METHOD AND APPARATUS FOR IMAGE RECOGNITION SERVICES

• US 20090240735A1
• Filed: 03/05/2009
• Published: 09/24/2009
• Est. Priority Date: 03/05/2008
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Olson, Jeffrey, Golovnya, Denis, Sundaresan, Neelakantan, Gupta, Raghav, Grandhi, Roopnath
• Granted Patent: US 10,936,650 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions

Abstract

A system to provide image processing services responsive to requests including image data includes a system layer that forwards a request to an image application processing interface. Image processing provides an image comparison, barcode recognition, and optical character recognition. The image processing compares the image data to products in a database in order to identify a matching product. The system layer receives the matching information and forwards to a user.

Claims

1. A method, comprising:

executing instructions on a computing platform to;

receive a request for at least one of a plurality of image processing services, the request including image data;

forward the request, including the image data, through an interface to the at least one image processing service;

receive a response from the at least one image processing service; and

forwarding the response, including product information, for display on a computing device.

2. The method of claim 1, wherein the at least one image processing service compares the image data to a database of items.

3. The method of claim 2, wherein the at least one image processing service compares at least one characteristic of the image data to database items, the at least one characteristic comprising one of color, shape or texture.

4. The method of claim 2, wherein the items are products for sale, and the method is further to:

determine a category associated with the image data;

wherein the at least one image processing service compares the image data with the database of items in the category.

5. The method of claim 2, wherein the image data is a barcode.

6. The method of claim 1, wherein the at least one image processing service performs optical character recognition of the image data.

7. The method of claim 1, wherein the request is received as an email message, wherein a command is in the email message.

8. The method of claim 7, wherein the command is included in the subject line of the email message.

9. The method of claim 7, wherein the command is included in the body of the email message.

10. The method of claim 7, wherein the command is to compare image data to the database of items.

11. The method of claim 1, wherein the request is received as an HTTP message.

12. The method of claim 1, wherein the at least one image processing service is a fraud detection service, wherein the image data is compared to product information to identify an inconsistency.

13. The method of claim 12, wherein the response is a notification of an inconsistency between the image data and valid product information.

14. The method of claim 13, wherein the image data resulting in an inconsistency is stored in a fraud records database, wherein the fraud detection service compares received image data to image data stored in the fraud records database.

15. A system including:

a receiver module to receive image processing requests for at least one of a plurality of image processing services, the request including image data;

a communication module to;

forward the requests to the at least one image processing service,

receive a response from the at least one image processing service; and

forward the response, including product information, for display on a computing device.

16. The system as in claim 15, wherein the communication module is to receive email messages, and wherein the request is an email message.

17. The system as in claim 16, wherein the communication module is further to parse email messages to extract the image data.

18. The system as in claim 15, further comprising:

a bulk uploader for receiving a batch of requests; and

a logic module to implement the at least one image processing service for the batch of requests.

19. The system as in claim 17, wherein the logic module is to implement any of the plurality of image processing services.

20. The system as in claim 15, further comprising:

an image comparison unit to compare image data to a set of target items; and

an optical character recognition unit to identify text information from the image data,

wherein the plurality of image processing services include an image comparison service and an optical character recognition service.

21. The system as in claim 15, further comprising:

a barcode processing unit to identify product information corresponding to image data, wherein the image data includes a barcode;

wherein the plurality of image processing services include a barcode processing service.

22. The system as in claim 15, further comprising:

a publication creation module,

wherein the one image processing service provides information for creating a publication of a product corresponding to the image data.

23. A computer-readable medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform the following operations:

receiving a message including a request for an image processing service and image data;

parsing the message to retrieve the image data;

processing the message to generate a first formatted message, the first formatted message having a format for input to the image processing service;

forwarding the first formatted message to the image processing service;

receiving a response from the image processing service;

processing the response as a response message; and

forwarding the response message for display on a computing device.

24. The computer-readable medium of claim 23, further comprising instructions for:

determining a category of products corresponding to the image data,

wherein the first formatted message identifies the category.

25. The computer-readable medium of claim 24, wherein the response from the image processing service identifies at least one product corresponding to the image data.

26. The computer-readable medium of claim 25, wherein the response from the image processing service identifies a second product similar to the at least one product.

27. The computer-readable medium of claim 23, wherein the first formatted message is in HTTP format, and the response is in XML format.

28. The computer-readable medium of claim 23, wherein the message is an email and the image data is an attachment to the email.

29. The computer-readable medium of claim 23, wherein the message is an email and the image data is included in the body of the email.

30. A method, comprising:

executing instructions on a computing platform to;

receive a request for one of a plurality of image processing services, the request including image data;

determine this an image type of the image data;

process the image data according to a first image processing service when the image data is a first image type;

process the image data according to a second image processing service when the image data is a second image type; and

identify at least one product corresponding to the image data.

31. The method as in claim 30, wherein the image data includes a barcode, and the first image processing service maps the barcode to a corresponding product in a product database.

32. The method as in claim 30, wherein the image data is a photographic image and the method further comprises:

determining parameters to be used in analyzing the image data; and

analyzing the image data using the parameters.

33. The method as in claim 30, wherein the image data is a photographic image and the method further comprises:

extracting textual information from the image data.