Systems and methods for automated object recognition

Patent metadata

Field	Value
Publication number	US-12282833-B2
Application number	US-202318460014-A
Country	US
Kind code	B2
Filing date	Sep 1, 2023
Priority date	Jun 23, 2016
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

A method for recognizing an object in a video stream may include receiving a video stream comprising a plurality of video frames from a video source. The method may also select at least one video frame from the video frames according to a frame selection rate. The method may also partition the selected video frame into a first plurality of image blocks, and recognize, out of the first plurality of image blocks, a second plurality of image blocks which comprise an image of an object, the recognition being based on an image recognition parameter determined by a machine-learning algorithm. The method may also determine that at least one of the second plurality of image blocks corresponds to the object based on a likelihood metric, the likelihood metric being determined by the processor based on at least the frame selection rate, and display, on a display, information identifying the object.

First claim

What is claimed is:

1. A system for providing an object list based on objects identified in a video stream, comprising:
a memory storing instructions; and
a processor configured to execute the stored instructions to:
select a video frame from the video stream based on a frame selection value;
identify within one or more image blocks of the selected video frame, a region comprising an image of one or more objects, based on a machine learning model for determining regions characterized by an image recognition parameter, wherein the machine learning model is further configured to detect information related to the one or more objects, wherein the information includes descriptions of the one or more objects, and wherein the descriptions of the one or more objects are related to a monetary value associated with the one or more objects;
update the object list comprising the one or more objects based on a likelihood metric indicating that the region is associated with the one or more objects; and
generate for display, on a user interface, information related to the object list.

2. The system of claim 1 , wherein the processor is further configured to:
identify, within the region, one or more descriptive elements indicating a value associated with the one or more objects.

3. The system of claim 1 , wherein updating the object list further comprises:
identifying a first descriptive element within the region indicating a user identifier of a user;
identifying a second descriptive element within the region indicating a value associated with the one or more objects; and
updating the object list using the user identifier and the value such that the object list i is associated with the user identifier and (ii) indicates the value associated with the one or more objects.

4. The system of claim 3 , wherein the object list is transactionally-related to an account of the user.

5. The system of claim 1 , wherein the processor is further configured to execute the stored instructions to:
compare the likelihood metric to a predetermined threshold; and
determine that the identified region is associated with the one or more objects when the likelihood metric exceeds or equals the predetermined threshold.

6. The system of claim 1 , wherein the processor is further configured to execute the stored instructions to store the region comprising the image of the one or more objects in a database.

7. The system of claim 1 , wherein the processor is further configured to execute the stored instructions to determine the likelihood metric based on information identifying the one or more objects.

8. A computer-implemented method for recognizing an object in a video stream, comprising:
selecting a video frame from the video stream based on a frame selection value;
identifying within one or more image blocks of the selected video frame, a region comprising an image of one or more objects, based on a machine learning model for determining regions characterized by an image recognition parameter, wherein the machine learning model is further configured to detect information related to the one or more objects, wherein the information includes descriptions of the one or more objects, and wherein the descriptions of the one or more objects are related to a monetary value associated with the one or more objects;
updating an object list comprising the one or more objects based on a likelihood metric indicating that the region is associated with the one or more objects; and
generating for displaying, on a user interface, information related to the object list.

9. The computer-implemented method of claim 8 , further comprising:
identifying, within the region, one or more descriptive elements indicating a value associated with the one or more objects.

10. The computer-implemented method of claim 8 , wherein updating the object list further comprising:
identifying a first descriptive element within the region indicating a user identifier of a user;
identifying a second descriptive element within the region indicating a value associated with the one or more objects; and
updating the object list using the user identifier and the value such that the object list (i) is associated with the user identifier and (ii) indicates the value associated with the one or more objects.

11. The computer-implemented method of claim 10 , wherein the object list is transactionally-related to an account of the user.

12. The computer-implemented method of claim 8 , further comprising:
receiving a user input; and
adjusting a frame selection rate based on the user input.

13. The computer-implemented method of claim 8 , further comprising:
determining a video quality of the video stream; and
determining whether the video quality meets a predetermined threshold.

14. The computer-implemented method of claim 8 , further comprising:
determining a pixel count for a partition of the video frame; and
determining the one or more image blocks based on the pixel count.

15. The computer-implemented method of claim 8 , further comprising:
retrieving a characteristic about a product; and
determining the image recognition parameter based on the characteristic.

16. The computer-implemented method of claim 8 , further comprising:
receiving an input from a media device; and
determining the image recognition parameter based on the input.

17. A non-transitory computer-readable medium storing instructions which, when executed, cause at least one processor to perform operations for recognizing an object in a video stream, the operations comprising:
selecting a video frame from the video stream based on a frame selection value;
identifying within one or more image blocks of the selected video frame, a region comprising an image of one or more objects, based on a machine learning model for determining regions characterized by an image recognition parameter;
updating an object list comprising the one or more objects based on a likelihood metric indicating that the region is associated with the one or more objects, wherein updating the object list further comprises:
identifying a first descriptive element within the region indicating a user identifier of a user;
identifying a second descriptive element within the region indicating a value associated with the one or more objects; and
updating the object list using the user identifier and the value such that the object list (i) is associated with the user identifier and (ii) indicates the value associated with the one or more objects; and
generating for displaying, on a user interface, information related to the object list.

18. The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:
identifying, within the region, one or more descriptive elements indicating a value associated with the one or more objects.

19. The non-transitory computer-readable medium of claim 17 ,
wherein the object list is transactionally-related to an account of the user.

20. The non-transitory computer-readable medium of claim 17 , wherein the machine learning model is further configured to detect information related to the one or more objects, and wherein the information includes information related to a monetary value associated with the one or more objects.

Assignees

• Capital One Services Llc

Inventors

• Jouhikainen Hannes Mikael
• Jacobs Drew

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06V10/443

  by matching or filtering · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/82

  using neural networks · CPC title