METHOD AND SYSTEM FOR IMAGE-BASED IDENTIFICATION

• US 20120134593A1
• Filed: 11/29/2010
• Published: 05/31/2012
• Est. Priority Date: 11/29/2010
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Becker, Christoph
• Granted Patent: US 8,861,896 B2
• Time in Patent Office: Days
• US Class Current: 382/195
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

The present invention may provide a method for image-based identification. The method may include providing a digital photo of an unidentified item; transmitting, over a network, the digital photo to an identification service; in response to transmitting the digital photo, receiving, over the network, item information from the identification service, wherein the item information includes textual identification information about the item; and displaying the textual identification information.

Claims

1. A method, comprising:

providing a digital photo of an unidentified item;

transmitting, over a network, the digital photo to an identification service;

in response to transmitting the digital photo, receiving, over the network, item information from the identification service, wherein the item information includes textual identification information about the item; and

displaying the textual identification information.

2. The method of claim 1, wherein the item is an object.

3. The method of claim 1, wherein the item is a person.

4. The method of claim 1, wherein the network is a wireless network.

5. The method of claim 1, wherein the providing the digital photo is taking a digital photo with a camera.

6. A method, comprising:

receiving a photo of an item over a communication network from a device;

applying a detection algorithm on the photo to generate photo image metadata;

searching a database for the image metadata;

matching the photo image metadata with stored image data in the database, wherein the stored image data includes image metadata and reference identification information for each image stored in the database;

in response to matching the photo image metadata, retrieving the reference identification information for the matched image metadata from the database; and

transmitting the reference identification information to the device over the communication network.

7. The method of claim 6, wherein the item is an object.

8. The method of claim 7, wherein the detection algorithm is an object detection algorithm.

9. The method of claim 6, wherein the item is a person.

10. The method of claim 7, wherein the detection algorithm is a face detection algorithm.

11. The method of claim 6, wherein the communication network is a wireless network.

12. The method of claim 6, if the matched image data has a plurality of corresponding reference identification information, retrieving and transmitting a highest ranked reference identification information of the plurality of corresponding reference identification information.

13. The method of claim 6, if the matched image data has a plurality of corresponding reference identification information, retrieving and transmitting all the corresponding reference identification information.

14. The method of claim 6, wherein applying the detection algorithm comprises applying a plurality of detection algorithms in parallel.

15. A method, comprising:

scanning images from a plurality of source locations;

for each scanned image, creating image identification metadata from the scanned image and creating image reference information from the source of the scanned image; and

storing, in a database, the image identification metadata and the image reference information.

16. The method of claim 15, further comprising:

for each scanned image, comparing image identification metadata with other stored imaged identification metadata; and

if there is a match, grouping image reference information for the matched images together.

17. The method of claim 16, further comprising:

ranking the grouped image reference information according to the reliability of the source location for each image reference information.

18. The method of claim 15, wherein the image is a picture of an object.

19. The method of claim 15, wherein the image is a picture of a person.

20. The method of claim 15, wherein at least one source location is a website from the world wide web.

21. The method of claim 15, wherein at least one source location is a private database.

22. The method of claim 15, wherein a plurality of image identification metadata is created using a plurality of detection algorithms applied in parallel.

23. The method of claim 22, wherein the plurality of image identification metadata is stored in a multi-layer structure.

24. An apparatus, comprising:

a processor to control operations of the apparatus;

a memory to store a photo of an item;

a communication system comprising a transmitter to transmit the photo over a communication network and a receiver to receive identification information for the item in response to transmitting the photo; and

a display to display the identification information.

25. The apparatus of claim 24 further comprises a camera to take the photo.

26. The apparatus of claim 24, wherein the communication system is a wireless communication system.

27. The apparatus of claim 24, wherein the item is an object.

28. The apparatus of claim 24, wherein the item is a person.

29. A system, comprising:

a communication system to receive a request to identify an item in a photo and to transmit identification information in response to the request;

a processor to apply a detection algorithm on the photo to generate photo image metadata; and

a database that stores image metadata and corresponding identification information.

30. The system of claim 29, wherein the communication system is a wireless communication system.

31. The system of claim 29, wherein the item is an object.

32. The system of claim 29, wherein the item is a person.

33. The system of claim 29, wherein the processor applies a plurality of detection algorithms in parallel.