Systems and methods for large scale, high-dimensional searches
AssigneeAdobe Systems Incorporated
InventorJonathan W. Brandt
Life of this patent
Estimating the term…
Loading patent…
AssigneeAdobe Systems Incorporated
InventorJonathan W. Brandt
Estimating the term…
Methods and systems for fast, large scale, high-dimensional searches are described. In some embodiments, a method comprises transforming components of a high-dimensional image descriptor into transformed components in a transform domain, allocating one or more bits available within a bit budget to a given transformed component within a first subset of transformed components as a function of a variance of the given transformed component, independently quantizing each transformed component within the first subset of transformed components, generating a compact representation of the high-dimensional image descriptor based, at least in part, on the independently quantized components, and evaluating a nearest neighbor search operation based, at least in part, on the compact representation of the high-dimensional image descriptor.
A computer-readable storage medium, excluding signals per se, comprising instructions stored thereon that, responsive to execution by a computing device, direct the computing device to perform operations comprising:
A method, comprising:
A system, comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Distances to prototypes: distances to cluster centroïds
Salient features, e.g. scale invariant feature transforms [SIFT]: using a plurality of salient features, e.g. bag-of-words [BoW] representations
Computing and data processing
Image and video recognition
About 4 years 9 months of term left · ends 18 Jul 2031 (estimated)
1. Field of the Invention
This specification relates to computer technologies, and, more particularly, to systems and methods for performing fast, large scale, high-dimensional searches.
2. Description of the Related Art
FIG. 1 is a block diagram of an illustrative computer system or device configured to implement some embodiments of the techniques described herein.
FIG. 2 is a block diagram of an illustrative image analysis module according to some embodiments.
FIG. 3 is a flowchart of a method for generating a compact representation of high-dimensional image descriptors according to some embodiments.
While this specification provides several embodiments and illustrative drawings, a person of ordinary skill in the art will recognize that the present specification is not limited only to the embodiments or drawings described. It should be understood that the drawings and detailed description are not intended to limit the specification to the particular form disclosed, but, on the contrary, the intention is to cover all modifications, equivalents and alternatives falling within the spirit and scope of the claims. The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description. As used herein, the word “may” is meant to convey a permissive sense (i.e., meaning “having the potential to”), rather than a mandatory sense (i.e., meaning “must”). Similarly, the words “include,” “including,” and “includes” mean “including, but not limited to.”
This specification first presents an illustrative computer system or device, as well as an illustrative image analysis module that may implement certain embodiments of methods disclosed herein. The specification then provides several techniques for: (1) generating a compact representation of a high-dimensional descriptor; (2) estimating distances among components of the high-dimensional descriptor; and (3) performing fast, high-dimensional searches based at least in part on those estimated distances. The final portion of the specification discusses various applications and experiments where the systems and methods described herein have been employed.
Some of the embodiments disclosed herein are in the field of digital, image processing and computer vision, and therefore are suitable for use in image searches. It should be understood, however, that the techniques described herein are not limited to use with digital image data. Where suitable, these techniques may be employed in any application where other types of high-dimensional searches may be performed, such as, for example and without limitation, medicine (e.g., microarray DNA analysis), Internet portals (e.g., searching among millions or billions of records), financial data (e.g., information about stock exchange data), etc.