Document optical character recognition
Vehicles and other items often have corresponding documentation, such as registration cards, that includes a significant amount of informative textual information that can be used in identifying the item. Traditional OCR may be unsuccessful when dealing with non-cooperative images. Accordingly, features such as dewarping, text alignment, and line identification and removal may aid in OCR of non-cooperative images. Dewarping involves determining curvature of a document depicted in an image and processing the image to dewarp the image of the document to make it more accurately conform to the ideal of a cooperative image. Text alignment involves determining an actual alignment of depicted text, even when the depicted text is not aligned with depicted visual cues. Line identification and removal involves identifying portions of the image that depict lines and removing those lines prior to OCR processing of the image.
1. A method comprising:
receiving, from a client device via a network, an image of a document comprising text describing one or more characteristics of a vehicle;
applying a dewarping function to at least a first region of the image based at least in part on identifying one or more curved lines within the first region of the image, the dewarping function comprising a transformation that straightens the one or more curved lines;
using image analysis, identifying the document;
determining a location of an identifier based on the identified document;
using optical character recognition, extracting the identifier of the vehicle from the location of the image after applying the dewarping function;
accessing, from a database, additional information regarding the vehicle based at least in part on the identifier of the vehicle; and
generating a listing for the vehicle in an online marketplace by including at least some of the additional information accessed from the database.
2. The method of claim 1 , further comprising:
determining portions of the image depicting text.
3. The method of claim 1 , further comprising:
identifying a line segment depicted in the image, the line segment having a first part within a portion of the image depicting text and a second part outside of portions of the image depicting text.
4. The method of claim 1 , further comprising:
identifying a color of a line segment depicted in the image based at least in part on a part of the line segment outside of portions of the image depicting text.
5. The method of claim 1 , further comprising:
determining a difference value between a color of a line segment depicted in the image and a color of an element of a portion of the image depicting text.
6. The method of claim 1 , wherein the identifying the document comprises accessing a database of known forms and determining a best-matching form, the best-matching form being used as a template to identify one or more locations of text and corresponding meanings.
7. The method of claim 1 , wherein the extracting of the identifier of the vehicle from the image comprises:
only performing optical character recognition on the determined location portion.
8. The method of claim 1 , wherein the additional information accessed from the database comprises a number of owners of the vehicle.
9. The method of claim 1 , wherein the additional information accessed from the database comprises a make and model of the vehicle.
10. The method of claim 9 , wherein the listing comprises a stock photo for the make, model, and year of the vehicle.
11. The method of claim 1 , wherein the one or more characteristics of the vehicle comprise at least one of a make of the vehicle, a model of the vehicle, a vehicle identification number (VIN), a registration number associated with the vehicle, or any combination thereof.
12. A system comprising:
a memory that stores instructions; and
one or more processors that, upon execution of the instructions, cause the system to perform operations comprising:
receiving, from a client device via a network, an image of a document comprising text describing one or more characteristics of a vehicle;
applying a dewarping function to at least a first region of the image based at least in part on identifying one or more curved lines within the first region of the image, the dewarping function comprising a transformation that straightens the one or more curved line;
using image analysis, identifying the document;
determining a location of an identifier based on the identified document;
using optical character recognition, extracting the identifier of the vehicle from the location of the image after applying the dewarping function;
accessing, from a database, additional information regarding the vehicle based at least in part on the identifier of the vehicle; and
generating a listing for the vehicle in an online marketplace by including, at least some of the additional information accessed from the database.
13. The system of claim 12 , wherein the operations further comprise:
determining portions of the image depicting text.
14. The system of claim 12 , wherein the operations further comprise:
identifying a line segment depicted in the image, the line segment having a first part within a portion of the image depicting text and a second part outside of portions of the image depicting text.
15. The system of claim 12 , wherein the operations further comprise:
identifying a color of a line segment depicted in the image based at least in part on a part of the line segment outside of portions of the image depicting text.
16. The system of claim 12 , wherein the operations further comprise:
determining a difference value between a color of a line segment depicted in the image and a color of an element of a portion of the image depicting text.
17. The system of claim 12 , wherein the identifying the document comprises accessing a database of known forms and determining a best-matching form, the best-matching form being used as a template to identify one or more locations of text and corresponding meanings.
18. A non-transitory machine-readable medium that stores instructions that, when executed by one or more processors, cause a system to perform operations comprising:
receiving, from a client device via a network, an image of a document comprising text describing one or more characteristics of a vehicle;
applying a dewarping function to at least a first region of the image based at least in part on identifying one or more curved lines within the first region of the image, the dewarping function comprising a transformation that straightens the one or more curved lines;
using image analysis, identifying the document;
determining a location of an identifier based on the identified document;
using optical character recognition, extracting the identifier of the vehicle from the location of the image after applying the dewarping function;
accessing, from a database, additional information regarding the vehicle based at least in part on the identifier of the vehicle; and
generating a listing for the vehicle in an online marketplace by including, at least some of the additional information accessed from the database.
19. The machine-readable medium of claim 18 , wherein the operations further comprise:
determining portions of the image depicting text.
20. The machine-readable medium of claim 18 , wherein the operations further comprise:
identifying a line segment depicted in the image, the line segment having a first part within a portion of the image depicting text and a second part outside of portions of the image depicting text.