Extracting card data with card models
Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.
1. A computer-implemented method for extracting card information, comprising:
identifying, by the one or more computing devices, a first area of the image, the first area being selected as a potential location of one or more digits on the image;
performing, by the one or more computing devices, a classification algorithm on data encompassed by the first area;
comparing, by the one or more computing devices, the image to one or more card models associated with a user, the one or more models comprising digit distribution patterns of data displayed on the image; and
performing, by the one or more computing devices, an optical character recognition algorithm on areas of the card that are anticipated by the one or more computing devices as comprising digits based on the application of the card models and the identified lines.
2. The method of claim 1 , further comprising selecting, by the one or more computing devices, the one or more card models based at least in part on stored user data indicating card types that are associated with the user.
3. The method of claim 1 , further comprising comparing, by the one or more computing devices, the model associated with the authenticated result to a database of card types to determine a card type of the card in the image.
4. The method of claim 1 , further comprising identifying, by the one or more computing devices, one or more lines of potential digits on the image based on the results of the application of the classification.
5. The method of claim 4 , wherein the lines are identified by analyzing, by the one or more computing devices, a position of the identified digits relative to each other and fitting lines to the positions.
6. The method of claim 1 , wherein the card models represent digit distribution patterns for known card issuers.
7. The method of claim 1 , wherein the card is a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.
8. A computer program product, comprising:
a non-transitory computer-readable storage device having computer-executable program instructions embodied thereon that when executed by a computer cause the computer to extract card information, comprising:
computer-executable program instructions to identify a first area of the image, the first area being selected as a potential location of one or more digits on the image;
computer-executable program instructions to perform a classification algorithm on data encompassed by the first area;
computer-executable program instructions to compare the image to one or more card models associated with a user, the one or more models comprising digit distribution patterns of data displayed on the image; and
computer-executable program instructions to perform an optical character recognition algorithm on areas of the card that are anticipated by the one or more computing devices as comprising digits based on the application of the card models and the identified lines.
9. The computer program product of claim 8 , the computer-executable program instructions further comprising selecting the one or more card models based at least in part on stored user data indicating card types that are associated with the user.
10. The computer program product of claim 8 , the computer-executable program instructions further comprising comparing the model associated with the authenticated result to a database of card types to determine a card type of the card in the image.
11. The computer program product of claim 8 , wherein the classification algorithm is a support vector machine.
12. The computer program product of claim 8 , wherein the card models represent digit distribution patterns for known card issuers.
13. The computer program product of claim 8 , wherein the card is a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.
14. The computer program product of claim 8 , the computer-executable program instructions further comprising identifying one or more lines of potential digits on the image based on the results of the application of the classification.
15. The computer program product of claim 14 , wherein the lines are identified by analyzing a position of the identified digits relative to each other and fitting lines to the positions.
16. A system for extracting financial card information with relaxed alignment, the system comprising:
a storage device;
a processor communicatively coupled to the storage device, wherein the processor executes application code instructions that are stored in the storage device to cause the system to:
identify a first area of the image, the first area being selected as a potential location of one or more digits on the image;
perform a classification algorithm on data encompassed by the first area;
compare the image to one or more card models, the one or more models comprising digit distribution patterns of data displayed on the image; and
perform an optical character recognition algorithm on areas of the card that are anticipated by the one or more computing devices as comprising digits based on the application of the card models and the identified lines.
17. The system of claim 16 , the processor executing further application code instructions that are stored in the storage device and that cause the system to select the one or more card models based at least in part on stored user data indicating card types that are associated with the user.
18. The system of claim 16 , the processor executing further application code instructions that are stored in the storage device and that cause the system to compare the model associated with the authenticated result to a database of card types to determine a card type of the card in the image.
19. The system of claim 16 , wherein the classification algorithm is a support vector machine.
20. The system of claim 16 , wherein the card models represent digit distribution patterns for known card issuers.
21. The system of claim 16 , wherein the card is a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.
22. The system of claim 16 , the processor executing further application code instructions that are stored in the storage device and that cause the system to identify one or more lines of potential digits on the image based on the results of the application of the classification.
23. The system of claim 22 , wherein the lines are identified by analyzing, by the one or more computing devices, a position of the identified digits relative to each other and fitting lines to the positions.