WO2019215758A1

WO2019215758A1 - System & method for blurring video on social platform for providing anonymity

Info

Publication number: WO2019215758A1
Application number: PCT/IN2019/050367
Authority: WO
Inventors: Ashish Kumar SINGH BAIS
Original assignee: Singh Bais Ashish Kumar
Priority date: 2018-05-09
Filing date: 2019-05-09
Publication date: 2019-11-14

Abstract

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. Fig 1 Summary: Interaction between User & Invention Fig 2 Description of the process (Operating System) Fig 3 Rendering and Recording to add anonymity to the selfie videos Fig 4 Working model on Invention 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. Fig 1 Summary: Interaction between User & Invention Fig 2 Description of the process (Operating System) Fig 3 Rendering and Recording to add anonymity to the selfie videos Fig 4 Working model on Invention Fig 5 Flowchart showing how Natural Language Processing is applied to the selfie videos to drive data, insights and analytics.

Description

SYSTEM & METHOD FOR BLURRING VIDEO ON SOCIAL PLATFORM FOR PROVIDING ANONYMITY

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.

Many people today are using social media to connect to other users, to express their thoughts and emotions. But by far the majority of the social media platforms are identity driven and recently many reports have been published that focuses on the harmful effect of the identity driven social media. Users of identity driven platforms bring their best foot forward and mostly highlight their good side and end up portraying just the good highlights of their life and this way these identity driven platforms restrict users from expressing their true feelings as their social footprints make them very conscious about how other users will perceive. Also, users hesitate to give their true opinions on other users’ content as they are too conscious to destroy their social footprints.

Above discussed are the major reasons that led to the emergence of some anonymous social media platforms. But these social media platforms only focus on text as means of communicating with other users. Problem with text form of communication is that they are less expressive and less engaging and a major problem in case of anonymous social media is the authenticity of the text messages. A bot can write 1000s of text messages and thus bring into question the very existence of these anonymous social media platforms. Invention addresses this gap by developing an anonymous social media platform which uses video as a means of communication making it more expressive and engaging. To make an individual anonymous within a video, the invention discloses a method to partial blur of screen where user’s facial key feature (which includes Nose, Lips and Eyes and Ears) and above part is completely blurred but below nose tip everything is clearly visible. This adjustment to nose tip happens dynamically so user can move their face while recording still they will be anonymous. Same video would be transmitted and saved on our server for other users to view. The benefit of dynamic partial screen blur compared to full screen blur is that it feels more authentic as user’s lips are clearly visible in sync with their voice. This makes the entire experience very engaging for all the users.

Prior arts available in the domain are, system which may recognizes the entire face (by Jon Hundley; US20090041311A1; Titled: Facial recognition-based content blocking system by Jon Hundley) or can blur/change the background of the video (By Microsoft; US2012203271712; Titled: Modifying video regions using mobile device input by Microsoft) or selective filtration is done with the help of presence selection device (by Biscotti Inc US20150070516A1; Titled: Automatic Content Filtering) or video sharing with happens with reduced action (by Lutebox LTD; US20150172238A1: Titled: Sharing content on devices with reduced user actions). There are Platform for pseudo-anonymous video chat with intelligent matching of chat partners (by Airtime Media Inc; US20120236103A1). In this invention chat partners do not know each other, and they are anonymously chatting to each other. US20150373021A1: Method & System for exchanging private messages by Kevin Alan Tussy; Most relevant as it enables user to quantify the amount blurring required.

Presently, there is no method and system that help to maintain the complete anonymity of the user for the various above stated reasons by partially blurring the video and hiding the portion which may otherwise reveal the identity of the person. Blurred portion is accordingly being synchronized with the non-blurred potion by the algorithm. There are few inventions available in this domain which are not able to cater this section of the consumer.

OBJECT OF THE INVENTION

The following presents a simplified summary of the disclosure in order to provide a basic understanding to the reader. This summary is not extensive overview of the disclosure and it does not identify key and/ or critical elements of the invention or delineate the scope of the invention. The sole purpose is to present some concepts disclosed herein in a simplified form as a prelude to the more detailed description that is presented later.

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). 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.

BRIEF DESCRIPTION OF THE DRAWING

A complete understanding of the system and method of the present invention may be obtained by reference to the following drawings:

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.

DETAILED DESCRIPTION OF THE INVENTION

The present invention now will be described hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. Indeed, the invention may be embodied in many different forms and should not be constructed as limited to the embodiments set forth herein, rather these embodiments are provided so that this disclosure will satisfy applicable legal requirements.

Many modifications and other embodiment of the invention set forth herein will readily occur to one skilled in the art to which the invention pertain having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the invention is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in generic and descriptive sense only and not for purpose of limitation.

Other objects and advantages of the present invention will become apparent to those skilled in the art upon reading the following detailed description of the preferred embodiments, in conjunction with accompanying drawings, wherein like reference numerals have been used to designate like elements, and wherein:

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. Also, 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. By this aggregation of above-mentioned technology, 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. Also, 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. Content received from users through anonymous selfie videos. 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. Further these Text are fed to APIs like IBM Watson, Google AI APIs, Amazon NLP to do Natural Language Processing (NLP) and Sentiment analysis. These data points are then captured in Hard disk database. This application of AI helps to extract analysis based on the audio content in the selfie videos.

More information to be provided, within the scope of the invention, would include but not limited to:

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.

Complaint / Feedback/ Review: Invention can help common people to raise their voice against powerful people/ industry/ service/ product in the society Eg. Corrupt politicians etc.

Industry worker-management communication: 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.

Survey: Invention can help in conducting a survey where people hesitate to share their identity but want to voice their concerns. Eg. Health survey.

Exit polls: Invention can help people to participate in the exit polls, where generally people do not want to share or reveal their real opinion. Eg. Election exit poll

Anonymous customer/user: Those who need more information on a given topic but do not want to be caught seeking out that information. Eg. 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.

Claims

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.