System and method of determining building numbers

• US 8,787,673 B2
• Filed: 07/12/2011
• Issued: 07/22/2014
• Est. Priority Date: 07/12/2010
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Wu, Bo, Bissacco, Alessandro, Smith, Raymond W., Cheung, Kong man, Frome, Andrea, Urbach, Shlomo
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): WOLDEMARIAM, AKLILU K
• Application Number:
  US13/181,081
• Publication Number:
  US 20120008865A1
• Time in Patent Office: 1,106 Days
• Field of Search: 382/299, 382/187, 382/185, 382/101, 382/177
• US Class Current: 382/182
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 50/10 Services
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/424 Postal images, e.g. labels or addresses on parcels or postal envelopes

Abstract

A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.

Claims

1. A method comprising:

receiving, by one or more processors, a first set of images of numbers on buildings associated with the address of such building;

receiving, by the one or more processors, a second set of images that do not contain numbers on buildings associated with the address of a building;

determining, by the one or more processors, a characteristic that is present within a plurality of the images of the first set but is not present within the image of the second set, wherein the characteristic is visually similar to one or more portions of one or more pictures of building numbers;

receiving, by the one or more processors, an image of a building from a plurality of images;

determining, by the one or more processors, whether a portion of the image of the building includes numbers matching the characteristic;

storing, by the one or more processors, an identification of the portion of the image of the building that matches the characteristic;

extracting, by the one or more processors, the identified portion of the image;

when the extracted portion of the image corresponds with a selected address, providing, by the one or more processors, the image of the building and the extracted portion to a human operator; and

when the extracted portion of the image does not correspond with the selected address, selecting, by the one or more processors, a different image from the plurality of images and repeating the determining, storing, and extracting steps with the different image.

2. The method of claim 1 wherein the first set of images and the second set of images are selected by a human operator from among a plurality of images.

3. The method of claim 1 wherein the characteristic comprises an image pattern.

4. The method of claim 1 wherein there at least 10 images in the first set and 10 images in the second set.

5. The method of claim 1, further comprising:

in response to providing the image of the building and the extracted portion to a human operator, receiving confirmation information; and

in response to receiving the confirmation information, associating the numbers matching the characteristic with the image of the building.

6. The method of claim 5, further comprising:

receiving a request identifying an address;

identifying the numbers matching the characteristic based on the address; and

providing the image of the building associated with the numbers matching the characteristic identified based on the address.

7. A system comprising one or more processors configured to:

receive a first set of images of numbers on buildings associated with the address of such building;

receive a second set of images that do not contain numbers on buildings associated with the address of a building;

determine a characteristic that is present within a plurality of the images of the first set but is not present within the image of the second set, wherein the characteristic is visually similar to one or more portions of one or more pictures of building numbers;

receive an image of a building from a plurality of images;

determine whether a portion of the image of the building includes numbers matching the characteristic;

store an identification of the portion of the image of the building that matches the characteristic;

extract the identified portion of the image;

when the extracted portion of the image corresponds with a selected address, provide the image of the building and the extracted portion to a human operator; and

when the extracted portion of the image does not correspond with the selected address, select a different image from the plurality of images and repeating the determining, storing, and extracting steps with the different image.

8. The system of claim 7 wherein the first set of images and the second set of images are selected by a human operator from among a plurality of images.

9. The system of claim 7 wherein the characteristic comprises an image pattern.

10. The system of claim 7 wherein there at least 10 images in the first set and 10 images in the second set.

11. The system of claim 7, wherein the one or more processors are further configured to:

in response to providing the image of the building and the extracted portion to a human operator, receive confirmation information; and

in response to receiving the confirmation information, associate the numbers matching the characteristic with the image of the building.

12. The system of claim 11, wherein the one or more processors are further configured to:

receive a request identifying an address;

identify the numbers matching the characteristic based on the address; and

provide the image of the building associated with the numbers matching the characteristic identified based on the address.

13. A non-transitory, computer-readable medium storing instructions, the instructions when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:

receiving a first set of images of numbers on buildings associated with the address of such building;

receiving a second set of images that do not contain numbers on buildings associated with the address of a building;

determining a characteristic that is present within a plurality of the images of the first set but is not present within the image of the second set, wherein the characteristic is visually similar to one or more portions of one or more pictures of building numbers;

receiving an image of a building from a plurality of images;

determining, with the processor, whether a portion of the image of the building includes numbers matching the characteristic;

storing an identification of the portion of the image of the building that matches the characteristic;

extracting the identified portion of the image;

when the extracted portion of the image corresponds with a selected address, providing the image of the building and the extracted portion to a human operator; and

when the extracted portion of the image does not correspond with the selected address, selecting a different image from the plurality of images and repeating the determining, storing, and extracting steps with the different image.

14. The non-transitory, computer-readable medium of claim 13, wherein the first set of images and the second set of images are selected by a human operator from among a plurality of images.

15. The non-transitory, computer-readable medium of claim 13, wherein the characteristic comprises an image pattern.

16. The non-transitory, computer-readable medium of claim 13, wherein there at least 10 images in the first set and 10 images in the second set.

17. The non-transitory, computer-readable medium of claim 13, wherein the method further comprises:

in response to providing the image of the building and the extracted portion to a human operator, receiving confirmation information; and

in response to receiving the confirmation information, associating the numbers matching the characteristic with the image of the building.

18. The non-transitory, computer-readable medium of claim 17, wherein the method further comprises:

receiving a request identifying an address;

identifying the numbers matching the characteristic based on the address; and

providing the image of the building associated with the numbers matching the characteristic identified based on the address.