Method, medium, and system for creating a filtered image set for a product

• US 8,762,218 B1
• Filed: 12/20/2010
• Issued: 06/24/2014
• Est. Priority Date: 12/29/2006
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Latin-Stoermer, Toby R., Bhaktwatsalam, Abhoy, Chung, Randy C., Kan, Chi Ming
• Primary Examiner(s): ZIMMERMAN, MATTHEW E
• Application Number:
  US12/973,841
• Time in Patent Office: 1,282 Days
• Field of Search: 705/26.1, 705/27.1, 382/164, 382/165, 382/224
• US Class Current: 705/26.1
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: Y10S 707/948 Product or catalog
• CPC Class Codes: Y10S 707/962 Entity-attribute-value

Abstract

Systems and methods for collecting, selecting, and displaying an image or image set in a network based environment are described. The systems and methods can collect multiple images for any given item from multiple sources, select a desired image (or set of images) that best depicts that item, and then display that selected image (or image set) in the network based environment. The desired image (or image set) that best depicts the item can be selected using any number or combination of pre-selected criteria. By using the pre-selected criteria, the process needs no manual intervention, and can therefore be automated or semi-automated to save both time and cost.

Claims

1. A computer-implemented method for selecting a set of images for display, the method comprising:

creating, using a computer processor, a target image set for a product by analyzing images in a first set of images based on one or more image metrics, wherein the first set of images includes images of the product from multiple sellers of the product;

determining that the target image set portrays the product, wherein the determination is based on an analysis of at least one attribute of the product included in each image of the target image set;

subsequent to the determination, receiving a request including at least one specified selection criteria for a filtered image set of the product;

creating, using a computer processor, the filtered image set of the product by selecting images from the target image set based at least in part on the at least one specified selection criteria and an analysis of one or more pixels in one or more images of the target image set; and

making the filtered image set available for display on a network.

2. The computer-implemented method of claim 1 further comprising automatically displaying the target image set.

3. The computer-implemented method of claim 1 further comprising automatically collecting criteria for creating the target image set and ranking the collected criteria before using the criteria to create the target image set.

4. The computer-implemented method of claim 1 further comprising allowing manual verification that the filtered image set satisfies an identifiable aspect depicted in the plurality of images.

5. The computer-implemented system of claim 1 further comprising automatically filtering the target image set for images that fail to meet a threshold requirement.

6. The computer-implemented method of claim 1, wherein creating the target image set includes determining a primary image and a plurality of secondary images.

7. The computer-implemented method of claim 6, wherein the plurality of secondary images depict two or more perspectives including at least one of a top view, a front view, and a side view of the selected item.

8. The computer-implemented method of claim 1, wherein the first set of images have been analyzed at least based on at least one of pixel analysis, size, granularity, and color.

9. The computer-implemented method of claim 1, wherein the at least one specified selection criteria includes at least one of pixel analysis criteria, size criteria, granularity criteria, and color criteria.

10. The computer-implemented method of claim 1, wherein creating the filtered image set of the product by selecting images from the target image includes determining whether more than a threshold number of pixels in one or more images depict a substantially similar color.

11. The computer-implemented method of claim 1, wherein creating the filtered image set of the product by selecting images from the target image includes determining whether a background in two or more images depicts a substantially similar color.

12. A computer-implemented system for selecting images for display, the system comprising:

a data store for storing a plurality of images from multiple sources; and

a computer processor in communication with said data store that is operative to;

create a target image set for a product by analyzing images in a first set of images based on one or more image metrics, wherein the first set of images includes images of the product from multiple sellers of the product;

determine that the target image set portrays the product, wherein the determination is based on an analysis of at least one attribute of the product included in each image of the target image set;

subsequent to the determination, receive a request including at least one specified selection criteria for a filtered image set of the product;

create the filtered image set of the product by selecting images from the target image set based at least in part on the at least one specified selection criteria and an analysis of one or more pixels in one or more images of the target image set; and

make the filtered image set available for display on a network.

13. The computer-implemented system of claim 12, wherein the computer processor is further operative to automatically collect criteria for creating the target image set and rank the collected criteria before using the criteria to create the target image set.

14. The computer-implemented system of claim 12, wherein the computer processor is further operative to allow manual verification that the filtered image set satisfies an identifiable aspect depicted in the plurality of images.

15. The computer-implemented system of claim 12, wherein the target image set includes a primary image and a plurality of secondary images.

16. The computer-implemented system of claim 12, wherein the at least one specified selection criteria includes at least one of pixel analysis criteria, size criteria, granularity criteria, and color criteria.

17. The computer-implemented system of claim 12, wherein the computer processor is further operative to determine whether more than a threshold number of pixels in one or more images depict a substantially similar color.

18. A non-transitory computer-readable medium containing computer executable code for selecting images to display, wherein the computer executable code when executed by a computing apparatus causes the computing apparatus to:

create a target image set for a product by analyzing images in a first set of images based on one or more image metrics, wherein the first set of images includes images of the product from multiple sellers of the product;

determine that the target image set portrays the product, wherein the determination is based on an analysis of at least one attribute of the product included in each image of the target image set;

subsequent to the determination, receive a request including at least one specified selection criteria for a filtered image set of the product;

create the filtered image set of the product by selecting images from the target image set based at least in part on the at least one specified selection criteria and an analysis of one or more pixels in one or more images of the target image set; and

make the filtered image set available for display on a network.

19. The computer readable medium of claim 18, wherein the computer executable code further causes the computing apparatus to allow manual verification that the filtered image set satisfies an identifiable aspect of the depicted item.

20. The computer readable medium of claim 18, wherein the first set of images have been analyzed at least based on at least one of pixel analysis, size, granularity, and color.

21. The computer readable medium of claim 18, wherein the computer executable code further causes the computing apparatus to determine whether a background in two or more images depict a substantially similar color.