein, Sn[t] indicates that cross-correlation group, x [m] indicate m-th of sampled data in first set of samples, y [m-t]
Indicate (m-t) a sampled data in second set of samples, t indicates the offset of time, and t is integer, value be from 0 to
M, WtIndicate that window function, wherein n=l*f, l are cross-correlation weights, f is the default sample frequency.
Wherein, the electronic equipment can be as snap point using the corresponding audio frame position of the maximum numerical value:
After the electronic equipment finds the maximum numerical value, can according to above-mentioned formula (1) instead release m be it is how many,
Then namely which sampled data determines which the audio frame where the sampled data is, and uses the audio again
Frame is as snap point.
In addition, the electronic equipment is after getting third telephone voice signal and the 4th telephone voice signal,
It is not the two telephone voice signals are verified one by one, but the two telephone voice signals is synthesized to obtain
Then synthetic video signal again matches synthetic video signal with the verification voice signal, and after voice signal synthesis,
It will produce and more can verify that parameter (such as whether two sections of sound are aligned, the phase difference etc. of two telephone voice signals), compare
In verifying two telephone voice signals one by one, the safety of verification is improved.
In the embodiment of the present invention, the electronic equipment judges whether are the synthetic video signal and the verification voice signal
Matching, including:
The electronic equipment pre-processes the synthetic video signal, and pretreatment includes preemphasis, framing and adding window
Processing;Vocal print feature MFCC, LPCC, △ MFCC, △ LPCC, energy, energy are extracted from pretreated synthetic video signal
First-order difference and GFCC collectively constitute the first multidimensional characteristic vectors, wherein:MFCC is mel-frequency cepstrum coefficient, and LPCC is
Linear prediction residue error, △ MFCC are the first-order difference of MFCC, and △ LPCC are the first-order difference of LPCC, and GFCC is
Gammatone filter cepstrum coefficients;Judge the first multidimensional characteristic vectors whether with it is described verification voice signal vocal print feature
Corresponding second multi-C vector matching, if it does, determining the sound-content of the synthetic video signal and the verification sound
Whether the sound-content of signal is identical, if identical, it is determined that the synthetic video signal is matched with the verification voice signal.
Wherein, implement the above embodiment, the accuracy of Sound Match can be improved.
In the method described in Fig. 2, when the session log in a certain dialog interface in instant communication client includes
Important image level target image it is selected when, detect selected from session log come from two different dialogue sides and hair
The cloth time earlier than first telephone voice signal of the issuing time of target image and second telephone voice signal, to first
A telephone voice signal and second telephone voice signal carry out synthesis be verified voice signal after, voice signal will be verified
It is associated with target image, and utilizes default insignificant picture coverage goal image in session log;Wherein, verification sound
Sound signal is as the foundation for presetting insignificant picture for removing coverage goal image.As it can be seen that implementing side described in Fig. 2
Method can prevent instant communication client dialogue note in the case of the non-screen locking of the electronic equipment where instant communication client
The important image for including in record is pried through by other people to the important image for including in reduction instant communication client session log
The risk revealed.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disk storages, magnetic disk storage, magnetic tape storage or can
Any other computer-readable medium for carrying or storing data.
Above to a kind of image processing method applied to instant communication client session log disclosed by the embodiments of the present invention
Method is described in detail, and principle and implementation of the present invention are described for specific case used herein, above
The explanation of embodiment is merely used to help understand the method and its core concept of the present invention;Meanwhile for the general skill of this field
Art personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this
Description should not be construed as limiting the invention.