Extracting image data using three-dimensional models

Abstract

Comparing extracted card data from a continuous scan comprises an optical character recognition (“OCR”) system for extracted data based on three-dimensional models. The system receives a digital scan of a physical card and obtains a plurality of images of the card from the digital scan of the physical card. The system performs an OCR algorithm on a three-dimensional model based on the images and determines if a confidence level of the results are above a preconfigured level. If the results are below the preconfigured levels, a second three dimensional model is created that includes additional received images. When results are over the preconfigured level, the results are accepted as an accurate extraction.

What is claimed is: 
     
         1 . A computer-implemented method to verify extracted data based on three-dimensional models of digital card images, comprising:
 obtaining, by one or more computing devices, a plurality of images of a physical card from a digital scan of the physical card;   creating, by one or more computing devices, a first three-dimensional model of the physical card based upon the plurality of images;   performing, by the one or more computing devices, an optical character recognition algorithm on a plurality of perspectives of the first three-dimensional model;   determining, by the one or more computing devices, a confidence level of a result of performing the application of the optical character recognition algorithm to the plurality of perspectives of the first three-dimensional model;   comparing, by the one or more computing devices, the confidence level of the first result to a preconfigured level; and   accepting, by the one or more computing devices, the first result when the confidence level of the first result is greater than or equal to the preconfigured level.   
     
     
         2 . The method of  claim 1 , further comprising:
 receiving, by the one or more computing devices, additional images based at least in part on a determination that the confidence level is lower than the preconfigured level;   creating, by one or more computing devices, a second three-dimensional model, based at least in part on the additional images;   performing, by the one or more computing devices, the optical character recognition algorithm on a plurality of perspectives of the second three-dimensional model;   determining, by the one or more computing devices, a confidence level of a result of performing the application of the optical character recognition algorithm to the second three-dimensional model;   comparing, by the one or more computing devices, the confidence level of the second result to the preconfigured level; and   accepting, by the one or more computing devices, the second result when the confidence level of the first result is greater than or equal to the preconfigured level.   
     
     
         3 . The method of  claim 1 , further comprising:
 comparing, by the one or more computing devices, results of performing the optical character recognition algorithm for the first three-dimensional model and the second three-dimensional model;   determining, by the one or more computing devices, if a preconfigured level of the results for each of the first and the second three-dimensional models match each other;   verifying, by the one or more computing devices, the results when the results for each of the first and the second three-dimensional models match each other; and   verifying, by the one or more computing devices, the results with the highest confidence level when the results do not match each other.   
     
     
         4 . The method of  claim 1 , wherein the additional images are accessed from the obtained images. 
     
     
         5 . The method of  claim 1 , wherein the additional images are obtained via a second scan of the card. 
     
     
         6 . The method of  claim 1 , wherein only the additional images are used to create the second three-dimensional model. 
     
     
         7 . The method of  claim 1 , wherein the digital scan is received from a camera. 
     
     
         8 . The method of  claim 1 , wherein the digital scan comprises a video or a plurality of still images. 
     
     
         9 . 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 verify extracted data based on three-dimensional models of digital card images, the computer-executable instructions comprising:
 computer-executable program instructions to receive a digital scan of a physical card; 
 computer-executable program instructions to obtain a plurality of images of the physical card from the digital scan of the physical card; 
 computer-executable program instructions to create a first three-dimensional model of the card based upon the plurality of images; 
 computer-executable program instructions to perform an optical character recognition algorithm on a plurality of perspectives of the first three-dimensional model; 
 program instructions to determine a confidence level of a result of performing the application of the optical character recognition algorithm to the plurality of perspectives of the first three-dimensional model; 
 computer-executable program instructions to compare the confidence level of the first result to a preconfigured level; 
 computer-executable program instructions to verify the first result when the confidence level of the first result is greater than or equal to the preconfigured level; 
 computer-executable program instructions to receive additional images based at least in part on a determination that the confidence level is lower than the preconfigured level; 
 computer-executable program instructions to create a second three-dimensional model, based at least in part on the additional images; 
 computer-executable program instructions to perform the optical character recognition algorithm on a plurality of perspectives of the second three-dimensional model; 
 computer-executable program instructions to determine a confidence level of a result of performing the application of the optical character recognition algorithm to the second three-dimensional model; 
 computer-executable program instructions to compare the confidence level of the second result to a preconfigured level; and 
 computer-executable program instructions to accept the second result when the confidence level of the first result is greater than or equal to the preconfigured level. 
   
     
     
         10 . The computer program product of  claim 8 , further comprising:
 computer-executable program instructions to compare results of the application of the optical character recognition algorithm for first and second three-dimensional models;   computer-executable program instructions to determine if a preconfigured level of the results for each of the first and the second three-dimensional models match each other;   computer-executable program instructions to verify the results when the results for each of the first and the second three-dimensional models match each other; and   computer-executable program instructions to verify the results with the highest confidence level when the results do not match each other.   
     
     
         11 . The computer program product of  claim 8 , further comprising computer-executable program instructions to receive the additional images from the obtained images. 
     
     
         12 . The computer program product of  claim 8 , further comprising computer-executable program instructions to receive the additional images via a second scan of the card. 
     
     
         13 . The computer program product of  claim 8 , further comprising computer-executable program instructions to create a second three-dimensional model using only the additional images. 
     
     
         14 . A system to verify extracted data based on three-dimensional models of digital card images, comprising:
 a storage resource;   a processor communicatively coupled to the storage resource, wherein the processor executes application code instructions that are stored in the storage resource to cause the system to:
 receive a digital scan of a card; 
 obtain a plurality of images of the physical card from the digital scan of the physical card; 
 create a first three-dimensional model of the card based upon the plurality of images; 
 perform an optical character recognition algorithm on a plurality of perspectives of the first three-dimensional model; 
 determine a confidence level of a first result performing of the application of the optical character recognition algorithm to the plurality of perspectives of the first three-dimensional model; 
 compare the confidence level of the first result to a preconfigured level; 
 accept the first result when the confidence level of the first result is greater than or equal to the preconfigured level; 
 receive additional images based at least in part on a determination that the confidence level is lower than the preconfigured level; 
 create a second three-dimensional model, based at least in part on the additional images; 
 perform the optical character recognition algorithm on a plurality of perspectives of the second three-dimensional model; and 
 determine a confidence level of a result of performing the application of the optical character recognition algorithm to the second three-dimensional model. 
   
     
     
         15 . The system of  claim 13 , the processor further executing application code instructions to cause the system to:
 compare results of the application of the optical character recognition algorithm for first and second three-dimensional models;   determine if a preconfigured level of the results for each of the first and the second three-dimensional models match each other;   verify the results when the results for each of the first and the second three-dimensional models match each other; and   verify the results with the highest confidence level when the results do not match each other.   
     
     
         16 . The system of  claim 13 , the processor further executing application code instructions to cause the system to receive only the additional images to create the second three-dimensional model. 
     
     
         17 . The system of  claim 13 , the processor further executing application code instructions to cause the system to receive the digital scan from a camera. 
     
     
         18 . The system of  claim 13 , wherein the digital scan comprises a video or a plurality of still images.