Methods and apparatus for capturing, processing, training, and detecting patterns using pattern recognition classifiers

Abstract

A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.

1 .- 3 . (canceled) 
     
     
         4 . A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform operations for generating classifier data structures for classifying graphical objects, the operations comprising:
 receiving an image;   detecting one or more graphical objects within the image; and   identifying a set of candidate features for each of the graphical objects;   comparing the set of candidate features for each of the graphical objects to information included in one or more classifier data structures to determine a graphical object type associated with each of the graphical objects; and   populating one or more input fields of a user interface based at least in part on the graphical object type associated with each of the graphical objects.   
     
     
         5 . The non-transitory computer-readable storage medium of  claim 4 , the operations further comprising:
 detecting an error associated with the graphical object; and   in response to detecting the error, transmitting information associated with the error to a remote system.   
     
     
         6 . The non transitory computer-readable storage medium of  claim 5 , wherein the information associated with the error includes the image and data representative of the graphical object associated with the error. 
     
     
         7 . The non-transitory computer-readable storage medium of  claim 5 , the operations further comprising:
 prompting a user to provide an input confirming a graphical object type for the graphical object associated with the error;   receiving the input; and   populating the input field based, at least in part, on the received input.   
     
     
         8 . The non-transitory computer-readable storage medium of  claim 7 , wherein the information associated with the error includes the image, data representative of the graphical object associated with the error, and the input received from the user. 
     
     
         9 . The non-transitory computer-readable storage medium of  claim 4 , the operations further comprising determining, for each of the graphical objects, a probability that a graphical object corresponds to a graphical object type associated with one of the one or more classifier data structures until a probability satisfying a threshold is determined, wherein the one or more input fields are populated based on graphical object types associated with the probabilities satisfying the threshold for each of the graphical objects. 
     
     
         10 . The non-transitory computer-readable storage medium of  claim 4 , the operations further comprising:
 determining, based on the comparing, a probability that each of the graphical objects corresponds to a graphical object type associated with each of the one or more classifier data structures; and   identifying, for each of the graphical objects, a graphical object type having a highest probability of corresponding to a particular graphical object, wherein the one or more input fields are populated based on a graphical object type having the highest probabilities with respect to each of the graphical objects.   
     
     
         11 . The non-transitory computer-readable storage medium of  claim 10 , wherein each of the classifier data structures corresponds to one of a letter, a number, a symbol, or an element of a picture, and wherein the classifier data structures includes information that classifies detected graphical objects as a particular letter, a particular number, a particular symbol, or a particular element of a picture.