System and method for updating geographic data

• US 9,076,061 B2
• Filed: 04/12/2012
• Issued: 07/07/2015
• Est. Priority Date: 03/12/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zennaro, Marco, Vincent, Luc, Cheung, Kong Man, Abraham, David
• Primary Examiner(s): Bhatnagar, Anand
• Assistant Examiner(s): PARK, SOO JIN
• Application Number:
  US13/445,352
• Publication Number:
  US 20150139482A1
• Time in Patent Office: 1,181 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/21 Design, administration or maintenance of databases
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition

Abstract

According to one aspect, embodiments of the invention provide a system and method for utilizing the effort expended by a user in responding to a CAPTCHA request to automatically transcribe text from images in order to verify, retrieve and/or update geographic data associated with geographic locations at which the images were recorded.

Claims

1. A method for updating geographic data associated with a geographic location, the method comprising:

receiving, by one or more computing devices, at least one image recorded at the geographic location;

identifying, by the one or more computing devices, an area within the at least one image, the area including text, wherein identifying an area includes identifying coordinates of a location of the area within the at least one image;

transmitting, by the one or more computing devices, the area to one out of a group of Completely Automated Public Turing test to tell Computer and Humans Apart (CAPTCHA) systems, wherein a language associated with the geographic location is used to select the one out of the group of CAPTCHA systems;

receiving, by the one or more computing devices, a set of transcription attempts from the CAPTCHA system;

analyzing, by the one or more computing devices, the set of transcription attempts;

generating, by the one or more computing devices, a transcription of the text based on the act of analyzing; and

updating, by the one or more computing devices, the geographic data associated with the geographic location based on the transcription of the text associated with the identified coordinates of the location of the area within the at least one image.

2. The method of claim 1, wherein the act of updating geographic data includes updating at least one of a building name, a business name, and a building number associated with the geographic location based on the transcription of the text.

3. The method of claim 1, wherein the act of transmitting includes selectively transmitting the area to a CAPTCHA system based on the geographic location.

4. The method of claim 1, further comprising filtering the set of transcription attempts to remove erroneous transcription attempts.

5. The method of claim 4, wherein the act of filtering is based on the geographic location.

6. The method of claim 1, wherein the area includes a box.

7. The method of claim 1, wherein the act of analyzing includes acts of:

comparing the transcription attempts within the set; and

determining whether a pre-defined number of transcription attempts match each other.

8. The method of claim 7, wherein the act of generating includes, in response to a determination that the pre-defined number of transcription attempts match, generating the transcription of the text based on the matched transcription attempts.

9. The method of claim 1, wherein the act of analyzing includes acts of:

comparing the transcription attempts within the set; and

determining whether a pre-defined percentage of transcription attempts match each other.

10. The method of claim 9, wherein the act of generating includes, in response to a determination that the pre-defined percentage of transcription attempts match, generating the transcription of the text based on the matched transcription attempts.

11. The method of claim 1, further comprising adjusting at least one of the size, shape, and aspect ratio of the area.

12. The method of claim 1, wherein the at least one image is a photographic image.

13. A system for updating geographic data associated with a geographic location, the system comprising;

one or more computing devices;

an input of the one or more computing devices configured to receive at least one image recorded at the geographic location;

an extraction component of the one or more computing devices configured to encode the at least one image with an identification of an area within the image that includes text, wherein the area includes coordinates of a location of the area within the at least one image;

a clipping component of the one or more computing devices configured to remove the area from the at least one image;

an interface of the one or more computing devices configured to transmit the area to one out of a group of Completely Automated Public Turing test to tell Computer and Humans Apart (CAPTCHA) systems, wherein a language associated with the geographic location is used to select the one out of the group of CAPTCHA systems, and to receive a set of transcription attempts from the CAPTCHA system;

a merging component of the one or more computing devices configured to analyze the set of transcription attempts received from the CAPTCHA system and generate a transcription of the text based on the analysis of the set of transcription attempts; and

a database of the one or more computing devices configured to receive the transcription of the text associated with the coordinates of the location of the area within the at least one image and in response, update the geographic data associated with the geographic location stored within the database.

14. The system of claim 13, wherein the CAPTCHA system is a reCAPTCHA system.

15. The system of claim 13, further comprising a filter component configured to filter out erroneous transcription attempts from the set of transcription attempts.

16. The system of claim 15, wherein the image is further encoded with the geographic location.

17. The system of claim 16, wherein the filter component is further configured to filter the set of transcription attempts based on the geographic location.

18. The system of claim 13, further comprising a scaling component configured to adjust at least one of the size, shape, and aspect ratio of the area.

19. A non-transitory computer readable medium comprising computer-executable instructions that when executed on a processor performs a method for updating geographic data associated with a geographic location, the method comprising acts of:

receiving at least one image recorded at the geographic location;

identifying an area within the at least one image, the area including text, wherein identifying an area includes identifying coordinates of a location of the area within the at least one image;

transmitting the area to one out of a group of Completely Automated Public Turing test to tell Computer and Humans Apart (CAPTCHA) systems, wherein a language associated with the geographic location is used to select the one out of the group of CAPTCHA systems;

displaying the area to a plurality of users having access to the selected one out of the group of CAPTCHA systems;

recording a set of transcription attempts from the plurality of users;

analyzing the set of transcription attempts;

generating a transcription of the text based on the act of analyzing; and

updating the geographic information related to the geographic location based on the transcription of the text associated with the identified coordinates of the location of the area within the at least one image.