Summary of the invention
The embodiment of the present disclosure provides a kind of data guard method, apparatus and system, is able to solve user using computer
There are problems that the security risk of leaking data in the process.The technical solution is as follows:
According to the first aspect of the embodiments of the present disclosure, a kind of data guard method is provided, this method comprises:
The scene image in predeterminable area is obtained, predeterminable area includes opposite with the target display screen of data to be protected is shown
Region;
Image recognition is carried out to scene image and obtains image recognition result;
Image recognition result instruction scene image include subject image element when, control target display screen stop display to
Protect data.
By carrying out image recognition to scene image, it can be determined that go out whether the predeterminable area opposite with target display screen has
The behavior taken on the sly then controls target display screen and stops showing data to be protected, avoid data to be protected if there is the behavior taken on the sly
Leakage, improves the Information Security of computer.
In one embodiment, image recognition is carried out to scene image and obtains image recognition result, comprising:
Obtain images match model;
Image recognition is carried out to scene image using images match model and generates image recognition result, image recognition result
It whether is used to indicate in scene image comprising subject image element.
Obtain images match model, using images match model judge in scene image whether include subject image element more
It is accurate to add, and reduces erroneous judgement.
In one embodiment, images match model is obtained, comprising:
Initial matching model and sample image are obtained, sample image includes first kind sample image and the second class sample graph
Picture, wherein first kind sample image includes subject image element, and the second class sample image does not include subject image element;
Sample image is handled using initial matching model to obtain the decision content of sample image;
It is obtained after being adjusted according to parameter of the difference of the decision content of sample image and reference value to initial matching model
Images match model.
Parameter adjustment, obtained images match are carried out to initial matching model according to the decision content of sample image and reference value
Model is more accurate for the processing of image, can more accurately determine whether the behavior of taking on the sly occur in scene image.
In one embodiment, image recognition is carried out to scene image and obtains image recognition result, comprising:
Image recognition is carried out to scene image and obtains at least one pictorial element;
At least one pictorial element is matched with subject image element, if successful match, it is determined that at least one
It include subject image element in pictorial element, if it fails to match, it is determined that do not include target figure at least one pictorial element
Pixel element;
Image recognition result is generated according to matching result.
At least one pictorial element and subject image element match whether determining scene image marks on a map comprising improving eyesight
Pixel element, and then determine that the predeterminable area opposite with target display screen whether there is the behavior taken on the sly, according to subject image element
Determined, ensure that the accuracy of judgement, and being capable of flexibly adjustment Rule of judgment.
In one embodiment, this method further include:
To using the target user of target display screen to carry out recognition of face, target user is determined according to the result of recognition of face
For legitimate user.
In one embodiment, control target display screen stops showing data to be protected, comprising:
The display source of target display screen is cut off, and controls target display screen display warning image.
The display source for cutting off target display screen, ensure that data to be protected are not revealed, while show screen display in target
Image is warned, reminds user to reinforce the protection to data, further improves Information Security.
According to the second aspect of an embodiment of the present disclosure, a kind of data protecting device is provided, comprising: image collection module, figure
As identification module and display control module;
Image collection module, for obtaining the scene image in predeterminable area, predeterminable area includes and shows number to be protected
According to the opposite region of target display screen;
Picture recognition module obtains image recognition result for carrying out image recognition to scene image;
Display control module, for controlling mesh when image recognition result instruction scene image includes subject image element
Display screen is marked to stop showing data to be protected.
In one embodiment, picture recognition module includes: the first matched sub-block and the first identification submodule;
First matched sub-block, for obtaining images match model;
First identification submodule is known for carrying out image recognition to scene image using images match model and generating image
Not as a result, whether image recognition result is used to indicate in scene image comprising subject image element.
In one embodiment, the first matched sub-block includes: initial cell, computing unit and model unit;
Initial cell, for obtaining initial matching model and sample image, sample image include first kind sample image and
Second class sample image, wherein first kind sample image includes subject image element, and the second class sample image does not include target figure
Pixel element;
Computing unit obtains the decision content of sample image for being handled using initial matching model sample image;
Model unit, for according to the difference of the decision content of sample image and reference value to the parameter of initial matching model into
Images match model is obtained after row adjustment.
In one embodiment, picture recognition module includes: the second matched sub-block and the second identification submodule;
Second identification submodule obtains at least one pictorial element for carrying out image recognition to scene image;
Second matched sub-block, for matching at least one pictorial element with subject image element, if matching
Success, it is determined that include subject image element at least one pictorial element, if it fails to match, it is determined that at least one image
Subject image element is not included in element;Image recognition result is generated according to matching result.
In one embodiment, data protecting device further includes face recognition module;
Face recognition module, for target user's progress recognition of face to target display screen is used, according to recognition of face
Result determine target user be legitimate user.
According to the third aspect of an embodiment of the present disclosure, a kind of data protection system is provided, which includes: number
According to protective device, host and display screen, data are transmitted by data transmission link between host and display screen;
Wherein, data protecting device is that data described in any one embodiment of second aspect or second aspect are protected
Protection unit, data protecting device are mounted on host or display screen;
Alternatively, data protecting device is a part of host or display screen.
In one embodiment, data protecting device obtains the scene image in predeterminable area, and predeterminable area includes and shows
Show the opposite region of the target display screen of data to be protected;Image recognition is carried out to scene image and obtains image recognition result;?
When image recognition result indicates that scene image includes subject image element, caution signal is transmitted to display screen, caution signal is used for
Instruction stops showing data to be protected;
Display screen stops showing data to be protected according to caution signal, and cuts off the data transmission link between host.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
The embodiment of the present disclosure provides a kind of data transmission method, as shown in Figure 1, the data transmission method includes following step
It is rapid:
101, the scene image in predeterminable area is obtained.
Predeterminable area includes the region opposite with the target display screen of data to be protected is shown, predeterminable area is can to shoot
To the region of target display screen.
Optionally, Image Acquisition can be carried out to predeterminable area by image collecting device and generates scene image.Image
Acquisition device can be a part of data protecting device, be also possible to through external interface and data protecting device connection communication
External image acquisition device;Image collecting device is also possible to a part of target display screen, or passes through external interface
With the external image acquisition device of target display screen connection communication.Data protecting device can be a part of target display screen,
The external device (ED) either being connect with target display screen.
For example, data protecting device is a device inside target display screen, image is installed on target display screen and is adopted
Acquisition means can carry out Image Acquisition to the predeterminable area opposite with target display screen.
Specifically, above-mentioned image collecting device can be camera, the frequency of Image Acquisition can be 30 times/second.Wait protect
Shield data can be preset classified papers etc., show that the opposite region of the target display screen of data to be protected belongs to target and shows
The direction of panel pair, for example, as shown in Fig. 2, image collecting device is set to target display screen upper edge, certainly, image is adopted
Acquisition means can have multiple, also can be set in different ground France, towards with target display screen just facing towards identical, acquisition
The region of image can be used as predeterminable area.
In an alternative embodiment, camera starts after being configurable to booting, i.e., sets belonging to target display screen
After standby (such as: computer etc.) booting, camera starting obtains the image in predeterminable area.
In an alternative embodiment, ecret protection application program is can be set in computer, when user starts the privacy
When protecting application program, image collecting device starting.This mode can reduce power consumption.
102, image recognition is carried out to scene image and obtains image recognition result.
Two specific examples can be enumerated and be illustrated herein there are many mode by carrying out image recognition to scene image:
In first example, image recognition is carried out to scene image and obtains image recognition result, comprising:
Obtain images match model;Image recognition is carried out to scene image using images match model and generates image recognition
As a result, whether image recognition result is used to indicate in scene image comprising subject image element.
Obtain images match model, using images match model judge in scene image whether include subject image element more
It is accurate to add, and reduces erroneous judgement.
It should be noted that images match model can be pre-set, can also be obtained by training study, for example,
Obtain images match model, comprising:
Initial matching model and sample image are obtained, sample image includes first kind sample image and the second class sample graph
Picture, wherein first kind sample image includes subject image element, and the second class sample image does not include subject image element;It utilizes
Initial matching model handles sample image to obtain the decision content of sample image;According to the decision content of sample image and reference
The difference of value obtains images match model after being adjusted to the parameter of initial matching model.
It should be noted that reference value can be it is preset.Herein, column take a particular example further explanation figure
As the acquisition process of Matching Model.For example, first kind sample image and the second class sample image are marked respectively, can incite somebody to action
First kind sample image is labeled as (1,0), and the second class sample image is labeled as (0,1), then using initial matching model to sample
This image A (sample image A is any one sample image, is only illustrated by taking sample image A as an example herein) is handled,
Two steps can be divided into using treatment process of the initial matching model to sample image A;The first step utilizes first network model
Feature extraction is carried out to sample image A, obtains the characteristic value of sample image A, the characteristic value of sample image A is for indicating sample graph
As the characteristics of image of A;Second step carries out the characteristic value of sample image A using the second network model sample image A is calculated
Decision content.If sample image A is first kind sample image, reference value is (1,0), if the judgement of sample image A
Value is (0.5,0), and the change of parameter in first network model and the second network model is calculated using the difference of decision content and reference value
Then change value is adjusted the first network model and the second network model, and is trained next time.Into excessively a large amount of instruction
Practice, so that it may obtain images match model.
If being more than using difference of the images match model to the scene image decision content handled and reference value
Preset range, then illustrate that scene image differs larger with the characteristics of image of sample image, using images match model to scene
The difference of decision content and reference value that image is handled within a preset range, then illustrates scene image and sample image
Characteristics of image is close, it is likely that includes subject image element.According to the decision content of sample image and reference value to initial matching mould
Type carries out parameter adjustment, and obtained images match model is more accurate for the processing of image, can more accurately determine scene
Whether there is the behavior of taking on the sly in image.
In second example, it can establish database, include a large amount of subject image elements in database, then by scene
Image is matched with the subject image element in database, and then whether determine in scene image includes subject image element,
For example, carrying out image recognition to scene image obtains image recognition result, comprising:
Image recognition is carried out to scene image and obtains at least one pictorial element;By at least one pictorial element and target figure
Pixel element is matched, if successful match, it is determined that includes subject image element at least one pictorial element, if matching
Failure, it is determined that do not include subject image element at least one pictorial element;Image recognition result is generated according to matching result.
It should be noted that each pictorial element includes at least one pixel, a target at least one pictorial element
Pictorial element also includes at least one pixel, at least one pictorial element with subject image element match can pass through by
Pixel in two pictorial element same positions is compared to determine.It is with the pictorial element A at least one pictorial element
Example, if the pixel value of two pixels on pictorial element A and subject image element same position is less than or equal to preset difference value,
Two pixels are then determined as same pixel pair, if the quantity of pictorial element A and subject image element same pixel pair is being schemed
The all pixels for including as elements A and subject image element are greater than or equal to preset ratio to ratio shared in quantity, then really
Determine pictorial element A and subject image element matching.Certainly, only exemplary illustration herein, does not represent the disclosure and is confined to this.
The matching of pictorial element A and subject image element is the matching of Pixel-level, and therefore, matching result is more acurrate, moreover, to database
In subject image element can be updated, allow subject image element to cover various behaviors of taking on the sly, data protection
Safety is higher.
103, when image recognition result instruction scene image includes subject image element, control target display screen stops aobvious
Show data to be protected.
Subject image element embodies the key message of shooting behavior, for example, posture of taking pictures, photographic device etc..Target image
Element may include the image of some specific people, also may include image (such as the figure of camera of image collecting device
Picture), if image recognition result instruction scene image includes subject image element, someone can be determined to target display screen
It takes on the sly.
In one embodiment, this method further include: target user's progress recognition of face to target display screen is used, root
Determine that target user is legitimate user according to the result of recognition of face.
It should be noted that target user carry out recognition of face can be target user using target display screen it
Before, for example, recognition of face is carried out to target user, if according to recognition of face when target user opens target display screen
As a result determine that target user is legitimate user, then opens target display screen, otherwise, be not turned on target display screen;Alternatively, to mesh
Mark user carry out recognition of face can be detected take behavior on the sly when, carry out recognition of face, for example, in image recognition knot
When fruit indicates that scene image includes subject image element, recognition of face is carried out to the target user before target display screen, if root
It determines that target user is illegal user according to the result of recognition of face, then controls target display screen and stop showing data to be protected and report
It is alert, if determining that target user is legitimate user according to the result of recognition of face, retains the result of recognition of face and ask target
User chooses whether to misidentify, and certainly, this is a kind of example, does not represent the disclosure and is confined to this.
In one embodiment, control target display screen stops showing data to be protected, comprising:
The display source of target display screen is cut off, and controls target display screen display warning image.
It should be noted that warning image can be and be stored in advance in target display screen, can also be filled by data protection
It sets and is transmitted to target display screen.The display source for cutting off target display screen, ensure that data to be protected are not revealed, while aobvious in target
Show that screen display warns image, reminds user to reinforce the protection to data, further improve Information Security.
Further, by taking target display screen does not include data protecting device as an example, scene figure is determined in data protecting device
When as comprising subject image element, data protecting device sends caution signal, mesh to target display screen by data transmission interface
It marks display screen and display source is cut off according to caution signal, and show warning image;When scene image does not include subject image element,
Data protecting device can not send signal to target display screen, can also be sent by data transmission interface to target display screen
Safety signal.The data transmission interface can be high-definition multimedia interface (English: High Definition
Multimedia Interface, HDMI) or digital visual interface (English: Digital Visual Interface,
DVI), it is also possible to universal serial bus (English: Universal Serial Bus, USB) interface, the disclosure does not limit this
System.
The data guard method that the embodiment of the present disclosure provides, by carrying out image recognition to scene image, it can be determined that go out
Whether the predeterminable area opposite with target display screen has the behavior taken on the sly, if there is the behavior taken on the sly, then controls target display screen
Stop showing data to be protected, avoids leaking data to be protected, improve the Information Security of computer.
Based on data guard method described in the corresponding embodiment of above-mentioned Fig. 1, following is embodiment of the present disclosure,
It can be used for executing embodiments of the present disclosure.
The embodiment of the present disclosure provides a kind of data protecting device, as shown in figure 3, the data protecting device 30 includes: image
Obtain module 301, picture recognition module 302 and display control module 303;
Image collection module 301, for obtaining the scene image in predeterminable area, predeterminable area includes to be protected with display
The opposite region of the target display screen of data;
Picture recognition module 302 obtains image recognition result for carrying out image recognition to scene image;
Display control module 303, for controlling when image recognition result instruction scene image includes subject image element
Target display screen stops showing data to be protected.
In one embodiment, as shown in figure 4, picture recognition module 302 includes: the first matched sub-block 3021 and first
Identify submodule 3022;
First matched sub-block 3021, for obtaining images match model;
First identification submodule 3022, for carrying out image recognition to scene image using images match model and generating figure
As recognition result, whether image recognition result is used to indicate in scene image comprising subject image element.
In one embodiment, as shown in figure 5, the first matched sub-block 3021 includes: initial cell 30211, calculates list
Member 30212 and model unit 30213;
Initial cell 30211, for obtaining initial matching model and sample image, sample image includes first kind sample graph
Picture and the second class sample image, wherein first kind sample image includes subject image element, and the second class sample image does not include mesh
Logo image element;
Computing unit 30212 is sentenced for being handled to obtain sample image to sample image using initial matching model
Definite value;
Model unit 30213, for according to the decision content of sample image and the difference of reference value to initial matching model
Parameter obtains images match model after being adjusted.
In one embodiment, as shown in fig. 6, picture recognition module 302 includes: the second matched sub-block 3023 and second
Identify submodule 3024;
Second identification submodule 3024 obtains at least one pictorial element for carrying out image recognition to scene image;
Second matched sub-block 3023, at least one pictorial element to be matched with subject image element, if
Successful match, it is determined that include subject image element at least one pictorial element, if it fails to match, it is determined that at least one
Subject image element is not included in pictorial element;Image recognition result is generated according to matching result.
In one embodiment, as shown in fig. 7, data protecting device 30 further includes face recognition module 304;
Face recognition module 304, for being known according to face to using the target user of target display screen to carry out recognition of face
Other result determines that target user is legitimate user.
The data protecting device that the embodiment of the present disclosure provides, by carrying out image recognition to scene image, it can be determined that go out
Whether the predeterminable area opposite with target display screen has the behavior taken on the sly, if there is the behavior taken on the sly, then controls target display screen
Stop showing data to be protected, avoids leaking data to be protected, improve the Information Security of computer.
Based on the corresponding embodiment of above-mentioned Fig. 1-Fig. 7, the embodiment of the present disclosure provides a kind of data protection system, referring to Fig. 8
Shown, which includes: data protecting device 801, host 802 and display screen 803, host 802 and display screen
Data are transmitted by data transmission link between 803;
Wherein, data protecting device 801 is number described in any one embodiment of second aspect or second aspect
According to protective device 30, data protecting device 80 is mounted on host 802 or display screen 803;
Alternatively, data protecting device 80 is a part of host 802 or display screen 803, as shown in Figure 9.
It should be noted that the data transmission link between host 802 and display screen 803 can be wire link, it can also
To be Radio Link.Display screen 803 can be target display screen described in the corresponding embodiment of Fig. 1-Fig. 7.
In one embodiment, data protecting device 801 obtain predeterminable area in scene image, predeterminable area include with
Show the opposite region of the target display screen of data to be protected;Image recognition is carried out to scene image and obtains image recognition result;
When image recognition result instruction scene image includes subject image element, caution signal, caution signal are transmitted to display screen 803
It is used to indicate stopping and shows data to be protected;
Display screen 803 is instructed according to cutting, stops showing data to be protected, and is cut off the data between host 802 and passed
Transmission link.
In another embodiment, data protecting device 801 obtains the scene image in predeterminable area, and predeterminable area includes
The region opposite with the target display screen of data to be protected is shown;Image recognition is carried out to scene image and obtains image recognition knot
Fruit;When image recognition result instruction scene image includes subject image element, cutting instruction is transmitted to host 802, cutting refers to
Enable the data transmission link being used to indicate between cutting host 802 and display screen 803;
Host 802 is instructed according to cutting, sends caution signal to display screen, caution signal is used to indicate stopping and shows wait protect
Data are protected, and cut off the data transmission link between display screen 803;
Display screen stops showing data to be protected according to caution signal.
The data protection system that the embodiment of the present disclosure provides, by carrying out image recognition to scene image, it can be determined that go out
Whether the predeterminable area opposite with target display screen has the behavior taken on the sly, if there is the behavior taken on the sly, then controls target display screen
Stop showing data to be protected, avoids leaking data to be protected, improve the Information Security of computer.
Based on data guard method described in the corresponding embodiment of above-mentioned Fig. 1, the embodiment of the present disclosure also provides one kind
Computer readable storage medium, for example, non-transitorycomputer readable storage medium can be read-only memory (English: Read
Only Memory, ROM), it is random access memory (English: Random Access Memory, RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..It is stored with computer instruction on the storage medium, for executing the corresponding embodiment of above-mentioned Fig. 1
Described in data guard method, details are not described herein again.
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.