The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 05, 2025

Filed:

Dec. 02, 2021
Applicant:

Amazon Technologies, Inc., Seattle, WA (US);

Inventors:

Manoj Aggarwal, Seattle, WA (US);

Gerard Guy Medioni, Los Angeles, CA (US);

Lavisha Aggarwal, Seattle, WA (US);

Prithviraj Banerjee, Redmond, WA (US);

Jiuhong Xiao, Long Island, NY (US);

Rajeev Ranjan, Seattle, WA (US);

Dilip Kumar, Seattle, WA (US);

Assignee:

AMAZON TECHNOLOGIES, INC., Seattle, WA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 40/50 (2022.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 9/00 (2006.01); G06V 40/10 (2022.01);
U.S. Cl.
CPC ...
G06V 40/50 (2022.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 9/00 (2013.01); G06V 40/11 (2022.01);
Abstract

During enrollment to a biometric identification system an image of at least a portion of a user is acquired and processed to determine a compact representation (CR). The CR may be stored for later comparison to identify the user, to train embedding models, and so forth. The image is not stored. A machine learning system that comprises a variational autoencoder is trained to produce the CR with a loss function that includes a distortion loss, an embedding distance loss, and in some implementations a bitrate loss. The trained encoder is used to determine the CR from an input image, while the decoder is not stored. The CR contains sufficient information to be used as training data for embedding models, instead of acquired images. Training may be more computationally efficient using the CR. Recognition comparisons may be more efficiently performed using the CR, compared to query images.


Find Patent Forward Citations

Loading…