HIERARCHICAL SPARSE REPRESENTATION FOR IMAGE RETRIEVAL

Patent №

US 8,463,045

Granted

2013-06-11

Filed 2010

Owner

MICROSOFT CORPORATION

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

12943805

A hierarchical sparse codebook allows efficient search and comparison of images in image retrieval. The hierarchical sparse codebook includes multiple levels and allows a gradual determination/classification of an image feature of an image into one or more groups or nodes by traversing the image feature through one or more paths to the one or more groups or nodes of the codebook. The image feature is compared with a subset of nodes at each level of the codebook, thereby reducing processing time.

AI classification

Vision1.00
Machine learning1.00
AI hardware0.98
Natural language0.22
Planning0.14
Knowledge representation0.05
Speech0.04
Evolutionary computation0.00

Ownership

MICROSOFT CORPORATION

assignment · 253520530

Assignors

YANG, LINJUN, TIAN, QI, NI, BINGBING

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC