Flaw analysis of images

Patent metadata

Field	Value
Publication number	US-2017193594-A1
Application number	US-201514986486-A
Country	US
Kind code	A1
Filing date	Dec 31, 2015
Priority date	Dec 31, 2015
Publication date	Jul 6, 2017
Grant date	—

Abstract

Systems and methods are disclosed to provide flaw accentuation to an image in an e-commerce online marketplace. In some embodiments, a method may include receiving at an online marketplace, from a seller through the Internet, an image of an item being listed for sale at the online marketplace and text related to the item being listed for sale; determining that the item includes a flaw based on the text related to the item being listed for sale or the image of the item; creating a flaw accentuation to the image; and creating a listing in the online marketplace for the item that includes the image and the flaw accentuation to the image.

First claim

1 . A method for providing flaw accentuation to an image of an item for sale in an e-commerce online marketplace, the method comprising:
receiving at one or more servers that host an online marketplace, an image of an item being listed for sale at the online marketplace and text that describes the item from a seller through the Internet; determining, by the one or more servers, that the item includes a flaw based on the text, the flaw including damage to the item; in response to a determination that the item includes the flaw, creating, by the one or more servers, a flaw accentuation to the image that modifies the image such that the flaw stands out; further creating, by the one or more servers, a listing in the online marketplace for the item, the listing including the image and the flaw accentuation to the image; and in response to a search query, displaying, by the one or more servers, the listing for the item.

2 . The method according to claim 1 , wherein creating the flaw accentuation comprises applying a digital image filter to the image.

3 . The method according to claim 1 , wherein:
the determining that the item includes the flaw includes determining a flaw type based on the text; and the method further comprises determining a flaw accentuation type based on the flaw type.

4 . The method according to claim 3 , wherein determining the flaw accentuation type based on the flaw type further comprises looking up the flaw accentuation type in a database that correlates flaw accentuation type with item type.

5 . The method according to claim 1 , wherein the determining that the item includes the flaw includes determining whether the text includes a term selected from the list consisting of scratch, chip, dent, fold, crack, water damage, stain, discoloration, fading, hole, ink stain, and gouge.

6 . The method according to claim 1 , wherein:
the text related to the item includes text indicating an item type; the determining that the item includes the flaw includes looking up in a database one or more specific flaw types that are correlated with the item type in the database; and the flaw accentuation is created based on the one or more specific flaw types.

7 . The method according to claim 1 , wherein the determining that the item includes the flaw includes determining whether the image is an altered image.

8 . (canceled)

9 . The method according to claim 2 , wherein the digital image filter comprises a digital image filter selected from the list consisting of a contrast accentuation digital image filter, a color inversion digital image filter, a spatial domain digital image filter, detecting digital image filters, an unsharp digital image filter, a Laplacian digital image filter, a Gaussian digital image filter, and a smoothing digital image filter.

10 . The method according to claim 1 , wherein the creating the listing includes creating a listing in the online marketplace for the item that includes the image and a second image that includes the flaw accentuation to the image.

11 . One or more non-transitory computer-readable media storing one or more programs that are configured, when executed, to cause one or more processors to execute the method as recited in claim 1 .

12 . A method for determining whether a digital display includes a flaw, the method comprising:
receiving, at a server that hosts an online marketplace, listing information from a seller for listing an item for sale in the online marketplace; determining, by the server, that the item includes a digital display; providing, by the server, a sample image to the seller; receiving, by the server, a digital photograph of the item displaying the sample image on the digital display; comparing, by the server, the received digital photograph with the sample image to determine a difference between the digital photograph and the sample image; in response to the difference being greater than a threshold value, determining, by the server, that the digital display includes a flaw; and presenting, by the server, an item listing in the online marketplace for the digital display, the item listing including the flaw presented such that the flaw stands out.

13 . The method according to claim 12 , wherein providing a sample image to the seller includes at least one of the following selected from the list consisting of:
emailing the sample image to the seller; and providing a link pointing to the sample image located at a network location.

14 . The method according to claim 12 , wherein:
the listing information comprises text describing the item; and determining that the item includes a digital display further comprises determining whether the text describing the item includes keywords associated with an item that includes a digital display.

15 . The method according to claim 12 , wherein:
the listing information comprises an item type; and determining that the item includes a digital display further comprises determining whether the item type corresponds with item types having a digital display.

16 . (canceled)

17 . One or more non-transitory computer-readable media storing one or more programs that are configured, when executed, to cause one or more processors to execute the method as recited in claim 12 .

18 . An online marketplace system comprising:
a network interface; a memory; and a processor configured to:
receive an image from a seller through the network interface, the image being an image of an item being listed for sale at the online marketplace;
determine that the image has been altered; and
in the event that it is determined that the image has been altered:
send a request to the seller through network interface for an unaltered image; or
create a listing in the online marketplace for the item that includes the image and demoting a ranking of the created listing to change an order of items displayed to a buyer in response to a search request from the buyer.

19 . The system according to claim 18 , wherein determining that the image has been altered is based on metadata associated with the image.

20 . The system according to claim 18 , wherein determining that the image has been altered is based on results of a forensic analysis and/or digital image filter.

21 . The system according to claim 18 , wherein determining that the image has been altered further comprises:
sending the image to forensic analysis service via the Internet; and receiving a forensic analysis from the forensic analysis service.

22 . The method according to claim 12 , wherein the comparing is performed pixel by pixel or region by region.

Assignees

• Ebay Inc

Inventors

• Glasgow Dane
• Eramian David
• Godsey Sandy
• VanWinkle Justin

Classifications

• G06F18/24

  Classification techniques · CPC title

• G06Q30/0619 Primary

  Neutral agent · CPC title

• G06Q30/0643 Primary

  graphically representing goods, e.g. 3D product representation · CPC title

• G06T7/00

  Image analysis · CPC title

• G06Q30/0609

  Qualifying participants for shopping transactions (payment transaction verification G06Q20/401) · CPC title