CN108833257B - Picture covering method applied to group - Google Patents

Picture covering method applied to group Download PDF

Info

Publication number
CN108833257B
CN108833257B CN201810550426.2A CN201810550426A CN108833257B CN 108833257 B CN108833257 B CN 108833257B CN 201810550426 A CN201810550426 A CN 201810550426A CN 108833257 B CN108833257 B CN 108833257B
Authority
CN
China
Prior art keywords
sound signal
social client
group
picture
target picture
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810550426.2A
Other languages
Chinese (zh)
Other versions
CN108833257A (en
Inventor
向敏明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XI'AN YULE CULTURAL TECHNOLOGY Co.,Ltd.
Original Assignee
Xi'an Yule Cultural Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xi'an Yule Cultural Technology Co ltd filed Critical Xi'an Yule Cultural Technology Co ltd
Priority to CN201810550426.2A priority Critical patent/CN108833257B/en
Publication of CN108833257A publication Critical patent/CN108833257A/en
Application granted granted Critical
Publication of CN108833257B publication Critical patent/CN108833257B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
    • H04L51/10—Multimedia information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the invention relates to the technical field of social contact, and discloses a picture covering method applied to a group, which comprises the following steps: the method comprises the steps that a social client detects a covering instruction input by any target picture issued on a group conversation interface aiming at a group; the social client prompts any two users who issue sound signals on a group conversation interface to be selected from the group according to the covering instruction so as to form a first user pair; the social client associates the first user pair with the target picture, and covers the target picture by using a preset non-privacy picture on a group session interface; the first user pair is used as a first basis for removing the non-private picture covered by the target picture. By implementing the embodiment of the invention, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of the private photos being leaked is reduced.

Description

Picture covering method applied to group
Technical Field
The invention relates to the technical field of social contact, in particular to a picture covering method applied to a group.
Technical Field
At present, groups are generally created on various social clients including WeChat and QQ, and users in the groups sometimes post some privacy pictures on a group session interface. In practice, it is found that when a privacy photo is published on a group session interface of a group of social clients, if a user device (such as a mobile phone) where the social clients are located is not locked, the privacy photo published on the group session interface is easily stolen by other people, so that the privacy photo is revealed.
Disclosure of Invention
The embodiment of the invention discloses a picture covering method applied to a group, which can effectively prevent private pictures published on a group session interface of the group from being stolen and seen by others and reduce the risk of the private pictures being revealed.
The picture covering method applied to a group, wherein the group is created in a social client, comprises the following steps:
the social client detects an overlay instruction input by aiming at any target picture published on a group conversation interface of the group;
the social client prompts any two users who issue sound signals on the group conversation interface to be selected from the group according to the covering instruction so as to form a first user pair;
the social client associates the first user pair with the target picture, and covers the target picture with a preset non-private picture on the group session interface; wherein the first user pair is used as a first basis for removing the non-privacy picture which covers the target picture.
As an optional implementation manner, in an embodiment of the present invention, after the social client overwrites the target picture with a preset non-private picture on the group session interface, the method further includes:
the social client detecting a removal instruction for the non-private picture on the group session interface that has overlaid the target picture;
the social client prompts any two users to be selected from the group according to the removing instruction so as to form a second user pair;
the social client judges whether the second user pair is the same as the first user pair serving as a first basis for removing the non-private picture covering the target picture;
if the group conversation interface is the same as the target picture, the social client removes the non-privacy picture which is covered by the target picture on the group conversation interface so as to redisplay the target picture.
As an optional implementation manner, in an embodiment of the present invention, after the social client associates the first user pair with the target picture and before the target picture is covered by a preset non-privacy picture on the group session interface, the method further includes:
the social client prompts to select a first sound signal issued by the first user to one user included in the group session interface and prompts to select a second sound signal issued by the first user to another user included in the group session interface;
the social client synthesizes the selected first sound signal and the second sound signal to obtain a verification sound signal;
the social client associates the verification sound signal with the target picture and executes the step of covering the target picture with a preset non-privacy picture on the group session interface; wherein the verification sound signal is used as a second basis for removing the non-privacy picture which covers the target picture;
after the social client determines that the second user pair is the same as the first user pair serving as a first basis for removing the non-private picture covering the target picture, and before the social client removes the non-private picture covering the target picture on the group session interface to redisplay the target picture, the method further includes:
the social client prompts to select a third sound signal issued by one user included in the second user pair from the group session interface and prompts to select a fourth sound signal issued by another user included in the second user pair from the group session interface;
the social client synthesizes the selected third sound signal and the selected fourth sound signal to obtain a synthesized sound signal;
and the social client judges whether the synthesized sound signal is matched with the verification sound signal which is used as a second basis for removing the non-privacy picture covering the target picture, and if so, executes the step of removing the non-privacy picture covering the target picture on the group conversation interface so as to redisplay the target picture.
As an optional implementation manner, in an embodiment of the present invention, the synthesizing, by the social client, the selected first sound signal and the second sound signal to obtain a verification sound signal includes:
the social client side determines an alignment point between the selected first sound signal and the second sound signal; wherein the alignment point refers to a starting position of the synthesis of the first sound signal and the second sound signal;
and the social client synthesizes the first sound signal and the second sound signal into a verification sound signal according to the alignment point.
As an optional implementation manner, in an embodiment of the present invention, the determining, by the social client, an alignment point between the first selected sound signal and the second selected sound signal includes:
the social client side calculates a first time length of the selected first sound signal and a second time length of the second sound signal; wherein the first duration represents a duration of sound of the first sound signal; the second time duration represents a time duration of sound of the second sound signal;
the social client calculates a difference between the first duration and the second duration;
and the social client judges whether the difference value is smaller than or equal to a preset value, if so, any one of the first sound signal and the second sound signal is subjected to periodic scaling so as to obtain the first sound signal and the second sound signal with the same final duration, and then the first audio frame of the first sound signal and the first audio frame of the second sound signal with the same final duration are used as an alignment point.
As an optional implementation manner, in an embodiment of the present invention, the social client scaling, periodically, any one of the first sound signal and the second sound signal, includes:
if the first time length of the first sound signal is shorter than the second time length of the second sound signal, the social client determines a ratio X of the difference value to the first time length of the first sound signal according to the difference value;
the social client side calculates the audio frame number Y of the first sound signal;
the social client computing a magnification factor Z, which is X (Y/(Y-1));
and the social client amplifies other audio frames except the first audio frame in the first sound signal in an equal proportion according to the amplification coefficient, so that the final duration of the amplified first sound signal is the same as the second duration of the second sound signal.
As an optional implementation manner, in an embodiment of the present invention, if the difference is greater than the preset value, the method further includes:
the social client side respectively samples the first sound signal and the second sound signal by using the same default sampling frequency to obtain a first sampling group and a second sampling group;
the social client side generates a cross-correlation group according to the default sampling frequency, the first sampling group, the second sampling group and the cross-correlation weight; wherein the cross-correlation weight is positively correlated with the difference, and the cross-correlation group comprises a plurality of values;
the social client compares the plurality of values in the cross-correlation group to find out the maximum value;
and the social client uses the audio frame position corresponding to the maximum numerical value as an alignment point.
As an optional implementation manner, in an embodiment of the present invention, the generating, by the social client, a cross-correlation group according to the default sampling frequency, the first sampling group, the second sampling group, and a cross-correlation weight includes:
Figure BDA0001681090820000041
wherein S isn[t]Representing a set of cross-correlations, x [ m ]]Representing the mth sample data in the first sample group, y [ m-t ]]Represents the (m-t) th sampling data in the second sampling group, t represents the offset of time, t is an integer and takes the value from 0 to m, WtAnd representing a window function, wherein n is l f, l is a cross-correlation weight, and f is the default sampling frequency.
As an optional implementation manner, in an embodiment of the present invention, the determining, by the social client, whether the synthesized sound signal matches the verification sound signal as a second basis for removing the non-privacy picture that has covered the target picture includes:
the social client determining whether the alignment point between the synthesized sound signal and the verification sound signal as a second basis for removing the non-private picture that has covered the target picture is the same;
if the two multi-dimensional vectors are the same, the social client judges whether the first multi-dimensional vector corresponding to the voiceprint feature of the synthesized voice signal is matched with the second multi-dimensional vector corresponding to the voiceprint feature of the verification voice signal, and if the two multi-dimensional vectors are matched, the synthesized voice signal is matched with the verification voice signal; if not, determining that the synthesized voice signal does not match the verification voice signal;
the first multi-dimensional vector corresponding to the voiceprint feature of the synthetic sound signal is composed of a mel-frequency cepstrum coefficient, a linear prediction cepstrum coefficient, a first order difference of the mel-frequency cepstrum coefficient, a first order difference of the linear prediction cepstrum coefficient, energy, a first order difference of the energy and a Gammatone filter cepstrum coefficient.
In the embodiment of the invention, the social client can detect a covering instruction input by any target picture issued on a group conversation interface aiming at a group, and prompt any two users who issue sound signals on the group conversation interface to be selected from the group so as to form a first user pair; the social client can associate the first user pair with the target picture, and cover the target picture with a preset non-privacy picture on the group session interface, wherein the first user pair serves as a first basis for removing the non-privacy picture covered with the target picture. Therefore, by the embodiment of the invention, even under the condition that the user equipment (such as a mobile phone) where the social client is located is not locked, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of the private photos being leaked is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a picture covering method applied to a group according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another method for covering a group of pictures according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of another method for overlaying pictures applied to a group according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a variation of a group session interface of a social client according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, of embodiments of the present invention are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a picture covering method applied to a group, which can effectively prevent private pictures published on a group conversation interface of the group from being stolen and seen by others even under the condition that user equipment (such as a mobile phone) where a social client is located is not locked, and reduce the risk of the private pictures being leaked. The following detailed description is made with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a picture covering method applied to a group according to an embodiment of the present invention. In the picture overlay method applied to a group shown in fig. 1, the group is created in a social client, which may include, but is not limited to, WeChat, QQ; the social client can be installed on a mobile phone, a tablet computer and other user equipment. As shown in fig. 1, the method for overlaying pictures applied to a group may include the following steps:
101. the social client detects an overlay instruction input by any target picture published on a group session interface of the group.
As an alternative embodiment, after the social client performs step 101 and before the social client performs step 102, the following steps may be further performed:
the method comprises the steps that a social client side collects color information of a face image of a current user of the social client side;
the social client carries out binarization processing on the color information of the face image of the current user;
the social client divides the face image of the current user after binarization processing into a plurality of pixel blocks, and performs OR operation on pixel values corresponding to all pixels in each pixel block to obtain an OR operation result of each pixel block to form a down-sampling picture of the face image of the current user;
the social client divides the obtained down-sampling picture into a plurality of pixel regions, and obtains the characteristic information of each pixel region forming the face image of the current user by summing the OR operation results of all pixel points in each pixel region;
the social contact client side judges whether the face image of the current user is matched with the face image of a legal user stored in the social contact client side in advance according to the feature information of each pixel region of the face image of the current user, and if the face image of the current user is matched with the face image of the legal user, the step 102 is executed; if not, the process is ended. According to the embodiment, the subsequent image covering can be executed when the current user of the social client is accurately identified to be a legal user stored in the social client in advance, the illegal user is prevented from triggering the social client to cover any target image published on the group session interface of the group, and therefore the legality and reliability of the image covering can be improved.
As another optional implementation, after the social client determines, according to the feature information of each pixel region of the face image of the current user, that the face image of the current user matches with the face image of the legal user stored in the social client in advance, and before the social client performs step 102, the following steps may be further performed:
the social client preprocesses a touch fingerprint image corresponding to the covering instruction, wherein the preprocessing comprises image segmentation, image enhancement, image binarization and thinning processing of the touch fingerprint image respectively to obtain an input thinned fingerprint image;
the social client extracts fingerprint minutiae from the input refined fingerprint image, tracks the input refined fingerprint image, extracts sampling points on ridge lines in the input refined fingerprint image, extracts convex hulls of the sampling points of the input refined fingerprint image, and generates input fingerprint characteristics containing the fingerprint minutiae, all the sampling points on the ridge lines and the convex hulls of the sampling points;
the social contact client identifies whether the input fingerprint features are matched with fingerprint features of legal users stored in advance by the social contact client, and if the input fingerprint features are matched with the fingerprint features of the legal users, the step 102 is executed; if not, the flow is ended. According to the embodiment, the subsequent image covering can be executed when the current user of the social client is identified to be a legal user pre-stored in the social client more accurately, the illegal user is prevented from triggering the social client to cover any target image published on the group session interface of the group, and therefore the legality and reliability of the image covering can be improved.
102. And the social client prompts to select any two users who issue sound signals on the group conversation interface from the group according to the covering instruction so as to form a first user pair.
In the embodiment of the invention, the social client can select each user who issues the sound signal on the group session interface from the group according to the covering instruction, and pop up a first user pair selection interface, wherein the first user pair selection interface comprises the identifier of each user who issues the sound signal on the group session interface and selected from the group; accordingly, the social client may detect the identifiers of any two users selected by the current user of the social client from the first user pair selection interface, so as to select any two users from the group, to which the sound signal is issued on the group session interface, to form the first user pair.
The users who issue the sound signals on the group conversation interface refer to the users who issue the sound signals and can be seen on the group conversation interface at present.
103. The social client associates the first user pair with the target picture, and covers the target picture by using a preset non-privacy picture on a group session interface; the first user pair is used as a first basis for removing the non-private picture covered by the target picture.
The social client associates the first user pair with the target picture means that the social client associates the corresponding relationship between the identifiers of the two users in the first user pair with the target picture.
In the method described in fig. 1, even when the user equipment (e.g., a mobile phone) where the social client is located is not locked, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of revealing the private photos is reduced. In addition, in the method described in fig. 1, an illegal user can be prevented from triggering the social client to overlay any target picture published on the group session interface of the group, so that the legality and reliability of the overlay of the picture can be improved.
Referring to fig. 2, fig. 2 is a schematic flow chart illustrating another method for covering a group of pictures according to an embodiment of the present invention. As shown in fig. 2, the method for overlaying pictures applied to a group may include the following steps:
201. the social client detects an overlay instruction input by any target picture published on a group session interface of the group.
As an alternative embodiment, after the social client performs step 201 and before the social client performs step 202, the following steps may be further performed:
the method comprises the steps that a social client side collects color information of a face image of a current user of the social client side;
the social client carries out binarization processing on the color information of the face image of the current user;
the social client divides the face image of the current user after binarization processing into a plurality of pixel blocks, and performs OR operation on pixel values corresponding to all pixels in each pixel block to obtain an OR operation result of each pixel block to form a down-sampling picture of the face image of the current user;
the social client divides the obtained down-sampling picture into a plurality of pixel regions, and obtains the characteristic information of each pixel region forming the face image of the current user by summing the OR operation results of all pixel points in each pixel region;
the social contact client side judges whether the face image of the current user is matched with the face image of a legal user stored in the social contact client side in advance according to the characteristic information of each pixel region of the face image of the current user, and if the face image of the current user is matched with the face image of the legal user, the step 202 is executed; if not, the process is ended. According to the embodiment, the subsequent image covering can be executed when the current user of the social client is accurately identified to be a legal user stored in the social client in advance, the illegal user is prevented from triggering the social client to cover any target image published on the group session interface of the group, and therefore the legality and reliability of the image covering can be improved.
As another optional implementation, after the social client determines, according to the feature information of each pixel region of the face image of the current user, that the face image of the current user matches with the face image of the legal user stored in the social client in advance, and before the social client performs step 202, the following steps may be further performed:
the social client preprocesses a touch fingerprint image corresponding to the covering instruction, wherein the preprocessing comprises image segmentation, image enhancement, image binarization and thinning processing of the touch fingerprint image respectively to obtain an input thinned fingerprint image;
the social client extracts fingerprint minutiae from the input refined fingerprint image, tracks the input refined fingerprint image, extracts sampling points on ridge lines in the input refined fingerprint image, extracts convex hulls of the sampling points of the input refined fingerprint image, and generates input fingerprint characteristics containing the fingerprint minutiae, all the sampling points on the ridge lines and the convex hulls of the sampling points;
the social contact client identifies whether the input fingerprint features are matched with fingerprint features of legal users stored in advance by the social contact client, and if the input fingerprint features are matched with the fingerprint features of the legal users, the step 202 is executed; if not, the flow is ended. According to the embodiment, the subsequent image covering can be executed when the current user of the social client is identified to be a legal user pre-stored in the social client more accurately, the illegal user is prevented from triggering the social client to cover any target image published on the group session interface of the group, and therefore the legality and reliability of the image covering can be improved.
202. And the social client prompts to select any two users who issue sound signals on the group conversation interface from the group according to the covering instruction so as to form a first user pair.
In the embodiment of the invention, the social client can select each user who issues the sound signal on the group session interface from the group according to the covering instruction, and pop up a first user pair selection interface, wherein the first user pair selection interface comprises the identifier of each user who issues the sound signal on the group session interface and selected from the group; accordingly, the social client may detect the identifiers of any two users selected by the current user of the social client from the first user pair selection interface, so as to select any two users from the group, to which the sound signal is issued on the group session interface, to form the first user pair.
The users who issue the sound signals on the group conversation interface refer to the users who issue the sound signals and can be seen on the group conversation interface at present.
203. The social client associates the first user pair with the target picture, and covers the target picture by using a preset non-privacy picture on a group session interface; the first user pair is used as a first basis for removing the non-private picture covered by the target picture.
204. The social client detects a removal instruction for a non-private picture that has been overlaid with a target picture on a group session interface.
205. And the social client prompts to select any two users from the group according to the removing instruction so as to form a second user pair.
In the embodiment of the present invention, the social client may pop up a second user pair selection interface according to the removal instruction, where the second user pair selection interface includes identifiers of all users in the group; accordingly, the social client may detect the identifiers of any two users selected by the current user of the social client from the second user pair selection interface, so as to select any two users from the group to form a second user pair.
206. The social client side judges whether the selected second user pair is the same as a first user pair serving as a first basis for removing the non-private picture covering the target picture or not; if yes, go to step 207; if not, the process is ended.
207. And the social client removes the non-privacy pictures covering the target pictures on the group session interface so as to redisplay the target pictures.
In the method described in fig. 2, only when a second user pair formed by any two users selected from the group by the social client is the same as a first user pair associated with the target picture and having a sound signal posted on the group conversation interface, the non-private picture of the target picture already covered on the group conversation interface is removed to redisplay the target picture; on the contrary, if the second user formed by any two users selected from the group by the social client is different from the first user associated with the target picture and issued with the sound signal on the group conversation interface, the non-private picture covered with the target picture on the group conversation interface is not removed, and the target picture is still covered. Therefore, by implementing the method described in fig. 2, even when the user equipment (such as a mobile phone) where the social client is located is not locked, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of revealing the private photos is reduced. In addition, in the method described in fig. 2, an illegal user can be prevented from triggering the social client to overlay any target picture published on the group session interface of the group, so that the legality and reliability of the overlay of the picture can be improved.
Referring to fig. 3, fig. 3 is a schematic flow chart illustrating another method for covering a group of pictures according to an embodiment of the present invention. As shown in fig. 3, the method for overlaying pictures applied to a group may include the following steps:
301. the social client detects an overlay instruction input by any target picture published on a group session interface of the group.
302. And the social client prompts to select any two users who issue sound signals on the group conversation interface from the group according to the covering instruction so as to form a first user pair.
303. The social client associates the first user pair with the target picture, prompts to select a first sound signal issued by one user included in the first user pair from the group conversation interface, and prompts to select a second sound signal issued by another user included in the first user pair from the group conversation interface.
The first sound signal issued by the first user to the included user may be a sound signal issued by the first user to the included user on the group conversation interface or an ambient sound signal, and the first sound signal issued by the first user to the included user may be a sound signal issued by the first user to the included user on the group conversation interface or an ambient sound signal, which is not limited in the embodiment of the present invention.
304. And the social client synthesizes the selected first sound signal and the second sound signal to obtain a verification sound signal.
As an alternative embodiment, in the implementation of the present invention, before the social client performs step 304, the social client may first determine whether the first sound signal and the second sound signal are both voice signals, and then perform step 304 if the first sound signal and the second sound signal are both voice signals.
For example, the social client may accurately determine whether the first sound signal is a voice signal by:
the social client performs fast Fourier transform on the first sound signal to obtain a frequency domain signal;
the social client side calculates a spectrum amplitude value according to the frequency domain signal;
the social client side calculates probability density according to the spectrum amplitude value;
the social client side calculates the spectral entropy of the first sound signal according to the probability density;
the social client determines whether the first sound signal is a voice signal according to the spectral entropy;
wherein, the social client determines whether the first sound signal is a speech signal according to the spectral entropy, which may include:
the social client calculates the energy of the first sound signal;
the social client determines whether the first sound signal is a voice signal or not according to the energy and the spectral entropy of the first sound signal, namely the social client can calculate a product of the energy of the first sound signal and the spectral entropy of the first sound signal and perform a square-open operation on the product to obtain a square-open value corresponding to the product; and the social client side can judge whether the square value corresponding to the product is larger than a preset threshold value, if so, the first sound signal is determined to be the voice signal, and if not, the first sound signal is determined not to be the voice signal.
305. The social client associates the verification sound signal with the target picture, and covers the target picture with a preset non-privacy picture on a group session interface; the first user pair is used as a first basis for removing the non-private picture covered by the target picture; verifying a sound signal as a second basis for removing the non-private picture that has covered the target picture.
306. The social client detects a removal instruction for a non-private picture that has been overlaid with a target picture on a group session interface.
307. And the social client prompts to select any two users from the group according to the removing instruction so as to form a second user pair.
308. The social client side judges whether the second user pair is the same as the first user pair serving as a first basis for removing the non-private picture covering the target picture or not; if yes, go to step 309-step 311; if not, the process is ended.
309. And the social client prompts to select a third sound signal issued by the second user to the contained one user from the group session interface and prompts to select a fourth sound signal issued by the second user to the contained other user from the group session interface.
310. And the social client synthesizes the selected third sound signal and the selected fourth sound signal to obtain a synthesized sound signal.
311. The social client determines whether the synthesized sound signal matches the verification sound signal as a second basis for removing the non-private picture that covers the target picture, and if yes, performs step 312; if not, the process is ended.
312. And the social client removes the non-privacy pictures covering the target pictures on the group session interface so as to redisplay the target pictures.
As an alternative implementation, in step 304, the synthesizing, by the social client, the selected first sound signal and the second sound signal to obtain the verification sound signal includes:
the social client side determines an alignment point between the selected first sound signal and the second sound signal; wherein, the alignment point refers to a starting position of the synthesis of the first sound signal and the second sound signal; in other words, if the first sound signal and the second sound signal are to be synthesized, it is necessary to find out from which audio frame the synthesis starts, and this audio frame can be understood as the alignment point;
and the social client synthesizes the first sound signal and the second sound signal into a verification sound signal according to the alignment point.
As an alternative embodiment, the social client determines an alignment point between the selected first sound signal and the second sound signal, including:
the social client calculates a first time length of the selected first sound signal and a second time length of the second sound signal; wherein the first duration represents a time of sound duration of the first sound signal; the second time duration represents a time duration of sound of the second sound signal;
the social client calculates a difference value between the first time length and the second time length;
and the social client judges whether the difference value is smaller than or equal to a preset value, if so, any one of the first sound signal and the second sound signal is subjected to periodic scaling to obtain the first sound signal and the second sound signal with the same final duration, and then the first audio frame of the first sound signal and the first audio frame of the second sound signal with the same final duration are used as an alignment point.
In the embodiment of the present invention, if the difference is smaller than or equal to the predetermined value, it indicates that the difference between the two sound signals (i.e. the first sound signal and the second sound signal) is small, and at this time, one of the sound signals (e.g. the first sound signal) may be scaled periodically, for example, periodically compressing the sound signal with a longer duration (i.e. commonly referred to as fast forwarding), and/or periodically amplifying the sound signal with a shorter duration (i.e. commonly referred to as slow forwarding), so that the final durations of the two sound signals are the same, and then the first audio frames of the two sound signals are aligned as an alignment point.
Wherein, the value range of the preset value can be 0 to 0.1 second.
As an optional implementation, the social client performs periodic scaling on any one of the first sound signal and the second sound signal, including:
if the first time length of the first sound signal is shorter than the second time length of the second sound signal, the social client determines the proportion X of the difference value in the first time length of the first sound signal according to the difference value;
the social client calculates the audio frame number Y of the first sound signal;
the social client calculates a magnification factor Z, wherein Z is X (Y/(Y-1));
and the social client side amplifies the audio frames except the first audio frame in the first sound signal in an equal proportion according to the amplification coefficient, so that the final duration of the amplified first sound signal is the same as the second duration of the second sound signal.
For example, if the first sound signal is 1 second and there are 100 audio frames, each audio frame is 0.01 second, and the second sound signal is 1.1 second, it is necessary to amplify the first sound signal to 1.1 second. The first frame is not moved, the subsequent 99 frames are amplified, and the amplification factor Z is firstly determined to be 0.1 (100/(100-1)) -0.101, namely 10.1%; at this time, in the subsequent 99 frames, each frame needs to be amplified by 10.1%, each amplified frame is 0.01 × 0.01101 (1+ 10.1%), the length of the 99 frames after amplification is 1.09 seconds, and the final duration of the first amplified sound signal is 1.1 seconds after the first frame without motion is added by 0.01 seconds, that is, the final duration of the first amplified sound signal is the same as the second duration of the second sound signal.
In the embodiment of the present invention, if the difference is greater than the preset value, it indicates that the difference between the two sound signals (i.e., the first sound signal and the second sound signal) is large when inputting, and if one of the sound signals is periodically scaled at this time, then relatively serious distortion may be caused after scaling, and a problem may occur in subsequent verification, so that a cross-correlation algorithm may be used to determine the alignment point. That is, when the difference is greater than the preset value, the method further includes:
the social client side uses the same default sampling frequency to respectively sample the first sound signal and the second sound signal to obtain a first sampling group and a second sampling group;
the social client generates a cross-correlation group according to a default sampling frequency (for example, 8000Hz to 10000Hz), the first sampling group, the second sampling group and the cross-correlation weight; wherein, the cross-correlation weight is positively correlated with the difference (for example, the cross-correlation weight may be 1.5 times of the difference), and the cross-correlation group includes a plurality of values;
the social client compares a plurality of values in the cross-correlation group to find out the maximum value;
the social client uses the audio frame position corresponding to the maximum value as the alignment point.
The social client generates a cross-correlation group according to the default sampling frequency, the first sampling group, the second sampling group and the cross-correlation weight, and includes:
Figure BDA0001681090820000161
wherein S isn[t]Representing a set of cross-correlations, x [ m ]]Representing the mth sample data in the first sample group, y [ m-t ]]Represents the (m-t) th sampling data in the second sampling group, t represents the offset of time, t is an integer and takes the value from 0 to m, WtAnd expressing a window function, wherein n is l and f, l is a cross-correlation weight, and f is a default sampling frequency.
The social client may use the audio frame position corresponding to the maximum numerical value as the alignment point:
after the social client finds the maximum value, it can reversely deduce what m is, i.e. which sample data, according to the above formula (1), and then determine which audio frame the sample data is in, and use the audio frame as the alignment point.
In the embodiment of the invention, after the social client acquires the first sound signal and the second sound signal, the two sound signals are not verified one by one, but are synthesized to obtain the verified sound signal, then the synthesized sound signal is matched with the verified sound signal when the non-private picture needs to be removed, and after the sound signals are synthesized, more verifiable parameters (such as whether the alignment points are the same or not, whether voiceprint characteristics are matched or not) are generated, so that compared with the method for verifying the two sound signals one by one, the security of verification is improved.
As an alternative implementation, in step 311, the determining, by the social client, whether the synthesized sound signal matches the verification sound signal as a second basis for removing the non-privacy picture covered by the target picture includes:
the social client side judges whether an alignment point between the synthesized sound signal and a verification sound signal serving as a second basis for removing the non-privacy picture covering the target picture is the same; the alignment points are the same, and the content of a mixed frame of two mixed audio frames corresponding to the alignment points (one mixed audio frame belongs to the synthesized sound signal, and the other mixed audio frame belongs to the verification sound signal) is the same, and the frame time of the two mixed audio frames corresponding to the alignment points is also the same;
if the first multi-dimensional vector is the same as the second multi-dimensional vector, the social client judges whether the first multi-dimensional vector corresponding to the voiceprint feature of the synthesized voice signal is matched with the second multi-dimensional vector corresponding to the voiceprint feature of the verified voice signal, and if the first multi-dimensional vector is matched with the second multi-dimensional vector, the synthesized voice signal is matched with the verified voice signal; if not, determining that the synthesized voice signal is not matched with the verification voice signal;
the first multi-dimensional vector corresponding to the voiceprint features of the synthesized sound signal is composed of a Mel frequency cepstrum coefficient, a linear prediction cepstrum coefficient, a first order difference of the Mel frequency cepstrum coefficient, a first order difference of the linear prediction cepstrum coefficient, energy, a first order difference of the energy and a Gammatone filter cepstrum coefficient. In addition, the above embodiment can improve the accuracy of sound matching.
In the method described in fig. 3, even when the user equipment (e.g., a mobile phone) where the social client is located is not locked, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of revealing the private photos is reduced. In addition, in the method described in fig. 3, an illegal user can be prevented from triggering the social client to overlay any target picture published on the group session interface of the group, so that the legality and reliability of the overlay of the picture can be improved.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating a variation of a group session interface of a social client according to an embodiment of the present invention. In the group conversation interface shown in fig. 4, different avatars respectively represent different users in a group, and the same avatar represents the same user in the group. As shown in a in fig. 4, the social client may detect an overlay instruction of any target picture published on the group session interface for the group input by the current user of the social client through a touch operation; as shown in B in fig. 4, the social client may prompt to select any two users who have issued sound signals on the group conversation interface from the group according to the overlay instruction, so as to form a first user pair; the current user of the social client can hook any two users who issue sound signals on a group session interface, the two hooked users represent the two selected users, and the two users can form a first user pair; as shown in C in fig. 4, after associating the first user pair with the target picture, the social client may overlay the target picture with a preset non-privacy picture on the group session interface; the first user pair is used as a first basis for removing the non-private picture covered by the target picture. Therefore, even under the condition that the screen of the user equipment (such as a mobile phone) where the social client is located is not locked, the private photos published on the group session interface of the group can be effectively prevented from being stolen and seen by others, and the risk of revealing the private photos is reduced.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by hardware instructions of a program, and the program may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory, such as a magnetic disk, or a combination thereof, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
The above detailed description is made on the image covering method applied to the group, which is disclosed in the embodiment of the present invention, and the principle and the implementation manner of the present invention are explained in the present document by applying a specific example, and the description of the above embodiment is only used to help understanding the method of the present invention and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (9)

1. A picture overlay method applied to a group created in a social client, the method comprising:
the social client detects an overlay instruction input by aiming at any target picture published on a group conversation interface of the group;
the social client prompts any two users who issue sound signals on the group conversation interface to be selected from the group according to the covering instruction so as to form a first user pair;
the social client associates the first user pair with the target picture, and covers the target picture with a preset non-private picture on the group session interface; wherein the first user pair is used as a first basis for removing the non-privacy picture which covers the target picture.
2. The method for overlaying pictures applied to a group according to claim 1, wherein after the social client overlays the target picture with a preset non-private picture on the group session interface, the method further comprises:
the social client detecting a removal instruction for the non-private picture on the group session interface that has overlaid the target picture;
the social client prompts any two users to be selected from the group according to the removing instruction so as to form a second user pair;
the social client side judges whether the selected second user pair is the same as the first user pair serving as a first basis for removing the non-private picture covering the target picture or not;
if the group conversation interface is the same as the target picture, the social client removes the non-privacy picture which is covered by the target picture on the group conversation interface so as to redisplay the target picture.
3. The method for overlaying pictures applied to a group according to claim 2, wherein after said social client associates said first user pair with said target picture and before overlaying said target picture with a preset non-private picture on said group session interface, said method further comprises:
the social client prompts to select a first sound signal issued by the first user to one user included in the group session interface and prompts to select a second sound signal issued by the first user to another user included in the group session interface;
the social client synthesizes the selected first sound signal and the second sound signal to obtain a verification sound signal;
the social client associates the verification sound signal with the target picture and executes the step of covering the target picture with a preset non-privacy picture on the group session interface; wherein the verification sound signal is used as a second basis for removing the non-privacy picture which covers the target picture;
after the social client determines that the second user pair is the same as the first user pair serving as a first basis for removing the non-private picture covering the target picture, and before the social client removes the non-private picture covering the target picture on the group session interface to redisplay the target picture, the method further includes:
the social client prompts to select a third sound signal issued by one user included in the second user pair from the group session interface and prompts to select a fourth sound signal issued by another user included in the second user pair from the group session interface;
the social client synthesizes the selected third sound signal and the selected fourth sound signal to obtain a synthesized sound signal;
and the social client judges whether the synthesized sound signal is matched with the verification sound signal which is used as a second basis for removing the non-privacy picture covering the target picture, and if so, executes the step of removing the non-privacy picture covering the target picture on the group conversation interface so as to redisplay the target picture.
4. The method as claimed in claim 3, wherein the step of synthesizing the selected first sound signal and the second sound signal by the social client to obtain a verification sound signal comprises:
the social client side determines an alignment point between the selected first sound signal and the second sound signal; wherein the alignment point refers to a starting position of the synthesis of the first sound signal and the second sound signal;
and the social client synthesizes the first sound signal and the second sound signal into a verification sound signal according to the alignment point.
5. The method of claim 4, wherein the social client determines an alignment point between the first sound signal and the second sound signal, and comprises:
the social client side calculates a first time length of the selected first sound signal and a second time length of the second sound signal; wherein the first duration represents a duration of sound of the first sound signal; the second time duration represents a time duration of sound of the second sound signal;
the social client calculates a difference between the first duration and the second duration;
and the social client judges whether the difference value is smaller than or equal to a preset value, if so, any one of the first sound signal and the second sound signal is subjected to periodic scaling so as to obtain the first sound signal and the second sound signal with the same final duration, and then the first audio frame of the first sound signal and the first audio frame of the second sound signal with the same final duration are used as an alignment point.
6. The picture overlay method applied to the group according to claim 5, wherein the social client periodically scales any one of the first sound signal and the second sound signal, comprising:
if the first time length of the first sound signal is shorter than the second time length of the second sound signal, the social client determines a ratio X of the difference value to the first time length of the first sound signal according to the difference value;
the social client side calculates the audio frame number Y of the first sound signal;
the social client computing a magnification factor Z, which is X (Y/(Y-1));
and the social client amplifies other audio frames except the first audio frame in the first sound signal in an equal proportion according to the amplification coefficient, so that the final duration of the amplified first sound signal is the same as the second duration of the second sound signal.
7. The method as claimed in claim 5 or 6, wherein if the difference is greater than the predetermined value, the method further comprises:
the social client side respectively samples the first sound signal and the second sound signal by using the same default sampling frequency to obtain a first sampling group and a second sampling group;
the social client side generates a cross-correlation group according to the default sampling frequency, the first sampling group, the second sampling group and the cross-correlation weight; wherein the cross-correlation weight is positively correlated with the difference, and the cross-correlation group comprises a plurality of values;
the social client compares the plurality of values in the cross-correlation group to find out the maximum value;
and the social client uses the audio frame position corresponding to the maximum numerical value as an alignment point.
8. The method of claim 7, wherein the social client generates the cross-correlation set according to the default sampling frequency, the first sampling set, the second sampling set, and the cross-correlation weight, and comprises:
Figure FDA0002572265150000041
wherein S isn[t]Representing a set of cross-correlations, x [ m ]]Representing the mth sample data in the first sample group, y [ m-t ]]Represents the (m-t) th sampling data in the second sampling group, t represents the offset of time, t is an integer and takes the value from 0 to m, WtAnd representing a window function, wherein n is l f, l is a cross-correlation weight, and f is the default sampling frequency.
9. The method as claimed in any one of claims 4 to 6, wherein the determining, by the social client, whether the synthesized sound signal matches the verification sound signal as a second basis for removing the non-private picture that has been overlaid with the target picture comprises:
the social client determining whether the alignment point between the synthesized sound signal and the verification sound signal as a second basis for removing the non-private picture that has covered the target picture is the same;
if the two multi-dimensional vectors are the same, the social client judges whether the first multi-dimensional vector corresponding to the voiceprint feature of the synthesized voice signal is matched with the second multi-dimensional vector corresponding to the voiceprint feature of the verification voice signal, and if the two multi-dimensional vectors are matched, the synthesized voice signal is matched with the verification voice signal; if not, determining that the synthesized voice signal does not match the verification voice signal;
the first multi-dimensional vector corresponding to the voiceprint feature of the synthetic sound signal is composed of a mel-frequency cepstrum coefficient, a linear prediction cepstrum coefficient, a first order difference of the mel-frequency cepstrum coefficient, a first order difference of the linear prediction cepstrum coefficient, energy, a first order difference of the energy and a Gammatone filter cepstrum coefficient.
CN201810550426.2A 2018-05-31 2018-05-31 Picture covering method applied to group Active CN108833257B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810550426.2A CN108833257B (en) 2018-05-31 2018-05-31 Picture covering method applied to group

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810550426.2A CN108833257B (en) 2018-05-31 2018-05-31 Picture covering method applied to group

Publications (2)

Publication Number Publication Date
CN108833257A CN108833257A (en) 2018-11-16
CN108833257B true CN108833257B (en) 2021-01-19

Family

ID=64146986

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810550426.2A Active CN108833257B (en) 2018-05-31 2018-05-31 Picture covering method applied to group

Country Status (1)

Country Link
CN (1) CN108833257B (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8943141B2 (en) * 2012-06-18 2015-01-27 Lutebox Ltd. Social networking system and methods of implementation
CN105451198B (en) * 2014-09-30 2019-04-09 阿里巴巴集团控股有限公司 Share the method and apparatus of picture in instant messaging
CN104951682A (en) * 2015-06-05 2015-09-30 小米科技有限责任公司 Privacy protection method and device
CN105760778B (en) * 2016-02-17 2019-05-17 北京金山安全软件有限公司 Method and device for improving security of private picture and electronic equipment
CN107666395A (en) * 2016-07-28 2018-02-06 中兴通讯股份有限公司 One population file management method, user terminal, group chat system

Also Published As

Publication number Publication date
CN108833257A (en) 2018-11-16

Similar Documents

Publication Publication Date Title
CN109450850B (en) Identity authentication method, identity authentication device, computer equipment and storage medium
US20210192033A1 (en) Detection of replay attack
RU2738325C2 (en) Method and device for authenticating an individual
US10783455B2 (en) Bot-based data collection for detecting phone solicitations
US6959099B2 (en) Method and apparatus for automatic face blurring
CN106778179B (en) Identity authentication method based on ultrasonic lip language identification
EP3321846A1 (en) Systems and methods for secure biometric sample raw data storage
CN107871236B (en) Electronic equipment voiceprint payment method and device
CN111160928A (en) Identity verification method and device
CN106980836B (en) Identity verification method and device
CN111611437A (en) Method and device for preventing face voiceprint verification and replacement attack
CN108574781B (en) Image processing method applied to instant messaging client dialogue record
CN108833257B (en) Picture covering method applied to group
CN109165533B (en) Anti-peeping method of short video based on cross-group mechanism
CN108959887B (en) Group control method applied to instant communication client
CN113191787A (en) Telecommunication data processing method, device electronic equipment and storage medium
EP3767872A1 (en) Method for generating a private key from biometric characteristics
CN109002728B (en) Group display control method based on one-key triggering
CN105227311B (en) Verification method and system, audio detection method and processing method
CN109033897A (en) It is a kind of based on the image processing method across group mechanisms
CN108704310B (en) Virtual scene synchronous switching method for double VR equipment participating in virtual game
CN108718425B (en) Picture sharing method applied to channels
CN108712273B (en) Picture publishing method based on anchor client triggering
CN109039864A (en) A kind of processing method of the word content based on social client
CN112818798B (en) Identity verification method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20201223

Address after: Room 12207, 22 / F, unit 1, building 5, No. 57, Keji 3rd road, Zhangba Street office, hi tech Zone, Xi'an City, Shaanxi Province

Applicant after: XI'AN YULE CULTURAL TECHNOLOGY Co.,Ltd.

Address before: Room 403, No.35, Sanxiang, xiashou new village, Xicheng District, Dongguan City, Guangdong Province 523073

Applicant before: DONGGUAN HUARUI ELECTRONIC TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An image overlay method applied to groups

Effective date of registration: 20220819

Granted publication date: 20210119

Pledgee: Xi'an innovation financing Company limited by guarantee

Pledgor: XI'AN YULE CULTURAL TECHNOLOGY Co.,Ltd.

Registration number: Y2022610000513

PE01 Entry into force of the registration of the contract for pledge of patent right