US 10,242,099 B1Granted

Cascaded multi-tier visual search system

AssigneeOath Inc.

InventorsPierre Garrigues, Benjamin Jackson Culpepper, Huy X. Nguyen, Charles Cadieu, Andrew Stadlen, Gerry Pesavento, David Warland

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A system for multi-tier visual recognition comprises a processor and a memory. The processor is configured to calculate a rank for each of a plurality of object models. The plurality of object models are used for visual recognition. Each of the plurality of object models has a size. The processor is configured to divide the plurality of object models into a plurality of sets based at least in part on the rank for each of the plurality of object models, and provide a first set of the plurality of sets to a first tier and a second set of the plurality of sets to a second tier. The memory coupled to the processor and configured to provide the processor with instructions.

Claims17

Dependent claims

A system for search of image data, comprising:

a processor;
and
a memory having stored thereon instructions that, when executed by the processor, cause the processor to:
receive the image data from a client device of a user,
obtain a plurality of object models used for visual recognition of objects in the image data, wherein each of the plurality of object models is associated with an image object capable of being identified within an image,
determine a rank for each of the plurality of object models,
identify a first set of the plurality of object models to be used by the client device and a second set of the plurality of object models to be used by a server based on the rank, and
provide the first set of the plurality of object models to the client device and the second set of the plurality of object models to the server so that the client device performs a first search for a first set of objects in the image data based on the first set of the plurality of object models and the server performs a second search for a second set of objects in the image data based on the second set of the plurality of object models.

5 more elements

A method implemented on a computing device having at least one processor, storage, and communication platform for search of image data, comprising:

receiving the image data from a client device of a user;
obtaining a plurality of object models used for visual recognition of objects in the image data, wherein each of the plurality of object models is associated with an image object capable of being identified within an image;
determining, by the processor, a rank for each of the plurality of object models;
identifying a first set of the plurality of object models to be used by the client device and a second set of the plurality of object models to be used by a server based on the rank;
and
providing the first set of the plurality of object models to the client device and the second set of the plurality of object models to the server so that the client device performs a first search for a first set of objects in the image data based on the first set of the plurality of object models and the server performs a second search for a second set of objects in the image data based on the second set of the plurality of object models.

3 more elements

Dependencies are inferred from the claim text.