公开(公告)号：US11361447B2

公开(公告)日：2022-06-14

申请号：US16912366

申请日：2020-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Sabine Sternig ,  Luitpold Staudigl ,  Pablo Barbachano ,  Thomas Sydney Austin Wallis ,  Muhammad Bilal Javed ,  Michael Donoser

IPC: G06F16/583 ,  G06T7/168 ,  G06V10/46 ,  G06V40/16

Abstract: In operating an ecommerce marketplace, pre-generated metadata is used to transform images after a request is received, in real-time, and with low latency. To accomplish the high-speed image transformation, an offline annotation of relevant image features is obtained using machine learning and metadata is stored based upon the results. The metadata is then used to perform the high-speed image transformation at request time. The transformations can include image cropping, adjustment in saturation, contrast, brightness, extracting portions of the image, etc. In one example, the metadata includes a bounding box giving coordinates of how to crop an image so that the image can be cropped without analyzing content or context of the image. Instead, to obtain the coordinates of the bounding box, content and context of the image are analyzed in pre-request processing. In this way, when the request is received, the more difficult and time-consuming processing is already completed.

公开(公告)号：US11586666B2

公开(公告)日：2023-02-21

申请号：US16908464

申请日：2020-06-22

Applicant: Amazon Technologies, Inc.

Inventor： Nikhil Garg ,  Toma Belenzada ,  Sabine Sternig ,  Brad Bowman ,  Zohar Barzelay

IPC: G06F16/583 ,  G06F16/56 ,  G06N5/046 ,  G06F3/04842

Abstract: Various embodiments of systems and methods allow a system to identify subsets of items by mixing and matching identified features in one or more other items. A system can identify features of items in an item database. The system can then calculate “fingerprints” of these features which are vectors describing the characteristics of the features. The system can present a collection of items and a user can select an item of the collection. The user can then select positive features to include in a search and/or negative features to include in the search. The system can then do a search of the database for items that contain features similar to those positive features and do not contain features similar to those negative features. The user can select features through a variety of means.

公开(公告)号：US10747807B1

公开(公告)日：2020-08-18

申请号：US16126868

申请日：2018-09-10

Applicant: Amazon Technologies, Inc.

Inventor： Nikhil Garg ,  Toma Belenzada ,  Sabine Sternig ,  Brad Bowman ,  Zohar Barzelay

IPC: G06F16/583 ,  G06F16/56 ,  G06N5/04 ,  G06F3/0484

Abstract: Various embodiments of systems and methods allow a system to identify subsets of items by mixing and matching identified features in one or more other items. A system can identify features of items in an item database. The system can then calculate “fingerprints” of these features which are vectors describing the characteristics of the features. The system can present a collection of items and a user can select an item of the collection. The user can then select positive features to include in a search and/or negative features to include in the search. The system can then do a search of the database for items that contain features similar to those positive features and do not contain features similar to those negative features. The user can select features through a variety of means.

公开(公告)号：US20210407100A1

公开(公告)日：2021-12-30

申请号：US16912366

申请日：2020-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Sabine Sternig ,  Luitpold Staudigl ,  Pablo Barbachano ,  Thomas Sydney Austin Wallis ,  Muhammad Bilal Javed ,  Michael Donoser

IPC: G06T7/168

Abstract: In operating an ecommerce marketplace, pre-generated metadata is used to transform images after a request is received, in real-time, and with low latency. To accomplish the high-speed image transformation, an offline annotation of relevant image features is obtained using machine learning and metadata is stored based upon the results. The metadata is then used to perform the high-speed image transformation at request time. The transformations can include image cropping, adjustment in saturation, contrast, brightness, extracting portions of the image, etc. In one example, the metadata includes a bounding box giving coordinates of how to crop an image so that the image can be cropped without analyzing content or context of the image. Instead, to obtain the coordinates of the bounding box, content and context of the image are analyzed in pre-request processing. In this way, when the request is received, the more difficult and time-consuming processing is already completed.

公开(公告)号：US20200320118A1

公开(公告)日：2020-10-08

申请号：US16908464

申请日：2020-06-22

Applicant: Amazon Technologies, Inc.

Inventor： Nikhil Garg ,  Toma Belenzada ,  Sabine Sternig ,  Brad Bowman ,  Zohar Barzelay

IPC: G06F16/56 ,  G06F16/583 ,  G06N5/04

Abstract: Various embodiments of systems and methods allow a system to identify subsets of items by mixing and matching identified features in one or more other items. A system can identify features of items in an item database. The system can then calculate “fingerprints” of these features which are vectors describing the characteristics of the features. The system can present a collection of items and a user can select an item of the collection. The user can then select positive features to include in a search and/or negative features to include in the search. The system can then do a search of the database for items that contain features similar to those positive features and do not contain features similar to those negative features. The user can select features through a variety of means.