US 11,960,569 B2Granted

System and method for refining an item identification model based on feedback

Assignee7-Eleven, Inc.

InventorsSumedh Vilas Datar, Sailesh Bharathwaaj Krishnamurthy, Shantanu Yadunath Thakurdesai, Shahmeer Ali Mirza

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system for refining an item identification model detects a triggering event at a platform, where the triggering event corresponds to a user placing the item on a platform. The system captures images of the item. The system extracts a set of features from at least one of the images. The system identifies the item based on the set of features. The system receives an indication that the item is not identified correctly. The system receives an identifier of the item. The system identifies the item based on the identifier of the item. The system feeds the identifier of the item and the images to the item identification model. The system retrains the item identification model to learn to associate the item to the images. The system updates the set of features based on the determined association between the item and the images.

Claims20

Dependent claims

A system for refining an item identification model, comprising:

a plurality of cameras, wherein each camera is configured to capture one or more images of at least a portion of a platform;
a memory, operable to store an item identification model, wherein the item identification model is configured to identify an item based at least in part upon an image of the item;
and
a processor, operably coupled with the memory, and configured to:
detect a triggering event at the platform, wherein the triggering event corresponds to a user placing the item on the platform;
capture one or more images of the item using the plurality of cameras, wherein the one or more images are captured from one or more angles;
extract a set of features from at least one of the one or more images, wherein each of the set of features corresponds to a physical attribute of the item;
identify the item based at least in part upon the set of features;
receive an indication that the item is not identified correctly;
receive an identifier of the item;
identify the item based at least in part upon the identifier of the item;
feed the identifier of the item and the one or more images to the item identification model;
retrain the item identification model to learn to associate the item to the one or more images;
and
update the set of features based at least in part upon the determined association between the item and the one or more images.

12 more elements

A method for refining an item identification model, comprising:

detecting a triggering event at a platform, wherein the triggering event corresponds to a user placing the item on the platform;
capturing one or more images of the item using a plurality of cameras, wherein the one or more images are captured from one or more angles;
extracting a set of features from at least one of the one or more images, wherein each of the set of features corresponds to a physical attribute of the item;
identifying the item based at least in part upon the set of features;
receiving an indication that the item is not identified correctly;
receiving an identifier of the item;
identifying the item based at least in part upon the identifier of the item;
feeding the identifier of the item and the one or more images to the item identification model;
retraining the item identification model to learn to associate the item to the one or more images;
and
updating the set of features based at least in part upon the determined association between the item and the one or more images.

8 more elements

A non-transitory computer-readable medium storing instructions that when executed by a processor cause the processor to:

detect a triggering event at a platform, wherein the triggering event corresponds to a user placing the item on the platform;
capture one or more images of the item using a plurality of cameras, wherein the one or more images are captured from one or more angles;
extract a set of features from at least one of the one or more images, wherein each of the set of features corresponds to a physical attribute of the item;
identify the item based at least in part upon the set of features;
receive an indication that the item is not identified correctly;
receive an identifier of the item;
identify the item based at least in part upon the identifier of the item;
feed the identifier of the item and the one or more images to the item identification model;
retrain the item identification model to learn to associate the item to the one or more images;
and
update the set of features based at least in part upon the determined association between the item and the one or more images.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/455,896Filed 19 Nov 2021 · continuation in part
Priority: 29 Jun 2021
Published: US 2022/0414399 A129 Dec 2022
Granted: 16 Apr 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification23 codes

G06F 18/2148
Generating training patterns; Bootstrap methods, e.g. bagging or boosting: characterised by the process organisation or structure, e.g. boosting…
G06V 20/52
Context or environment of the image: surveillance or monitoring of activities, e.g. for recognising suspicious objects
G01G 21/22
Details of weighing apparatus: weigh pans or other weighing receptacles; Weighing platforms
G01G 23/36
Indicating devices, e.g. for remote indication; Recording devices; Scales, e.g. graduated: indicating the weight by electrical means, e.g. using…

Family

Application17/362,261Parent of this continuation-in-part · filed 29 Jun 2021
US 2022/0414399 A1Pre-grant publication · published 29 Dec 2022
US 11,887,332 B2Related patent
US 2022/0414924 A1Published application
US 11,960,569 B2This patent

From the US filing history. Foreign family members aren’t listed.