IDENTIFICATION OF ITEMS DEPICTED IN IMAGES

• US 20090304267A1
• Filed: 02/16/2009
• Published: 12/10/2009
• Est. Priority Date: 03/05/2008
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Gupta, Raghav, Tapley, John, Farraro, Eric J., Grandhi, Roopnath
• Granted Patent: US 9,495,386 B2
• Time in Patent Office: Days
• US Class Current: 382/156
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

In an example embodiment, a method of identifying an item depicted in an image is provided. In this method, the image depicting the item is accessed; in addition, other images and their item identifiers are also accessed. A match of the image with one of the other images is identified. With a match, the image is then associated with an item identifier of the matched image.

Claims

1. A method of identifying an item depicted in an image, the method comprising:

receiving a request to identify the item, the request including the image;

accessing a plurality of other images and a plurality of item identifiers associated with the plurality of other images;

identifying a match of the image with one of the plurality of other images, the one of the plurality of other images being associated with one of the plurality of item identifiers;

associating the image with the one of the plurality of item identifiers based on the match;

accessing a template associated with the one of the plurality of item identifiers; and

transmitting the template in a response to the request.

2. The method of claim 1, wherein the identification of the match of the image comprises comparing the image with the one of the plurality of other images.

3. The method of claim 1, further comprising:

detecting a first edge in the image; and

detecting a second edge in the one of the plurality of other images,

wherein the identification of the match is based on the first edge and the second edge.

4. The method of claim 1, wherein the identification of the match comprises:

converting the image into a first color histogram;

converting the one of the plurality of other images into a second color histogram; and

comparing the first color histogram with the second color histogram.

5. A machine-readable medium that stores instructions, which when performed by a machine, cause the machine to perform operations comprising:

accessing an image depicting an item;

accessing a plurality of other images and a plurality of item identifiers associated with the plurality of other images;

applying an edge detection algorithm to the image;

applying the edge detection algorithm to at least one of the plurality of other images;

identifying a match of the image with the at least one of the plurality of other images, the at least one of the plurality of other images being associated with one of the plurality of item identifiers; and

associating the image with the one of the plurality of item identifiers based on the match, the association identifying the item in the image.

6. The machine-readable medium of claim 5, wherein the operation of identifying the match of the image comprises comparing the image with the at least one of the plurality of other images.

7. The machine-readable medium of claim 5, wherein the operation of identifying the match comprises:

converting the image into a first color histogram;

converting the at least one of the plurality of other images into a second color histogram; and

comparing the first color histogram with the second color histogram to identify a statistical difference between the first color histogram and the second color histogram,

wherein the identification of the match is based on the statistical difference.

8. The machine-readable medium of claim 5, wherein the instructions, when performed by a machine, cause the machine to perform operations further comprising:

receiving a request to identify the item depicted in the image;

accessing a plurality of item data associated with the one of the plurality of item identifiers; and

transmitting a response to the request, the response including the plurality of item data and the one of the plurality of item identifiers.

9. The machine-readable medium of claim 8, wherein the plurality of item data includes a description of the item.

10. The machine-readable medium of claim 8, wherein the plurality of item data includes a location of the item.

11. The machine-readable medium of claim 5, wherein the edge detection algorithm is a Canny edge detector algorithm.

12. A processing system comprising:

at least one processor; and

a memory in communication with the at least one processor, the memory being configured to store an item recognition module that is executable by the at least one processor, the item recognition module having instructions, that when executed by the at least one processor, cause operations to be performed, comprising;

accessing an image depicting an item;

accessing a plurality of other images and a plurality of item data associated with the plurality of other images;

parsing the plurality of item data to identify a plurality of item identifiers;

identifying a match of the image with one of the plurality of other images, the one of the plurality of other images being associated with one of the plurality of item identifiers; and

associating the image with the one of the plurality of item identifiers based on the match.

13. The processing system of claim 12, wherein the item recognition module has instructions that, when executed by the at least one processor, cause operations to be performed, further comprising detecting a first edge in the image and a second edge in the one of the plurality of other images, wherein the identification of the match is based on the detection of the first edge and the second edge.

14. The processing system of claim 12, wherein the item recognition module includes a neural network module that is executable by the at least one processor, wherein the neural network module has instructions that, when executed by the at least one processor, cause operations to be performed, comprising to identifying the match of the image with the one of the plurality of other images based on a learning algorithm.

15. The processing system of claim 12, wherein the plurality of item data includes a plurality of titles included in a plurality of item listings.

16. The processing system of claim 12, wherein the plurality of item data includes a plurality of descriptions included in a plurality of item listings.

17. The processing system of claim 12, wherein the operation of identifying the match comprises:

converting the image into a first color histogram;

converting the one of the plurality of other images into a second color histogram;

comparing the first color histogram with the second color histogram to identify a statistical similarity between the first color histogram and the second color histogram,

wherein the identification of the match is based on the statistical similarity.

18. An apparatus for identifying an item depicted in an image, the apparatus comprising:

a request handler module to receiving a request to identify the item, the request including the image, and to further access a plurality of other images and a plurality of item identifiers associated with the plurality of other images;

an image recognition module to identify a match of the image with one of the plurality of other images, the one of the plurality of other images being associated with one of the plurality of item identifiers, and to associate the image with the one of the plurality of item identifiers based on the match, the association identifying the item in the image; and

an item recognition module to access a template associated with the one of the plurality of item identifiers and to transmit the template in a response to the request.

19. An apparatus for identifying an item depicted in an image, the apparatus comprising:

a first means for accessing a request to identify the item, the request including the image, and for accessing a plurality of other images and a plurality of item identifiers associated with the plurality of other images;

a second means for identifying a match of the image with one of the plurality of other images, the one of the plurality of other images being associated with one of the plurality of item identifiers, and to associate the image with the one of the plurality of item identifiers based on the match, the association identifying the item in the image; and

a third means for accessing a template associated with the one of the plurality of item identifiers and for transmitting the template in a response to the request.

20. The apparatus of claim 19, wherein the plurality of other images are submitted by a plurality of users.