Methods and systems for image recognition

1. A method for image recognition implemented on a terminal device having an image capturing application, comprising:

acquiring image information for a target object to be recognized at the terminal device;

transferring said image information to a server wherein the server applies feature recognition techniques to the image information, and returns a recognition result; and

presenting the recognition result returned by the server on the terminal device;

wherein the server applying feature recognition techniques to the image information further comprises:

extracting feature information from the image information, including expressing the feature information by a first eigenvector;

comparing the feature information to a preset object feature template, wherein the preset object feature template is expressed by a second eigenvector;

when the first eigenvector and the second eigenvector have same size and a number percentage of same eigenvalues in the first eigenvector and the second eigenvector reaches a matching threshold, determining that the feature information matches the preset object feature template; and

identifying the recognition result when the feature information matches the preset object feature template, wherein the recognition result comprises profile information and address information corresponding to an object identified by the preset object feature template.

2. The method according to claim 1 , further comprising:

cropping the image information according to a preset image size; and

encoding the cropped image information,

wherein the transferring step comprises transferring the encoded cropped image information to the server.

3. The method according to claim 1 , wherein acquiring the image information for a target object to be recognized comprises:

monitoring an interface of the image capturing application;

acquiring the image information for a preset time period from the interface of the image capturing application; and

specifying the acquired image information for the preset time period as the image information for a target object to be recognized.

4. The method according to claim 3 , wherein the recognition result comprises profile information and address information included in the image information.

5. The method according to claim 4 , further comprising:

displaying a detailed interface linked to the address information when an operation is initiated based on the recognition result.

6. A method for image recognition implemented on a server, comprising:

receiving, from a terminal device, image information for a target object to be recognized;

applying feature recognition techniques to the image information;

obtaining a recognition result; and

transferring the recognition result to the terminal device;

wherein applying feature recognition techniques to the image information further comprises:

extracting feature information from the image information, including expressing the feature information by a first eigenvector;

comparing the feature information to a preset object feature template, wherein the preset object feature template is expressed by a second eigenvector;

when the first eigenvector and the second eigenvector have same size and a number percentage of same eigenvalues in the first eigenvector and the second eigenvector reaches a matching threshold, determining that the feature information matches the preset object feature template; and

identifying the recognition result when the feature information matches the preset object feature template, wherein the recognition result comprises profile information and address information corresponding to an object identified by the preset object feature template.

7. The method according to claim 6 , further comprising:

decoding the image information; and

applying feature recognition techniques to the image information to obtain the recognition result.

8. An image recognition system, comprising:

an acquisition module configured to acquire image information for a target object to be recognized;

a recognition module configured to transfer the image information to a server, wherein the server applies feature recognition techniques to the image information, and returns a recognition result; and

an output module configured to present the recognition result returned by the server;

wherein the server applying feature recognition techniques to the image information further comprises:

extracting feature information from the image information, including expressing the feature information by a first eigenvector;

comparing the feature information to a preset object feature template, wherein the preset object feature template is expressed by a second eigenvector;

when the first eigenvector and the second eigenvector have same size and a number percentage of same eigenvalues in the first eigenvector and the second eigenvector reaches a matching threshold, determining that the feature information matches the preset object feature template; and

identifying the recognition result when the feature information matches the preset object feature template, wherein the recognition result comprises profile information and address information corresponding to an object identified by the preset object feature template.

9. The image recognition system according to claim 8 , further comprising:

a cropping module configured to crop the image information according to a preset image size; and

an encoding module configured to encode the cropped image information.

10. The image recognition system according to claim 8 , the acquisition module comprising:

a monitoring unit configured to monitor an interface of an image capturing application;

an obtaining unit configured to acquire the image information for a preset time period from the interface of the image capturing application; and

a confirming unit configured to specify the acquired image information for the preset time period as the image information for a target object to be recognized.

11. The image recognition system according to claim 10 , wherein the recognition result comprises profile information and address information included in the image information.

12. The image recognition system according to claim 11 , further comprising:

a displaying module configured to display a detailed interface linked to the address information when an operation is initiated based on the recognition result.

13. The image recognition system according to claim 11 , wherein the image recognition system is installed in a terminal device.

14. An image recognition system, comprising:

a receiving module configured to receive image information for a target object to be recognized from a terminal device;

a recognition module configured to apply feature recognition techniques to obtain a recognition result; and

a result returning module configured to return the recognition result to the terminal device;

wherein recognition module comprises:

an extracting unit configured to extract feature information from the image information, including expressing the feature information by a first eigenvector;

a matching unit configured to:

match the feature information to a preset object feature template, wherein the preset object feature template is expressed by a second eigenvector; and

when the first eigenvector and the second eigenvector have same size and a number percentage of same eigenvalues in the first eigenvector and the second eigenvector reaches a matching threshold, determine that the feature information matches the preset object feature template; and

a confirming unit configured to specify profile information and address information corresponding to the object identified by the object feature template as the recognition result when the feature information matches the preset object feature template.

15. The image recognition system according to claim 14 , further comprising:

a decoding module configured to decode the received image information.

16. The image recognition system according to claim 15 , wherein the image recognition system is installed in a server.

17. The method according to claim 1 , wherein the matching threshold is 80%.

18. The image recognition system according to claim 8 , wherein the matching threshold is 80%.

19. The method according to claim 6 , wherein the matching threshold is 80%.

20. The image recognition system according to claim 14 , wherein the matching threshold is 80%.