Identification of product attributes

• US 8,787,707 B1
• Filed: 06/29/2011
• Issued: 07/22/2014
• Est. Priority Date: 06/29/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Steves, Andrea C., Lehmann, Sebastian
• Primary Examiner(s): Do, Anh
• Application Number:
  US13/171,647
• Time in Patent Office: 1,119 Days
• Field of Search: 382/321, 382/312, 382/181, 382/190, 382/182, 382/114, 382/115, 382/118, 358/442, 358/443, 715/700, 715/716, 707/E17.02, 725/40, 725/94, 725/87, 725/110, 709/217, 713/176
• US Class Current: 382/321
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0254 based on statistics

Abstract

Disclosed are various embodiments for performing an analysis on images of a product packaging. Capture of at least one image of at least one side of a packaging in initiated. An image analysis is performed on the at least one image. Product attributes are detected based at least upon the at least one image analysis and associated with the product in a data store.

Claims

1. A non-transitory computer-readable medium embodying a program executable in a computing device, the program comprising:

code that receives at least one image corresponding to at least one side of a packaging associated with a product;

code that performs an optical character recognition algorithm on the at least one image, the optical character recognition algorithm extracting text from the at least one image;

code that associates the extracted text with an inventory item in a data store;

code that performs at least one image recognition algorithm on the at least one image, the at least one image recognition algorithm configured to match at least one logo extracted from the at least one image with a known image corresponding to a product feature;

code that associates the product feature with the inventory item in the data store; and

code that assigns the product to a product category associated with at least one of the product feature and the extracted text.

2. A system, comprising:

at least one image capture device;

at least one computing device in communication with the at least one image capture device; and

a product image analysis application executable in the at least one computing device, the product image analysis application comprising;

logic that initiates capture of at least one image of at least one side of a packaging of a product;

logic that performs at least one image analysis on the at least one image;

logic that detects at least one product attribute associated with the product based at least upon the at least one image analysis; and

logic that stores the at least one product attribute in an inventory record associated with the product.

3. The system of claim 2, wherein the product image analysis application further comprises logic that associates the product with a product category associated with the at least one product attribute.

4. The system of claim 3, wherein the product image analysis application further comprises:

logic that generates a new product category corresponding to the at least one product attribute; and

logic that associates the product with the new product category.

5. The system of claim 2, wherein the at least one image capture device is positioned on a movable arm, and the logic that initiates capture of at least one image of at least one side of a packaging of the product further comprises logic that initiates movement of the movable arm about the product.

6. The system of claim 2, wherein the at least one image capture device further comprises a plurality of image capture devices, each of the image capture devices positioned in one of a plurality of axes about the product.

7. The system of claim 6, wherein the plurality of image capture devices further comprises three image capture devices, wherein each of the image capture devices is respectively positioned in an x-axis, a y-axis and a z-axis.

8. The system of claim 6, wherein the plurality of image capture devices further comprises six image capture devices, wherein two of the image capture devices are respectively positioned in opposing positions in an x-axis, a y-axis and a z-axis.

9. The system of claim 7, wherein the logic that initiates capture of at least one image of at least one side of a packaging of a product further comprises:

logic that initiates capture of a first series of images by the plurality of image capture devices;

logic that initiates rotation of the packaging about at least two of the axes; and

logic that initiates capture of a second series of images by the plurality of image capture devices.

10. The system of claim 2, wherein the logic that performs at least one image analysis on the at least one image further comprises:

logic that performs an optical character recognition algorithm on the at least one image, the optical character recognition algorithm identifying at least one word appearing on the packaging; and

logic that associates the at least one word with the at least one product attribute.

11. The system of claim 2, wherein the logic that performs at least one image analysis on the at least one image further comprises:

logic that performs an image recognition algorithm on the at least one image, the image recognition algorithm matching an image on the packaging with a logo image; and

logic that associates the logo image with the at least one product attribute.

12. The system of claim 11, wherein the logo image is associated with a known product attribute, and the logic that performs at least one image analysis on the at least one image further comprises:

logic that designates the known product attribute as the at least one product attribute.

13. The system of claim 12, wherein the known product attribute is at least one of:

an ingredient associated with the product, a third party product certification, a brand, or contents of the packaging.

14. A method, comprising the steps of:

initiating, in at least one computing device, capture of at least one image of at least one side of a packaging of a product by at least one image capture device;

performing, in the at least one computing device, at least one image analysis on the at least one image;

detecting, in the at least one computing device, at least one product attribute associated with the product based at least upon the at least one image analysis; and

storing, in the at least one computing device, the at least one product attribute in an inventory record associated with the product.

15. The method of claim 14, wherein the step of performing at least one image analysis on the at least one image further comprises:

determining, in the at least one computing device, whether the packaging can be shipped without additional shipment packaging; and

designating, in the at least one computing device, the at least one product attribute as a shipment safe packaging attribute.

16. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises the steps of:

identifying, in the at least one computing device, a plurality of attributes based at least upon the at least one image analysis; and

generating, in the at least one computing device, a vote corresponding to whether the packaging can be shipped without additional shipment packaging based at least upon the plurality of attributes.

17. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises:

initiating, in the at least one computing device, capture of a plurality of opposing images from an image capture device oriented in an x-axis, y-axis and z-axis; and

determining, in the at least one computing device, whether each of plurality of the opposing images reflects that the packaging is rectangular in each of the opposing images.

18. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises:

determining, in the at least one computing device, whether at least a portion of the packaging is at least one of transparent or translucent; and

designating, in the at least one computing device, the at least one product attribute as a non-shipment safe packaging attribute when at least a portion of the packaging is at least one of transparent or translucent.

19. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises:

determining, in the at least one computing device, whether at least a portion of the packaging comprises a plurality of perforations; and

designating, in the at least one computing device, the at least one product attribute as a non-shipment safe packaging attribute when the at least a portion of the packaging comprises a plurality of perforations.

20. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises:

performing, in the at least one computing device, an optical character recognition technique on the at least one image;

extracting, in the at least one computing device, text from the at least one image;

determining, in the at least one computing device, whether the text reflects that the packaging is not shipment safe; and

designating, in the at least one computing device, the at least one product attribute as a non-shipment safe packaging attribute.

21. The method of claim 20, wherein the step of determining whether the text reflects that the packaging is not shipment safe further comprises the step of determining whether the text corresponds to fragile contents of the packaging.

22. The method of claim 20, wherein the step of determining whether the text reflects that the packaging is not shipment safe further comprises the steps of:

determining, in the at least one computing device, whether the text corresponds to an edge crush test rating;

determining, in the at least one computing device, whether the edge crush test rating is below a predefined threshold; and

designating, in the at least one computing device, the at least one product attribute as a non-shipment safe packaging attribute when the edge crush test rating is below the predefined threshold.

23. The method of claim 15, wherein the step of determining whether the packaging can be shipped without additional shipment packaging further comprises:

performing, in the at least one computing device, an image recognition technique on the at least one image;

extracting, in the at least one computing device, at least one logo from the at least one image; and

determining, in the at least one computing device, whether the at least one logo corresponds to a known image that corresponds to a non-shipment safe designation.

24. The method of claim 23, wherein known image is at least one of:

a logo corresponding to a fragile product and a logo corresponding to a breakable product.