Methods for mobile image capture of vehicle identification numbers in a non-document
Various embodiments disclosed herein are directed to methods of capturing Vehicle Identification Numbers (VIN) from images captured by a mobile device. Capturing VIN data can be useful in several applications, for example, insurance data capture applications. There are at least two types of images supported by this technology: (1) images of documents and (2) images of non-documents.
1. A non-transitory computer readable medium containing instructions which, when executed by a computer, perform a process comprising:
capturing an image which includes a vehicle identification number (VIN);
making a color assumption with respect to the VIN;
identifying candidate text strings that may include the VIN;
performing an optical character recognition (OCR) on the candidate text strings;
sending the candidate text strings for validation; and
in response to the candidate test string being validated, receiving a confirmed VIN value for the validated candidate text strings.
2. The non-transitory computer readable medium of claim 1 , wherein validating the candidate text strings comprises performing a redundancy test.
3. The non-transitory computer readable medium of claim 2 , wherein the redundancy test includes a mod 11 rule test.
4. The non-transitory computer readable medium of claim 1 , wherein performing an optical character recognition on the candidate text strings produces ASCII text strings for each candidate text string.
5. The non-transitory computer readable medium of claim 1 , wherein the color assumption may be represented by set of three weights WR, WG and WB (WR+WG+WB=1.0) to generate a color conversion formula:
B ( P )=( R ( P )* WR+G ( P )* WG+B ( P )* WB )/3, where
P=P(X, Y)—an arbitrary pixel on the image represented by its X and Y-coordinates,
B(P)—a computed brightness value of pixel P on output grayscale image, and
R(P), G(P) and B(P)—Red, Green and Blue color value of pixel P on an original color image.
6. The non-transitory computer readable medium of claim 1 , further comprising post processing candidate text strings that fail validation.
7. The non-transitory computer readable medium of claim 6 , wherein the post processing comprises using second alternatives of OCR recognition for OCR engines that provide multiple recognition results per character.
8. A system for identifying a field in an image of a non-document, comprising:
a memory configured to store the image; and
a processor coupled with the memory, the processor configured to:
capture an image which includes a vehicle identification number (VIN);
make a color assumption with respect to the VIN;
identify candidate text strings that may include the VIN;
perform an optical character recognition (OCR) on the candidate text strings;
send the candidate text strings for validation; and
in response to a candidate test string being validated, receive a confirmed VIN value for the validated candidate text strings.
9. The system of claim 8 , wherein validating the candidate text strings comprises performing a redundancy test.
10. The system of claim 9 , wherein the redundancy test includes a mod 11 rule test.
11. The system of claim 8 , wherein performing an optical character recognition on the candidate text strings produces ASCII text strings for each candidate text string.
12. The system of claim 8 , wherein the color assumption is represented by set of three weights WR, WG and WB (WR+WG+WB=1.0) to generate a color conversion formula:
B ( P )=( R ( P )* WR+G ( P )* WG+B ( P )* WB )/3, where
P=P(X, Y)—an arbitrary pixel on the image represented by its X and Y-coordinates,
B(P)—a computed brightness value of pixel P on output grayscale image, and
R(P), G(P) and B(P)—Red, Green and Blue color value of pixel P on an original color image.
13. The system of claim 8 , wherein the process is further configured to post process candidate text strings that fail validation.
14. The system of claim 13 , wherein the post processing comprises using second alternatives of OCR recognition for OCR engines that provide multiple recognition results per character.
15. A method for identifying a field in an image of a non-document, comprising:
capturing an image which includes a vehicle identification number (VIN);
making a color assumption with respect to the VIN;
identifying candidate text strings that may include the VIN;
performing an optical character recognition (OCR) on the candidate text strings;
sending the candidate text strings for validation; and
in response to a candidate test string being validated, receive a confirmed VIN value for the validated candidate text strings.
16. The method of claim 15 , wherein validating the candidate text strings comprises performing a redundancy test.
17. The method of claim 16 , wherein the redundancy test includes a mod 11 rule test.
18. The method of claim 15 , wherein performing an optical character recognition on the candidate text strings produces ASCII text strings for each candidate text string.
19. The method of claim 15 , wherein the color assumption may be represented by set of three weights WR, WG and WB (WR+WG+WB=1.0) to generate a color conversion formula:
B ( P )=( R ( P )* WR+G ( P )* WG+B ( P )* WB )/3, where
P=P(X, Y)—an arbitrary pixel on the image represented by its X and Y-coordinates,
B(P)—a computed brightness value of pixel P on the output grayscale image, and
R(P), G(P) and B(P)—Red, Green and Blue color value of pixel P on an original color image.
20. The method of claim 15 , further comprising post processing candidate text strings that fail validation.