Back to results
US 2021/0342386 A1Published application
Similarity search engine for a digital visual object
AssigneeIsrael Atomic Energy Commission Nuclear Research Center—Negev
InventorsIdan Mosseri, Matan Rusanovsky, Gal Oren
Life of this patent
Estimating the term…
Abstract
The present invention provides a similarity search engine for a digital visual object (i.e., a digital image that represents a design, graphics, logo, symbols, words, or any combination thereof). The similarity search engine is based on a method that consists of conducting several independent search queries, thus each query examining a different aspect of similarity.
Claims8
A method of searching for similarity between digital visual objects, comprising:
- a) receiving an image of a digital visual object to be examined;
- b) applying similarity search on the received image by using one or more of the following similarities aspects:
- automated tags similarity, image/pixel similarity, text similarity and manual tags similarity;
- c) extracting from at least one database stored images of digital visual objects according to said applied similarity search;
- d) ordering the extracted images according to each similarity aspect;
- and
- e) displaying the ordered images of each aspect in a different section.
4 more elements
A system of searching for similarity between digital visual objects, comprising:
- a) at least one processor;
- and
- b) a memory comprising computer-readable instructions which when executed by the at least one processor causes the processor to execute similarity search engine, wherein the similarity search engine:
- I. receives an image of a digital visual object to be examined;
- II. applies similarity search on the received image by using one or more of the following similarities aspects:
- automated tags similarity, image/pixel similarity, text similarity and manual tags similarity;
- III. extracts from at least one database stored images of digital visual objects according to said applied similarity search;
- IV. orders the extracted images according to each similarity aspect;
- and
- V. displays the ordered images of each aspect in a different section.
7 more elements
Dependencies are inferred from the claim text.