Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a photographing-proof display which mainly comprises a built-in camera shooting acquisition module, a built-in identification judgment module and a control module, can monitor and automatically identify photographing equipment such as a mobile phone and photographing actions in real time, records the photographing actions, and has an active fortification function and an automatic disarming function. In addition, the display can be internally provided with an automatic alarm module to carry out stand-alone alarm and can also be sent to a monitoring center to realize a remote alarm function. The anti-photographing display can effectively prevent the problem of information leakage caused by photographing the display screen, and can protect screen information in real time, so that the safety of the information, the accuracy of threat early warning and the timeliness of protection are improved.
The technical scheme adopted by the invention for solving the technical problems is as follows: the utility model provides a prevent display of shooing, includes built-in collection module of making a video recording, built-in discernment decision module and built-in control module, wherein: the built-in camera shooting acquisition module adopts a camera to shoot and capture a front image of the display screen in real time and transmits the front image of the display screen to the built-in recognition judgment module; the built-in identification judgment module carries out identification judgment on the photographing equipment and the photographing action, records the photographing action and outputs a judgment result to the built-in control module; and the built-in control module controls the power supply circuit of the display screen according to the judgment result, so that the automatic arming and disarming functions are realized.
Compared with the prior art, the invention has the following positive effects:
the anti-shooting display can monitor and automatically identify shooting equipment such as a mobile phone and shooting actions in real time, record the shooting actions, and simultaneously has an active arming function and an automatic disarming function. In addition, the display can be internally provided with an automatic alarm module to carry out stand-alone alarm and can also be sent to a monitoring center to realize a remote alarm function. The invention effectively prevents the problem of information leakage caused by photographing the display screen, protects the screen information in real time, and improves the safety of the information, the accuracy of threat early warning and the timeliness of protection.
Detailed Description
An anti-shoot display, as shown in fig. 1, comprising: built-in collection module of making a video recording, built-in discernment judgement module, built-in control module, alarm module etc. wherein:
(1) the built-in camera shooting acquisition module acquires images by adopting a camera and provides the acquired images for the built-in recognition judgment module.
(2) The built-in recognition judgment module recognizes photographing equipment such as a mobile phone and the like by adopting a deep learning and image recognition method, recognizes photographing actions and records the photographing actions.
(3) The built-in control module is a built-in program control module of the display, and the module realizes the automatic arming and disarming functions by controlling the brightness or the power supply of the display screen according to the result judged by the identification and judgment module. The added anti-photographing circuit and the added module are completely independent from the display screen display information transmission and processing circuit, and only control the display screen power supply circuit.
(4) And an alarm module. The display can be internally provided with an automatic alarm module to carry out stand-alone alarm and can also be sent to a monitoring center to realize the remote alarm function. In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in detail below with reference to the accompanying drawings.
1 shooting collection module
The built-in camera shooting acquisition module acquires images by adopting a camera and provides the acquired images for the built-in recognition judgment module.
2 identification and judgment module
The built-in identification judgment module realizes the intelligent identification function of judging whether the information stealing situation by photographing exists or not by adopting a deep learning and image identification method.
The identification and judgment module mainly comprises two parts: one part is the training process and one part is the recognition process. The training process comprises the steps of inputting training pictures after sample label classification, repeatedly learning, deep network training and forming a classification model; the identification process comprises the steps of inputting test pictures which are shot and captured randomly by a camera, comparing the test pictures with a label sample library, judging whether the information stealing condition is caused by shooting exists or not, and outputting the result.
As shown in fig. 2, the decision process of the recognition decision module includes the following steps:
step one, classifying and preprocessing picture labels under the condition of photographing:
in the invention, the photographing device takes a mobile phone as an example, and the image label classification preprocessing mainly comprises two methods, one is direct classification under the condition of photographing or not, and the other is labeling classification.
The method I includes the steps that photos of mobile phones of different brands and shooting behaviors of the mobile phones from different shooting angles are classified into a 'mobile phone' category, and pictures of non-mobile phones are classified into a 'no mobile phone' category. In order to improve the recognition rate, the non-mobile phone selects a comparison sample with higher similarity to the mobile phone sample, such as sports goods, daily necessities, food, stationery and the like.
And in the second method, the non-mobile phone pictures are not needed, and only the pictures with the mobile phone need to be marked. In the process of marking, three marking modes are provided, namely, only marking a rear camera of the mobile phone, marking the whole mobile phone, combining the camera with the whole mobile phone, and combining the mobile phone with the hand under the condition that a person holds the mobile phone to take a picture.
Step two, establishing a photographing sample library:
the method comprises the steps of storing 'mobile phone' photos and 'no-mobile phone' photos containing mobile phones of different brands and shooting behaviors from different shooting angles by using the mobile phones under different folders respectively, and establishing a 'mobile phone' sample library and a 'no-mobile phone' sample library.
And secondly, after the pictures with the mobile phones are marked according to the four modes in the step one, storing the pictures with the mobile phones in a folder with the mobile phones, and establishing a sample library with the mobile phones.
Step three, training process:
the method I comprises the steps of inputting 'mobile phone' samples and 'no mobile phone' samples after label classification into a training process as training pictures, calling a training program to train the training pictures, and forming accurate 'mobile phone' and 'no mobile phone' template classification result models through repeated learning and deep network training.
And secondly, inputting the 'mobile phone' sample formed after marking as a training picture into a training process, calling a training program to train the training picture, and forming an accurate training result model through repeated learning and deep network training of the picture marking part.
Step four, identification process:
the method comprises the steps of taking a captured picture shot by a camera in real time as input, operating an identification program to identify the picture through a contour, judging by adopting a trained template classification result model, giving similarity for two conditions of 'mobile phone presence' and 'mobile phone absence', and outputting a similarity result. And if the similarity judgment result exceeds the set percentage threshold, recording and storing the called and judged picture.
And secondly, taking a captured picture shot by a camera in real time as input, operating an identification program to quickly identify a target of the picture through color, edge, texture and the like, judging by adopting a trained result model, quickly positioning and framing the identified one or more mobile phones in real time, giving a similarity result, and simultaneously recording and storing the current picture.
The photographing device in the process is only preferably a mobile phone, but is not limited in meaning, and the method is also applicable to other devices with photographing functions.
3 control module
And the control module is used for realizing the automatic arming and disarming functions by controlling the brightness of a display screen or a power supply according to the result judged by the built-in board card identification module, and the specific flow is shown in fig. 3.
If some shooting devices such as mobile phones and the like are close to the display or suspicious behaviors and actions of shooting appear, the display screen becomes dark or is powered off. If the camera does not have the photographing condition, the control module controls the change of the display screen according to whether a person appears in front of the camera or not, the screen is bright when the person is in front of the camera, and the screen is dark or powered off when the person is not in front of the camera. The added anti-photographing circuit and the added module are completely independent from the display screen display information transmission and processing circuit, and only control the display screen power supply circuit.
4 alarm module
When illegal equipment (mobile phone) or photographing behavior in a scene is identified, the alarm module can sound an alarm to play an alarm role. The display can be internally provided with an automatic alarm module for stand-alone alarm and can also be sent to a monitoring center for realizing a remote alarm function, as shown in figure 1.
The above is only one embodiment of the present invention, and it should be noted that the present invention is applicable to different platforms (CPU/GPU) and different operating systems (Windows/Linux/android), and it is obvious for those skilled in the art that several modifications can be made without departing from the principle of the present invention, and these modifications should be regarded as the protection measures of the present invention.