# US 12,561,975 B2 · Method and system for detecting private video > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,561,975 B2 - Document ID: US12561975B2 - Status: Granted - Kind: B2 - Application number: 18/327,385 - Filed: 2023-06-01 - Published: 2023-11-02 - Granted: 2026-02-24 - Earliest claimed: 2022-05-02 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Sukumar Moharana; Debi Prasanna Mohanty; Siva Prasad Thota; Archit Panwar; Dewang Agarwal; Anchal Pandey; Vanraj Vala; Dwaraka Bhamidipati Sreevatsa - Web page: https://patentgrep.com/patent/US12561975B2 ## CPC - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - H04N 21/4542: {Blocking scenes or portions of the received content, e.g. censoring scenes} - G06V 10/764: using classification, e.g. of video objects - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - H04N 7/0117: {involving conversion of the spatial resolution of the incoming video signal (for graphics images G09G2340/0407)} - H04N 21/44008: {involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)} - H04N 21/440245: {the reformatting operation being performed only on part of the stream, e.g. a region of the image or a time segment} - H04N 21/45455: {applied to a region of the image} - H04N 21/47205: {for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A method for detecting a private video may include estimating a low (e.g., minimum) resolution for performing analysis of a plurality of frames of a video. The method may include reducing a first resolution associated with the plurality of frames to the low (e.g., minimum) resolution. The method may include detecting a presence of at least one indicator for private information in one or more frames amongst the plurality of frames upon analyzing the plurality of frames at the low (e.g., minimum) resolution. The method may include detecting a presence of the private information in the video upon analyzing the one or more frames comprising the at least one indicator at a second resolution in response to detecting the presence of the at least one indicator at the low (e.g., minimum) resolution. The method includes classifying the video as the private video in response to detecting the presence of the private information in the video at the second resolution. ## Claims ### Claim 1 A method in an electronic device comprising at least one processor, for detecting a private video in the electronic device, the method comprising: estimating a low resolution for performing analysis of a plurality of frames of a video; reducing a first resolution associated with the plurality of frames to the low resolution; detecting a presence of at least one indicator for private information in one or more frames amongst the plurality of frames upon analyzing the plurality of frames at the low resolution; detecting a presence of the private information in the video upon analyzing the one or more frames comprising the at least one indicator at a second resolution in response to at least detecting the presence of the at least one indicator at the low resolution; and classifying, by the electronic device, the video as the private video in response to at least detecting the presence of the private information in the video at the second resolution, wherein estimating the low resolution for the plurality of frames is based on at least one of a plurality of latent parameters and a plurality of heuristic parameters associated with the video. ### Claim 2 (depends on 1) The method as claimed in claim 1, comprising: providing one or more suggestions to a user for converting the private video to a video without the private information in response to a detection of the private video. ### Claim 3 (depends on 1) The method as claimed in claim 1, comprising: receiving the video comprising a plurality of frames; and extracting the plurality of frames from the video and selecting the plurality of frames from the plurality of frames, wherein each frame amongst the plurality of frames is a key frame in the video. ### Claim 4 (depends on 1) The method as claimed in claim 1, comprising: marking the one or more frames as one or more private frames in response to at least detecting the private information in the one or more frames of the video; and classifying the video as the private video in response to at least determining that a number of the one or more private frames are greater than a pre-determined threshold number of frames. ### Claim 5 (depends on 1) The method as claimed in claim 1, wherein the low resolution is at least one of an ultra-low resolution, a low resolution, and a medium resolution by a resolution regressing engine. ### Claim 6 (depends on 1) The method as claimed in claim 1, wherein the one or more frames is passed to a high-resolution analyzer based on the one or more frames comprising the at least one indicator being greater than a pre-defined threshold number of frames. ### Claim 7 (depends on 1) The method as claimed in claim 1, wherein the at least one indicator comprises at least one of obscenity in the content, a presence of alcohol in the content, and a vice content. ### Claim 8 (depends on 1) The method as claimed in claim 1, wherein the private information indicates presence of at least one private body part in the one or more frames. ### Claim 9 (depends on 1) The method as claimed in claim 1, wherein the plurality of latent parameters comprises two or more of a readability of text in the video, a visual clarity of the video, a percentage of pixels of the video, an adversarial nature of the video, a transformation of orientations of the video caused due to change in a resolution of the video, and an aliasing caused due to the change in the first resolution of the video. ### Claim 10 (depends on 1) The method as claimed in claim 1, wherein the plurality of heuristic parameters comprises two or more of a color, an image compression quality, a percentage of contiguous region, a number of contours in the video, a computed histogram of gradients in the video, and text in the video. ### Claim 11 (depends on 1) The method as claimed in claim 1, wherein each frame amongst the plurality of frame comprises an inline frame (iframe). ### Claim 12 (depends on 1) The method as claimed in claim 1, wherein the second resolution is greater than the low resolution and lower than the first resolution of the video. ### Claim 13 A system for detecting a private video in an electronic device, the system comprising: a resolution regressing engine, comprising processing circuitry, configured to: estimate a low resolution associated with a plurality of frames of a video; and reduce a first resolution associated with the plurality of frames to the low resolution; a low-resolution analyzer, comprising circuitry, configured to detect a presence of at least one indicator for private information in one or more frames amongst the plurality of frames based on analyzing the plurality of frames at the low resolution; a high-resolution analyzer, comprising circuitry, configured to detect a presence of the private information in the video upon analyzing the one or more frames comprising the at least one indicator at a second resolution based on detection of the presence of the at least one indicator at the low resolution; and a processor, comprising circuitry, configured to classify the video as the private video based on detection of the presence of the private information in the video at the second resolution, wherein estimating the low resolution for the plurality of frames is based on at least one of a plurality of latent parameters and a plurality of heuristic parameters associated with the video. ### Claim 14 (depends on 13) The system as claimed in claim 13, comprising: an output engine, comprising circuitry, configured to provide one or more suggestions to a viewer for converting the private video to a video without the private information in response to a detection of the private video.