WO2019215758A1 - System & method for blurring video on social platform for providing anonymity - Google Patents
System & method for blurring video on social platform for providing anonymity Download PDFInfo
- Publication number
- WO2019215758A1 WO2019215758A1 PCT/IN2019/050367 IN2019050367W WO2019215758A1 WO 2019215758 A1 WO2019215758 A1 WO 2019215758A1 IN 2019050367 W IN2019050367 W IN 2019050367W WO 2019215758 A1 WO2019215758 A1 WO 2019215758A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- user
- image
- dynamic
- controlled
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Definitions
- This invention relates to the social Media industry specifically related to the technology which controls & processes the video images to the specific automatically determined portion of the face to render anonymity for the users on social media.
- the invention further relates to the system wherein processing of the image is done in the fraction of a second, to stream the video.
- the embodiment of the present invention contemplates to a method which is meant to let user share things which he/she would not share in a known social circle physical or digital for the fear of judgement. These things could be personal fear, confession, bad incident, embarrassment, professional opinion, political opinion, social opinion, depression etc as long as it does not hurt someone else.
- the reason user would be comfortable doing so with the help of disclosed invention is that it’s anonymous but still expressive as it uses selfie video technology for posting compared to other competitors who are just text based. It’s a well-known fact that sharing what’s bothering you would help you relieve and take off stress. And people are interested to watch posts from other users as they want to dive deep into reality of the world unlike the orchestrated image on Facebook.
- Yet another embodiment of the present invention contemplates to a method Restricting user to record only his face/selfie video, not an object or scenery. Otherwise there would be no visual content for the audience and it will become merely an audio post.
- Invention uses face recognition technology from other providers to make sure that a visible human face is there in the camera frame for recording to take place. If a user tries this recording without showing their face to camera, invention will not allow them to record a post.
- Yet another embodiment of the present invention addresses the challenge of making a user anonymous within a selfie (face) video and still keeps the expressions of user’s selfie video authentic. Also, the present invention ensures that the video content is authentic and comes from the real anonymous user and not a bot.
- Yet another object of the invention is to provide subtitles or other superimposed relevant text.
- Yet another object of the invention is to provide option to the end user to determine the degree of blurring before posting the video.
- Another embodiment of the present invention contemplates the video which is converted to audio files using servers, using other provider’s technology (discussed in the brief description below).
- the post video Once the post video is received by the server, it converts the video to an audio and subsequently to a text file. It is on these text data we apply Natural Language Processing to extract the subject, content, sentiment etc .
- the invention relates generally to the field of social media technology and internet base devices. More particularly, one or more of the embodiments relates to capturing selfie video and maintaining anonymity.
- FIG. 1 is a schematic view of the flowchart representing the overall mechanism of interaction between the end user and invention.
- the flowchart provided the explanation about the components user device and its interaction with the operating system device which is further integrated in the interaction device.
- Fig. 2 is a schematic view depicts various components of Operating System.
- the technology uses a camera to capture the face of the user, while the user records a selfie video through Unit 1
- Fig. 3 is a schematic view of the flowchart titled: Rendering and Recording to add anonymity to the selfie videos .
- Fig. 4 Presents Working model of the invention.
- Fig. 5 is a schematic view of the Flowchart showing how Natural Language Processing is applied to the selfie videos to drive data, insights and analytics .
- FIG. 1 is a schematic view of the flowchart representing the overall mechanism of interaction between the end User , invention hereinafter referred as Unit 1 and Server .
- the flowchart provided the explanation about the components which includes user’s device and its interaction with the Operating System ( This operating system includes Android, IOS, windows, tizen. So, this acts as an environment to run our algorithm ) device which is further integrated in the interaction device.
- Interaction Devices includes Mobile Phones, Laptops, and tablet etc.
- the video images collected through the interacting device is transferred to operating system comprised of algorithm which interacts with the Server comprised of memory unit, decoder unit, data collecting hard disk and a unit for data analysis.
- the invention would keep all the face features preferably above nose tip to be blurred so as to only reveal partial face of the user.
- the expressions of video are authentic with lips clearly visible in sync with user voice and everything above key features is blurred keeping user’s identity anonymous.
- Fig. 2 is a schematic view depicts various components of Operating System.
- the technology uses a camera to capture the face of the user, while the user records a selfie video through Unit 1.
- Unit1 identifies the relevant libraries such as but not limited to Google face recognition, Karios, Amazon Recognition are used to capture the facial key features.
- the processing involves detecting the prominent facial key features like lips, nose, eyes etc.
- Preferred embodiment explains the recognition of the nose tip and so capture the nose coordinates.
- the nose of the user is identified, and the technology superimposes a dynamic and controlled image on the nose up portion of the video thereby making the user anonymous (explained in detailed in Fig: 3) and in a video.
- the superimposed image is dynamic in the sense that its dimensions are in sync with the facial movement of the user, so that only the nose up part gets blurred.
- the image is controlled w.r.t its opacity or blurriness.
- blurriness is used to make the user partially blurred so as to maintain the authenticity of the video. The idea is to blur the user partially so that his lips could be seen in sync with what he says (audio part) in the video and this way the credibility of the video is not lost. Even if a user moves his/her face while recording the invention would readjust quickly to pinpoint the nose tip.
- Fig. 3 is a schematic view of the flowchart titled: Rendering and Recording to add anonymity to the selfie videos .
- Algorithm detects human face and sends the coordinates of the specific key feature to GPU of the device. GPU renders a controlled image on the portion above the key features (preferably nose). Image rendering and face recording happens simultaneously.
- the anonymous video so formed is stored in the server.
- the processing helps to get the coordinates of the key feature (preferably nose) and the audio part in a selfie video.
- the technology then superimposes a dynamic and controlled image on the up to the key feature (preferably nose) part of the video thus making user anonymous and authenticity of the selfie video is maintained by controlling the blurriness of the image so that the lips of the user and in sync with the audio content of the video.
- Fig. 4 Presents Working model of the invention.
- Fig. 5 is a schematic view of the Flowchart showing how Natural Language Processing is applied to the selfie videos to drive data, insights and analytics .
- the videos are converted to audio files on the server.
- the audio files are then converted to text files.
- Natural Language Processing is applied to the text data that is gathered. Natural Language Processing application gives the details like content, subject, sentiment etc. All the details from the text are collected in the server and gets reflected on the dashboard.
- the dashboard with insights on what user’s posts is shared with stakeholders like Media, Govt. agencies etc.
- the audio part of the selfie video is captured by the disclosed invention and this Audio is in converted to text using APIs like but not limited to IBM Watson, Google AI APIs, Amazon NLP etc.
- Dating/matrimonial platform A dating/matrimonial platform where match is performed on basis of interest, preference etc. rather than identity. Users can chat (in the anonymous video) initially and not reveal their identity to each other, and only decide to provide their identity later when comfortable, if they want.
- Job interview process In an organization for interview to ensure candidate does not get selected because of his/her identity or connection with the interviewer or partiality in looks. In such cases, interview in anonymous video chat can make the interview and selection process clean and not biased.
- News interview Invention can help to take interview (e.g. interview for news) of people who are not comfortable in revealing their identity or don't want to face the camera.
- Invention can improve internal communication between worker and higher management, by using anonymous video they(worker) can provide their real thought/feedback on a topic/issue/concern or can complaint against the senior authority(eg. manager etc) without any fear.
- Exit polls can help people to participate in the exit polls, where generally people do not want to share or reveal their real opinion.
- Anonymous customer/user Those who need more information on a given topic but do not want to be caught seeking out that information.
- Invention could help someone who’s struggling with their sexuality, hasn’t gone public with that struggle, but has many unvoiced questions and concerns. This person can ask all of their questions in an anonymous video without revealing their identity and risking premature exposure.
Abstract
Description
Claims (7)
- A method for transmitting anonymous video data of the user on social network, comprising:
A processing Unit which identifies the relevant libraries from open source to detect the the prominent facial key features and divides the video into dynamic and controlled images, wherein coordinates above the key feature is controlled image and below the key feature is dynamic;
Graphical Processing Unit (GPU) which pixelates the controlled images for changing the blurriness or opacity of controlled image and superimposes the controlled image with the dynamic coordinates of the image, wherein superimposition of controlled and dynamic image is done simultaneously;
Natural Language Processing Unit (NPLU) to convert audio information extracted through dynamic portion and convert it into text files. - The method as claimed in claim 1, wherein user can capture video through interacting devices which includes Mobile Phones, Laptops, and tablet.
- The method as claimed in claim 1, wherein relevant libraries includes but not limited to Google face recognition, Karios and Amazon Rekognition.
- The method as claimed in claim 1, wherein facial key features all predetermined facial feature not restricted to nose or lips.
- The method as claimed in claim 1, wherein the audio part of the selfie video is captured by the disclosed invention and this Audio is in converted to text using APIs like but not limited to IBM Watson , Google AI APIs, Amazon NLP etc.
- The method as claimed in claim 1, wherein conversion of audio to text file is done for data research and analysis.
- The method as claimed in claim 1 used to maintain anonymity of the user, used for the purpose not limited to Dating/matrimonial platform, Job interview process, News interview, Exit polls and Surveys.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
IN201811017386 | 2018-05-09 | ||
IN201811017386 | 2018-05-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019215758A1 true WO2019215758A1 (en) | 2019-11-14 |
Family
ID=68466736
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IN2019/050367 WO2019215758A1 (en) | 2018-05-09 | 2019-05-09 | System & method for blurring video on social platform for providing anonymity |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2019215758A1 (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030108240A1 (en) * | 2001-12-06 | 2003-06-12 | Koninklijke Philips Electronics N.V. | Method and apparatus for automatic face blurring |
-
2019
- 2019-05-09 WO PCT/IN2019/050367 patent/WO2019215758A1/en active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030108240A1 (en) * | 2001-12-06 | 2003-06-12 | Koninklijke Philips Electronics N.V. | Method and apparatus for automatic face blurring |
Non-Patent Citations (1)
Title |
---|
AKHIL KANADE ET AL.: "Automatic Subtitle Generation for Videos", INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH AND GENERAL SCIENCE, vol. 3, no. 6, 31 December 2015 (2015-12-31), pages 744 - 747, XP055653848 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10095918B2 (en) | System and method for interpreting interpersonal communication | |
US10311619B1 (en) | Video stream customization using graphics | |
US8154578B2 (en) | Multi-camera residential communication system | |
US8159519B2 (en) | Personal controls for personal video communications | |
US8253770B2 (en) | Residential video communication system | |
US8791977B2 (en) | Method and system for presenting metadata during a videoconference | |
US8063929B2 (en) | Managing scene transitions for video communication | |
US10834456B2 (en) | Intelligent masking of non-verbal cues during a video communication | |
US20110063440A1 (en) | Time shifted video communications | |
JP2009510877A (en) | Face annotation in streaming video using face detection | |
US20140282089A1 (en) | Analysis of multi-modal parallel communication timeboxes in electronic meeting for automated opportunity qualification and response | |
KR20160074616A (en) | Capturing media content in accordance with a viewer expression | |
JP6563421B2 (en) | Improved video conferencing cross-reference for related applications | |
PH12016500612B1 (en) | Relevance based visual media item modification | |
CN111316656B (en) | Computer-implemented method and storage medium | |
US20240048572A1 (en) | Digital media authentication | |
Hwang et al. | Hide and seek: Choices of virtual backgrounds in video chats and their effects on perception | |
US11294474B1 (en) | Controlling video data content using computer vision | |
Suduc et al. | Status, challenges and trends in videoconferencing platforms | |
US20230319234A1 (en) | System and Methods for Enhanced Videoconferencing | |
WO2019215758A1 (en) | System & method for blurring video on social platform for providing anonymity | |
Mallén | Stirring up virtual punishment: a case of citizen journalism, authenticity and shaming | |
Tanaka et al. | Appearance, motion, and embodiment: unpacking avatars by fine‐grained communication analysis | |
US20200110958A1 (en) | Modifying capture of video data by an image capture device based on identifying an object of interest within capturted video data to the image capture device | |
Cannavò et al. | Immersive movies: the effect of point of view on narrative engagement |
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: 19800249 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: 19800249 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19800249 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 02.03.2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19800249 Country of ref document: EP Kind code of ref document: A1 |