WO2020073739A1 - Système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie - Google Patents

Système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie Download PDF

Info

Publication number
WO2020073739A1
WO2020073739A1 PCT/CN2019/101701 CN2019101701W WO2020073739A1 WO 2020073739 A1 WO2020073739 A1 WO 2020073739A1 CN 2019101701 W CN2019101701 W CN 2019101701W WO 2020073739 A1 WO2020073739 A1 WO 2020073739A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
photographing
layer
light
computer vision
Prior art date
Application number
PCT/CN2019/101701
Other languages
English (en)
Chinese (zh)
Inventor
林桦
Original Assignee
林桦
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 林桦 filed Critical 林桦
Publication of WO2020073739A1 publication Critical patent/WO2020073739A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/82—Protecting input, output or interconnection devices
    • G06F21/84—Protecting input, output or interconnection devices output devices, e.g. displays or monitors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes

Definitions

  • the invention relates to the technical field of information security methods and devices based on computer vision, in particular to an anti-photographing display system and anti-photographing method based on computer vision.
  • CN106407827A a screen anti-sneaking device based on frequency difference
  • CN108174137A a method and device for preventing video candid by superimposing video watermark
  • the purpose of the present invention is to solve the shortcomings of the prior art, and to provide a computer vision-based anti-photographing display system and anti-photographing method, which recognizes the physical characteristics of the common components of all shooting equipment-cameras and flash, while supplementing different Recognize some typical visual characteristics of shooting equipment to achieve the effect of preventing photographing based on computer vision.
  • an anti-photographing display system based on computer vision
  • a display including a display; an image collector for collecting image information around the display; a memory for storing preset feature information of the candid camera; a processor It is used to identify the image information collected by the image collector and compare it with the preset feature information in the memory to determine whether there is a sneak shot device.
  • the preset feature information in the memory includes any one of the following feature information or any combination of feature information: a. It includes a middle layer that does not reflect light, and the inner side of the middle layer is the innermost layer, The innermost layer can reflect light; b. The innermost layer can reflect white light or blue-violet light or red light; c. On the side of the middle layer also includes white color features or yellow The color features may include both yellow and orange color features, and the color features exhibit concentric circular texture features; d. Trademark features of the image acquisition device; e. Shape features of the image acquisition device; f. The innermost layer is circular, and the middle layer is a circle or rectangle concentric with the center of the circle's innermost layer; g.
  • the outer side of the middle layer further includes an outer layer, and the outer layer is rectangular; h
  • the size of the outline of the outer layer satisfies the set range value; i.
  • the outline size of the outer layer and the outline size of the innermost layer meet the set proportional value.
  • the method further includes irradiating the periphery of the display device with an infrared light source or a laser.
  • the preset feature information in the memory further includes an image feature of a red light spot.
  • the method specifically includes the following steps: Step a. Perform RGB color space data reading on the image information; Step b. Filter the read data; Step c. Convert the RGB color space to HSV space ; Step d. Perform H, S, V channel separation and thresholding on the converted HSV image; Step e. Perform contour recognition and comparison on the image information.
  • FIG. 1 is a schematic structural diagram of an anti-photographing display system based on computer vision of the present invention in an embodiment.
  • FIG. 2 is a schematic flowchart of an anti-photographing method based on computer vision of the present invention in an embodiment.
  • the composition of the computer vision-based anti-photographing display system includes a display screen; a camera for capturing images is provided around the display screen, and the specific camera in this embodiment is provided in the middle of the display screen Upper side; infrared light sources are installed on both sides of the camera, so that the image collector can collect image information with light reflected by the light source, and can also be used to supplement the lack of natural light when necessary; there is a specially registered infrared dedicated around the display Logo, used to enable the image collector to collect the equipment used to realize reflection or refraction; and the hardware structure of the computer vision processing and the software onboard to identify the pictures and effects collected by the camera, and to match the preset features The information is compared to determine whether there is a candid camera.
  • this embodiment first uses computer vision principles to identify the color, shape, and size comparison of the core components of these camera devices, namely the camera lens and flash unit, so that the camera lens can be quickly discovered. It is supplemented by other visual features for further identification.
  • the core device is the lens to achieve a photo, and they have the following common characteristics.
  • the camera lens is composed of an optical lens group and a fixed frame. These two parts have the following physical characteristics.
  • the part of the optical lens group is the key to imaging. Early cameras generally did not have a coating, and the uncoated lens reflected various colors of light, so the reflected light appeared to be white light.
  • the lenses are all composed of lenses, the circular structure with a symmetrical center point can achieve uniform penetration of light in all directions to achieve the best imaging effect, so the lenses are all circular.
  • this black fixed frame will use a concentric circle that is concentric with the lens lens.
  • the black fixed frame is approximately a regular rectangular shape.
  • the body of the shooting equipment other than the camera part may have different colors and shapes, so the shooting equipment can be described as the following three-layer structure by color and shape.
  • a camera will have at least two physical layers of lens-fixture.
  • pixel indexes such as chroma, saturation, and brightness, so as to recognize colors and shapes, and then quickly identify the camera lens.
  • the dual-color temperature LED flash is the latest mobile phone LED flash at this stage. It is also composed of two LED flashes, but the light source of one of them is orange. We know that the sun's rays are not white, but are composed of seven monochromatic lights of red, orange, yellow, green, blue, indigo, and purple. In short, it is a mixed-color light, and the dual-color temperature LED flash is With white LED lights and orange LED lights, it provides a mixed color light to simulate the sun's light, so that the colors shot in dark light are closer to the original color, and the tone is more neutral. If the two-color LED flash uses one lamp bead, it looks half yellow and half orange, or two lamp beads, one yellow and one orange.
  • the outline size of the outer layer and the outline size of the innermost layer satisfy the set proportional value. Specifically, the diameter of the flashlight of the mobile phone, that is, the innermost layer, and the direction in which the mobile phone is held, namely In the width direction of the outer layer outline, the ratio of the outer dimensions is about 1/20 to 1/10.
  • Some digital cameras and mobile phones use laser focusing or infrared focusing technology, and red light will be emitted. And the laser and infrared transmitter / receiver parts are all a black transparent block.
  • the image collector of this embodiment that is, the camera, is not provided with an infrared filter, so that the laser / infrared focused light spot can be directly found.
  • some surveillance cameras can also emit infrared light, so the camera of this embodiment can also be detected.
  • the image sensor of a digital camera generally uses a CCD or CMOS image sensor.
  • the image sensor is sensitive to infrared light that is invisible to the human eye, so now many smart phone cameras have infrared cut-off filters inside to prevent infrared light from entering the image sensor.
  • the infrared cut-off filter has reflection type and absorption type.
  • the reflection type can reflect infrared rays, and the absorption type generally uses blue glass.
  • the mobile phone lens equipped with a reflective infrared cut-off filter will have strong infrared light reflection. Therefore, when the infrared light source provided by the anti-photographing display system in this embodiment illuminates the surrounding environment, if there are various cameras or some sneak shot devices using micro cameras will reflect the infrared light spot, through the image collector of the present invention You can detect.
  • the camera can quickly determine the presence of a mirror mapping as long as the camera finds a special mark in the picture or influence collected by the camera.
  • this embodiment In addition to being able to detect various photographic equipment, this embodiment also needs to be able to record illegal shooting, which can play a greater deterrent effect. Therefore, the anti-photographing display system continuously shoots and divides the scene in the field of view Segment records, when it is calculated that no lens is found in this segment, it will be cleared in time.
  • the anti-photographing display system can set several suspicious levels.
  • the suspicious levels are divided by the amount of preset feature information that is satisfied.
  • Screen display to protect documents.
  • the scene and the current display content of the screen should also be recorded as all on-site records of abnormal events. In this way, you can discover the candid incident and the content of the candid.
  • the first step R, G, B color space data reading.
  • OpenCV loads image data, and the image sensor can directly output pixel value data based on the R (red), G (green), and B (blue) color spaces.
  • the RGB color space is based on the fact that any color is composed of red, green, blue and three primary colors in a certain proportion. Any color will be divided into R, G, B three components, the value of each component from 0-255.
  • Gaussian filter function cvSmooth (src, dst, CV_GAUSSIAN, 3, 3, 0, 0) to perform Gaussian filtering to filter out random noise.
  • cvSmooth (src, dst, CV_MEDIAN, 3, 3, 0, 0) performs median filtering, and performs certain average processing on the pixel data to make the data smoother.
  • the third step color space conversion.
  • the RGB color space is mapped to the HSV space.
  • the HSV color space is characterized by chroma (H), saturation (S), and brightness (V), and has better resolution than RGB under different lighting conditions.
  • RGB to HSV can directly call OpenCV functions: cvCvtColor (src, dst, CV_RGB2HSV)
  • H chroma channel image
  • S saturation channel image
  • V variableness channel image
  • cvCvtPixToPlan (src, H, S, V, 0) can be achieved.
  • the screening of each component can call the function: cvlnRanges function.
  • the diameter of the contour can be obtained by the coordinates of the pixels on the edge of the contour, and the shape of the contour line can be determined. It may be a mobile phone or a digital camera, and compare whether there is the same image as the dedicated infrared mark to determine whether there is a mirror image.
  • This specific implementation can be used in computers, tablets, e-books, LCD TV displays, and projection displays, but is not limited to the above specific applications.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Studio Devices (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

L'invention concerne un système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie, se rapportant au domaine technique des procédés et dispositifs de sécurité d'informations basés sur la vision artificielle. Le système comprend : un dispositif d'affichage ; un collecteur d'image ; une mémoire ; et un processeur pour identifier des informations d'image collectées par le collecteur d'image et les comparer à des informations de caractéristiques prédéfinies dans la mémoire de façon à déterminer s'il existe un dispositif de photographie caché. Les avantages de la solution résident dans le fait que les caractéristiques physiques de parties communes de tous les dispositifs de photographie sont identifiées sur la base de la vision artificielle, et sont également identifiés à l'aide de certaines caractéristiques visuelles typiques de différents dispositifs de photographie, ce qui permet d'obtenir efficacement l'effet technique de prévention de l'utilisation d'une caméra cachée ; l'application du système d'affichage anti-photographie dans la production peut protéger efficacement la sécurité des informations ; et conjointement avec le procédé anti-photographie, un comportement de photographie illégale peut être surveillé et le comportement de photographie illégale peut être suivi, de telle sorte que la capacité de prévention et de commande pour la sécurité d'informations peut être améliorée.
PCT/CN2019/101701 2018-10-09 2019-08-21 Système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie WO2020073739A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811171034.1A CN109271814A (zh) 2018-10-09 2018-10-09 基于计算机视觉的防拍照显示系统及防拍照方法
CN201811171034.1 2018-10-09

Publications (1)

Publication Number Publication Date
WO2020073739A1 true WO2020073739A1 (fr) 2020-04-16

Family

ID=65195155

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/101701 WO2020073739A1 (fr) 2018-10-09 2019-08-21 Système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie

Country Status (3)

Country Link
CN (1) CN109271814A (fr)
TW (1) TW202014927A (fr)
WO (1) WO2020073739A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023225967A1 (fr) * 2022-05-26 2023-11-30 北京小米移动软件有限公司 Procédé et appareil d'invite anti-espionnage, dispositif électronique et support de stockage

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109271814A (zh) * 2018-10-09 2019-01-25 裕利年电子南通有限公司 基于计算机视觉的防拍照显示系统及防拍照方法
CN110084075A (zh) * 2019-04-12 2019-08-02 重庆科芮智能科技有限公司 图像处理方法及装置
CN110096972A (zh) * 2019-04-12 2019-08-06 重庆科芮智能科技有限公司 数据保护方法、装置及系统
CN110163010A (zh) * 2019-04-12 2019-08-23 重庆科芮智能科技有限公司 数据保护方法及装置
CN110084076A (zh) * 2019-04-12 2019-08-02 重庆科芮智能科技有限公司 证据显示方法及装置
CN110163100B (zh) * 2019-04-17 2022-04-01 中国电子科技网络信息安全有限公司 一种防拍照显示器
CN110119454B (zh) * 2019-05-05 2021-10-08 西安科芮智盈信息技术有限公司 证据管理方法及装置
CN110287342A (zh) * 2019-06-27 2019-09-27 维沃移动通信有限公司 设备检测方法、装置、移动终端及存储介质
CN110443136A (zh) * 2019-07-04 2019-11-12 北京九天翱翔科技有限公司 一种全智能电脑显示屏防手机偷拍系统
CN112351155B (zh) * 2019-08-06 2023-02-17 Oppo（重庆）智能科技有限公司 电子设备、用于电子设备的反偷拍装置及其控制方法
CN110572618B (zh) * 2019-09-24 2021-03-16 增长引擎（北京）信息技术有限公司 一种非法拍照行为监控方法、装置及系统
CN113223036B (zh) * 2020-01-21 2022-04-08 湖北讯甲科技有限公司 电子设备现场定位系统
CN111523384A (zh) * 2020-03-19 2020-08-11 浙江省北大信息技术高等研究院 一种基于视觉的会议防偷拍方法、装置、存储介质及终端
CN112051977B (zh) * 2020-09-03 2023-09-08 西安万像电子科技有限公司 屏幕控制方法、装置和系统
CN114564098B (zh) * 2022-02-22 2022-10-25 广州思涵信息科技有限公司 基于计算机视觉识别技术的电脑屏幕显示控制系统和方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005020571A1 (fr) * 2003-08-19 2005-03-03 Thomson Licensing S.A. Systeme d'identification theatral faisant appel a des identificateurs projetes sur un ecran
CN103248825A (zh) * 2013-05-14 2013-08-14 杭州亿脑智能科技有限公司 基于计算机视觉的防偷拍装置及方法
CN106998422A (zh) * 2016-01-26 2017-08-01 陈征 一种自动识别偷拍镜头的装置和方法
CN107146252A (zh) * 2017-04-28 2017-09-08 深圳齐心集团股份有限公司 一种大数据图像处理装置
CN109271814A (zh) * 2018-10-09 2019-01-25 裕利年电子南通有限公司 基于计算机视觉的防拍照显示系统及防拍照方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100627047B1 (ko) * 2003-12-02 2006-09-25 삼성테크윈 주식회사 디지털 카메라 및 그 파일관리방법
CN201751862U (zh) * 2010-07-23 2011-02-23 成都比昂科技有限公司 一种可用于探测光学镜头的光源器件
CN103208156B (zh) * 2013-02-06 2015-09-09 浙江科技学院 一种餐饮自动结算系统和方法
CN103501407A (zh) * 2013-09-16 2014-01-08 北京智谷睿拓技术服务有限公司 隐私保护装置和方法
CN107290752B (zh) * 2016-03-31 2021-01-29 北京中密安信息安全技术有限公司 光学镜头检测方法和检测器

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005020571A1 (fr) * 2003-08-19 2005-03-03 Thomson Licensing S.A. Systeme d'identification theatral faisant appel a des identificateurs projetes sur un ecran
CN103248825A (zh) * 2013-05-14 2013-08-14 杭州亿脑智能科技有限公司 基于计算机视觉的防偷拍装置及方法
CN106998422A (zh) * 2016-01-26 2017-08-01 陈征 一种自动识别偷拍镜头的装置和方法
CN107146252A (zh) * 2017-04-28 2017-09-08 深圳齐心集团股份有限公司 一种大数据图像处理装置
CN109271814A (zh) * 2018-10-09 2019-01-25 裕利年电子南通有限公司 基于计算机视觉的防拍照显示系统及防拍照方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023225967A1 (fr) * 2022-05-26 2023-11-30 北京小米移动软件有限公司 Procédé et appareil d'invite anti-espionnage, dispositif électronique et support de stockage

Also Published As

Publication number Publication date
CN109271814A (zh) 2019-01-25
TW202014927A (zh) 2020-04-16

Similar Documents

Publication Publication Date Title
WO2020073739A1 (fr) Système d'affichage anti-photographie basé sur la vision artificielle et un procédé anti-photographie
US10311298B2 (en) Biometric camera
CA2438724C (fr) Procede et appareil d'inhibition de projection de zones choisies d'une image projetee
TWI434574B (zh) 成像設備
US20070103552A1 (en) Systems and methods for disabling recording features of cameras
CN110365878B (zh) 一种摄像装置和方法
US20120314085A1 (en) Video image display screen, video image display system, and method for detecting camera used in illegal camcording
Yamada et al. Privacy visor: Method for preventing face image detection by using differences in human and device sensitivity
CN102118554B (zh) 监控系统
CN107820066A (zh) 一种低照度彩色摄像机
US20120128330A1 (en) System and method for video recording device detection
KR101608316B1 (ko) 실외 및 실내에서의 홍채이미지 획득장치 및 방법
JP2017207883A (ja) 監視システム、カラーカメラ装置及び光学部品
CN110072035A (zh) 双成像系统
KR101862043B1 (ko) 멀티 카메라
US20210274108A1 (en) A Device Having Exactly Two Cameras and a Method of Generating Two Images Using the Device
CN116828274A (zh) 一种基于hsv的摄像头识别方法及其应用
WO2019008936A1 (fr) Dispositif de traitement d'image, programme informatique, et procédé de traitement d'image
US11092491B1 (en) Switchable multi-spectrum optical sensor
JPWO2020121626A1 (ja) 画像処理装置、コンピュータプログラム、および画像処理システム
CN215990946U (zh) 一种夜视镜头结构以及夜视执法记录仪
KR101155992B1 (ko) 모바일폰을 이용한 카드의 비가시성 마크 검출 방법
CN210246885U (zh) 一种夜视记录装置及夜视执法记录仪
CN201146561Y (zh) 一种小型红外黑白数码照相机
JP6999478B2 (ja) マーカ及びマーカ検出システム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19872018

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19872018

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19872018

Country of ref document: EP

Kind code of ref document: A1