Back to results
US 10,347,293 B1Granted
Detecting, redacting, and scoring confidential information in video
AssigneeDroplr, Inc.
InventorsGray Skinner, Levi Nunnink
Life of this patent
Estimating the term…
Abstract
Provided is a process, including: obtaining screen-cast video; determining amounts of difference between respective frames; selecting a subset of frames based on the amounts; causing OCRing of each frame in the subset of frames; classifying text in each frame-OCR record as confidential or non-confidential; and forming a redacted version of the screen-cast video based on the classifying.
Claims22
A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:
- obtaining, with one or more processors, screen-cast video of a display of a first user computing device captured by a screen-cast-capable client application executing on the first user computing device, the video comprising a plurality of frames in a sequence of frames, each frame depicting an image of the display at a corresponding time;
- determining, with one or more processors, amounts of difference between respective frames and one or more frames that precede respective frames;
- selecting, with one or more processors, a subset of frames from among the plurality of frames based on the subset of frames each having greater than a threshold amount of difference relative to one or more respective preceding frames;
- associating, with one or more processors, with each frame in the subset of frames, respective indications of durations of time until a respective subsequent selected frame in the subset of frames;
- causing, in response to the selection, with one or more processors, optical character recognition (OCRing) of each frame in the subset of frames and obtaining corresponding frame-OCR records, each frame-OCR record including text determined by the OCRing to be depicted in a corresponding frame and bounding areas determined by the OCRing indicating display coordinates of pixels depicting the text in the corresponding frame;
- classifying, with one or more processors, text in each frame-OCR record as confidential or non-confidential;
- and
- forming, with one or more processors, a redacted version of the screen-cast video by, for each frame having text classified as confidential:
- determining bounding areas of the text classified as confidential based on the frame-OCR record corresponding to the respective frame having text classified as confidential;
- determining a subsequence of frames within the duration of time associated with the respective frame having text classified as confidential;
- and
- modifying, based on the determined bounding areas and the determined subsequence, pixel values in the bounding areas for each of the frames in the subsequence to redact the text classified as confidential in the respective frame and the subsequence of frames;
- and
- storing, with one or more processors, the redacted version of the screen-cast video in memory.
11 more elements
A method, comprising:
- obtaining, with one or more processors, screen-cast video of a display of a first user computing device captured by a screen-cast-capable client application executing on the first user computing device, the video comprising a plurality of frames in a sequence of frames, each frame depicting an image of the display at a corresponding time;
- determining, with one or more processors, amounts of difference between respective frames and one or more frames that precede respective frames;
- selecting, with one or more processors, a subset of frames from among the plurality of frames based on the subset of frames each having greater than a threshold amount of difference relative to one or more respective preceding frames;
- associating, with one or more processors, with each frame in the subset of frames, respective indications of durations of time until a respective subsequent selected frame in the subset of frames;
- causing, in response to the selection, with one or more processors, optical character recognition (OCRing) of each frame in the subset of frames and obtaining corresponding frame-OCR records, each frame-OCR record including text determined by the OCRing to be depicted in a corresponding frame and bounding areas determined by the OCRing indicating display coordinates of pixels depicting the text in the corresponding frame;
- classifying, with one or more processors, text in each frame-OCR record as confidential or non-confidential;
- and
- forming, with one or more processors, a redacted version of the screen-cast video by, for each frame having text classified as confidential:
- determining bounding areas of the text classified as confidential based on the frame-OCR record corresponding to the respective frame having text classified as confidential;
- determining a subsequence of frames within the duration of time associated with the respective frame having text classified as confidential;
- and
- modifying, based on the determined bounding areas and the determined subsequence, pixel values in the bounding areas for each of the frames in the subsequence to redact the text classified as confidential in the respective frame and the subsequence of frames;
- and
- storing, with one or more processors, the redacted version of the screen-cast video in memory.
11 more elements
Dependencies are inferred from the claim text.