Using extracted image text

• US 9,881,231 B2
• Filed: 12/01/2016
• Issued: 01/30/2018
• Est. Priority Date: 06/29/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Ulges, Adrian, Vincent, Luc
• Primary Examiner(s): Desire, Gregory M
• Application Number:
  US15/366,833
• Publication Number:
  US 20170193326A1
• Time in Patent Office: 425 Days
• CPC Class Codes: G01S 19/51 Relative positioning
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 3/4053 based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition

Abstract

Methods, systems, and apparatus including computer program products for using extracted image text are provided. In one implementation, a computer-implemented method is provided. The method includes receiving an input of one or more image search terms and identifying keywords from the received one or more image search terms. The method also includes searching a collection of keywords including keywords extracted from image text, retrieving an image associated with extracted image text corresponding to one or more of the image search terms, and presenting the image.

Claims

1. A computer-implemented method comprising:

receiving an input of one or more search terms;

identifying one or more keywords from the received one or more search terms;

searching a collection of keywords including keywords extracted from image text;

retrieving an image, the image being associated with extracted text corresponding to one or more of the search terms, and the image being associated with location data corresponding to a location associated with the image;

presenting the image; and

generating a map of the location associated with the image.

2. The method of claim 1, wherein the location data are determined by:

receiving a plurality of images, and, for each image;

extracting text from within the image;

indexing the extracted text; and

associating the extracted text with a mapping application.

3. The method of claim 2, where the location data comprises a set of GPS coordinates for each image.

4. The method of claim 2, wherein the extracting is constrained based on values in a database.

5. The method of claim 2, wherein the extracting is constrained to a numeric pattern.

6. The method of claim 1, where the keywords extracted from the image text are extracted using a text recognition process including:

processing the image to divide the image into one or more regions;

detecting one or more features in each region;

determining for each region whether it is a candidate text region potentially containing text using the detected features;

enhancing the candidate text regions to generate an enhanced image; and

performing optical character recognition on the enhanced image.

7. The method of claim 1, where the keywords extracted from the image text are extracted using a text recognition process including:

receiving a plurality of images;

processing the images to detect a corresponding set of regions of the images, each image having a region corresponding to each other image region, as potentially containing text;

combining the regions to generate an enhanced region image; and

performing optical character recognition on the enhanced region image.

8. The method of claim 1, further comprising:

providing images of businesses located nearby the location; and

identifying the locations of the businesses on a map.

9. A non-transitory computer-readable medium containing instructions that when executed by a data processing apparatus, cause the data processing apparatus to perform operations including:

receiving an input of one or more search terms;

identifying one or more keywords from the received one or more search terms;

searching a collection of keywords including keywords extracted from image text;

retrieving an image, the image being associated with extracted text corresponding to one or more of the search terms, and the image being associated with location data corresponding to a location associated with the image;

presenting the image; and

generating a map of the location associated with the image.

10. The non-transitory computer-readable medium of claim 9, wherein the location data are determined by:

receiving a plurality of images, and, for each image;

extracting text from within the image;

indexing the extracted text; and

associating the extracted text with a mapping application.

11. The non-transitory computer-readable medium of claim 10, where the location data comprises a set of GPS coordinates for each image.

12. The non-transitory computer-readable medium of claim 10, wherein the extracting is constrained based on values in a database.

13. The non-transitory computer-readable medium of claim 10, wherein the extracting is constrained to a numeric pattern.

14. The non-transitory computer-readable medium of claim 9, where the keywords extracted from the image text are extracted using a text recognition process including:

processing the image to divide the image into one or more regions;

detecting one or more features in each region;

determining for each region whether it is a candidate text region potentially containing text using the detected features;

enhancing the candidate text regions to generate an enhanced image; and

performing optical character recognition on the enhanced image.

15. The non-transitory computer-readable medium of claim 9, where the keywords extracted from the image text are extracted using a text recognition process including:

receiving a plurality of images;

processing the images to detect a corresponding set of regions of the images, each image having a region corresponding to each other image region, as potentially containing text;

combining the regions to generate an enhanced region image; and

performing optical character recognition on the enhanced region image.

16. The non-transitory computer-readable medium of claim 9, further comprising the operations of:

providing images of businesses located nearby the location; and

identifying the locations of the businesses on a map.

17. A system, comprising:

one or more processors;

a non-transitory memory storing instructions executable by the one or more processors and that upon such execution cause the one or more processors to perform operations comprising;

receive an input of one or more search terms;

identify one or more keywords from the received one or more search terms;

search a collection of keywords including keywords extracted from image text;

retrieve an image, the image being associated with extracted text corresponding to one or more of the search terms, and the image being associated with location data corresponding to a location associated with the image;

present the image; and

generate a map of the location associated with the image.

18. The system of claim 17, wherein the location data are determined by:

receiving a plurality of images, and, for each image;

extracting text from within the image;

indexing the extracted text; and

associating the extracted text with a mapping application.

19. The system of claim 17, where the keywords extracted from the image text are extracted using a text recognition process including:

processing the image to divide the image into one or more regions;

detecting one or more features in each region;

determining for each region whether it is a candidate text region potentially containing text using the detected features;

enhancing the candidate text regions to generate an enhanced image; and

performing optical character recognition on the enhanced image.