Automated and periodic updating of item images data store

Patent metadata

Field	Value
Publication number	US-11042787-B1
Application number	US-201916415390-A
Country	US
Kind code	B1
Filing date	May 17, 2019
Priority date	Jun 27, 2013
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

Abstract

This disclosure describes a system for automatically updating item image information stored in an item images data store and used for processing captured images to identify items represented in those images. In one implementation, once an identity of an item has been verified, captured images of that item are associated with the item and stored in the item images data store. As a result, the item images data store is updated each time an image of the item is captured and the identity of the item is verified.

First claim

What is claimed is:

1. A computing system, comprising:
one or more processors; and
a memory storing program instructions that when executed by the one or more processors cause the one or more processors to at least:
determine an identity of an item received into a materials handling facility;
obtain at least one image of the item as the item is received into the materials handling facility;
determine, based at least in part on a processing of the at least one image, that the item cannot be identified from the processing of the at least one image;
in response to a determination that the item cannot be identified from the processing of the at least one image:
create an association between at least one of the at least one image or item image information corresponding to the at least one image and the item; and
store at least one of the at least one image, the association, or the item image information in an item image data store such that a data set that includes stored item image information corresponding to the item is increased to include at least one of the at least one image, the association, or the item image information.

2. The computing system of claim 1 , wherein the program instructions that when executed by the one or more processors to cause the one or more processors to determine the identity of the item further include instructions that when executed by the one or more processors further cause the one or more processors to at least:
receive from an associate at the material handling facility an identifier corresponding to the item.

3. The computing system of claim 2 , wherein the identifier is at least one of a bar code identifier.

4. The computing system of claim 1 , wherein:
receive of the item into the materials handling facility includes one or more stages including one or more of identification of the item, segmentation of the item from a plurality of items for storage in the materials handling facility, or preparation of the item for storage in the materials handling facility.

5. The computing system of claim 1 , wherein the program instructions that when executed by the one or more processors further cause the one or more processors to at least:
process the at least one image to determine one or more of the identity of the item, a plurality of features of the image that are representative of the item, or an arrangement of the plurality of features.

6. The computing system of claim 1 , wherein the program instructions that when executed by the one or more processors further cause the one or more processors to at least:
determine a second identity of a second item received into the materials handling facility;
obtain a second image of the second item as the item is received into the materials handling facility;
determine, based at least in part on a processing of the second image, that the second item can be identified from the processing of the at least one image;
determine that an image correlation score indicative of a correlation between the second item and the second image is below a threshold;
in response to a determination that the image correlation score is below the threshold:
create a second association between at least one of the second image or second item image information corresponding to the second image and the second item; and
store at least one of the second image, the second association, or the second item image information in the item image data store such that a second data set that includes second stored item image information corresponding to the second item is increased to include at least one of the second image, the second association, or the second item image information.

7. The computing system of claim 1 , wherein the program instructions that when executed by the one or more processors further cause the one or more processors to at least:
determine a second identity of a second item received into the materials handling facility;
obtain second image of the second item as the item is received into the materials handling facility;
determine, based at least in part on a processing of the second image, that the second item can be identified from the processing of the at least one image;
determine that an image correlation score indicative of a correlation between the second item and the second image exceeds a threshold; and
in response to a determination that the image correlation score exceeds the threshold, discard the second image without updating the item image data store or a second data set corresponding to the second item.

8. A computer-implemented method, comprising:
determining an identity of an item received into a materials handling facility;
obtaining an image of the item as the item is received into the materials handling facility;
determining, based at least in part on a processing of the image, that the item can be identified from the processing of the image;
determining that an image correlation score indicative of a correlation between the item and the image is below a threshold;
in response to determining that the image correlation score is below the threshold:
creating an association between at least one of the image or item image information corresponding to the image and the item; and
storing at least one of the image, the association, or the item image information in an item image data store such that a data set that includes stored item image information corresponding to the item is increased to include at least one of the image, the association, or the item image information.

9. The computer-implemented method of claim 8 , further comprising:
processing the image to determine one or more of the identity of the item, a plurality of features of the image that are representative of the item, or an arrangement of the plurality of features.

10. The computer-implemented method of claim 9 , wherein the plurality of features include one or more of a shape of the item, a color of the item, a label on the item, a logo on the item, a wording on the item, a symbol on the item, a character of the item, a word on the item, a number on the item, a texture of the item, a gradient of the item, a reflectivity of the item, or an edge of the item.

11. The computer-implemented method of claim 9 , wherein processing the image includes:
converting the image to a grey-scale to determine the plurality of features.

12. The computer-implemented method of claim 9 , wherein the arrangement of the plurality of features includes one or more of a two dimensional relationship between each of the plurality of features or a three dimensional relationship between each of the plurality of features.

13. The computer-implemented method of claim 9 , wherein determining that the item can be identified from the processing of the image includes:
comparing the arrangement of the plurality of features with the item image information stored in the item image data store.

14. A computing system, comprising:
one or more processors; and
a memory storing program instructions that when executed by the one or more processors cause the one or more processors to at least:
determine an identity of an item received into a materials handling facility;
obtain an image of the item;
determine, based at least in part on a processing of the image, that the item cannot be identified from the image;
in response to a determination that the item cannot be identified from the image:
create an association between at least one of the image or item image information corresponding to the image and the item; and
store at least one of the image, the association, or the item image inform

Assignees

• Amazon Tech Inc

Inventors

• Kumar Dilip
• Ducrou Jon Robert
• Xavier Joseph
• Palaniappan Ramanathan
• Goldstein Michel Leonard
• Brundage Michael Lee

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06V10/751 Primary

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• G06K9/6267 Primary

  Physics · mapped topic