/Patent Tracker
SamsungGranted patentAI & softwareInterest 6/10

Samsung patents search tool that finds images in videos using text

Samsung describes a device that lets users search for specific scenes in videos or multimedia files by typing words. The system converts images in the media into text descriptions, then matches those descriptions with the user's search query to find the right moment.

Why it mattersThis could make it easier to find specific visual moments in long videos without scrubbing through the timeline manually.

In the filing’s own words

An electronic device includes a speaker; a display; a memory; and a processor operatively connected to the speaker, the display, and the memory. The processor is configured to: identify an input indicating to search a multimedia content stored in the memory, the multimedia content comprising a first text and a plurality of images, the input comprising a third text, generate a second text representing the plurality of images, identify, based on the first text and the second text, a portion of the multimedia content, which is matched to the third text, and output, via at least one of the speaker or the display, the portion of the multimedia content.

What exactly they claim (claim 1)

1. An electronic device comprising: a speaker; a display; memory including one or more storage media storing instructions; and at least one processor including processing circuitry, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: identify an input for searching a first set of contents stored in the memory, wherein the first set of contents include a first content including a first image and a second content including the first image; in response to the input, identify a second set of contents in which an image included in the first set of contents is replaced with at least one text, wherein the second set of contents include a third content corresponding to the first content in which the first image is replaced with a first text, and a fourth content corresponding to the second content in which the first image is replaced with a second text; identify at least portion of the second set of contents, which corresponds to a third text associated with the input; and output, via at least one of the speaker or the display, the at least portion of the second set of contents.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
Electronic device for identifying image combined with text in multimedia content and method thereof
Patent number
US12764081B2
Application number
18538649
Filed
Dec 13, 2023
Granted
Oct 13, 2026
Inventors
2
Claims
20

Classified under

H04L 51/10 Electricity & electronicsG06F 40/30 Physics & computingH04L 51/04 Electricity & electronics
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Samsung in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.