Systems and methods for classifying payment documents during mobile image processing

• US 10,423,826 B2
• Filed: 03/22/2016
• Issued: 09/24/2019
• Est. Priority Date: 01/18/2008
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Nepomniachtchi, Grigori, Kliatskine, Vitali, Kotovich, Nikolay
• Primary Examiner(s): Motsinger, Sean T
• Application Number:
  US15/077,801
• Publication Number:
  US 20160203364A1
• Time in Patent Office: 1,281 Days
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G06V 30/2253 Recognition of characters printed with magnetic ink G06V30/2247 takes precedence
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

Systems and methods are provided for processing an image of a financial payment document captured using a mobile device and classifying the type of payment document in order to extract the content therein. These methods may be implemented on a mobile device or a central server, and can be used to identify content on the payment document and determine whether the payment document is ready to be processed by a business or financial institution. The system can identify the type of payment document by identifying features on the payment document and performing a series of steps to determine probabilities that the payment document belongs to a specific document type. The identification steps are arranged starting with the fastest step in order to attempt to quickly determine the payment document type without requiring lengthy, extensive analysis.

Claims

1. A payment document classification system, comprising:

a communication unit to receive an image of a payment document captured by a camera of a mobile device;

a feature knowledge database to store a set of features, wherein a given feature in the set of stored features is associated with one or more probability values, and each of the one or more probability values represents a probability of occurrence of the given feature in a given payment document type within a set of known payment document types;

a preprocessing unit to extract a set of features from the image;

a classification unit which is configured to;

compare, by one or more processors, the set of extracted features against the set of stored features in the feature knowledge database;

in response to a match between an extracted feature in the set of extracted features and a stored feature in the set of stored features,

determine whether the payment document can be classified as one of the known payment document types associated with the matched stored feature based on the associated probability values of the matched stored feature by comparing the probability values associated with the matched stored feature with a predetermined threshold value; and

classify the payment document as the payment document type based on the determination;

a processing unit which is configured to;

process content of the payment document in view of the payment document type.

2. The payment document classification system of claim 1, wherein the classification unit is configured to determine whether the payment document can be classified as one of the known payment document types by:

in response to one of the probability values associated with the matched stored feature exceeds the predetermined threshold value, determining that the payment document can be classified as the known payment document type associated with the one of the probability values.

3. The payment document classification system of claim 1, wherein the set of stored features includes one or more of a geometric feature, a lock icon, a Magnetic Ink Character Recognition (MICR) line, an OCR-A line, a check number, a barcode, a keyword, and a combination of two or more of the above.

4. The payment document classification system of claim 1, wherein the set of known payment document types includes at least personal checks, business checks, cashier'"'"'s checks, traveler'"'"'s checks, money orders, store rebates, gift certificates, and IRS refunds.

5. The payment document classification system of claim 1, wherein the classification unit compares the set of extracted features against the set of stored features in the feature knowledge database in a sequence until one of the set of extracted features matches one of the set of stored features.

6. The payment document classification system of claim 4, wherein the classification unit compares the set of extracted features against the set of stored features in the feature knowledge database in a series, starting with an extracted feature which requires the least computation time among the set of extracted features.

7. The payment document classification system of claim 1, further comprising a configuration unit to allow a user to configure the set of payment document types into a category of payment document types for classifying the payment document as belonging to the category of payment document types.

8. The payment document classification system of claim 1, further comprising an image correction unit to receive the image of the payment document from the communication unit and corrects at least one aspect of the image of the payment document to produce a corrected image.

9. A method of classifying a payment document, comprising:

receiving an image of a payment document captured by a camera of a mobile device;

extracting a set of features from the image;

comparing the set of extracted features against a set of features stored in a feature knowledge database, wherein a given feature in the set of stored features is associated with one or more probability values, and each of the one or more probability values represents a probability of occurrence of the given feature in a given payment document type within a set of known payment document types; and

in response to a match between an extracted feature in the set of extracted features and a stored feature in the set of stored features,

determining whether the payment document can be classified as one of the known payment document types associated with the matched stored feature based on the associated probability values of the matched stored feature by comparing the probability values associated with the matched stored feature with a predetermined threshold value;

classifying the payment document as the payment document type based on the determination; and

processing content of the payment document in view of the payment document type.

10. The method of claim 9, wherein determining whether the payment document can be classified as one of the known payment document types includes:

in response to one of the probability values associated with the matched stored feature exceeds the predetermined threshold value, determining that the payment document can be classified as the known payment document type associated with the one of the probability values.

11. The method of claim 9, wherein the set of stored features includes one or more of a geometric feature, a lock icon, a MICR line, an OCR-A line, a check number, a barcode, a keyword, and a combination of two or more of the above.

12. The method of claim 9, wherein the set of known payment document types includes at least personal checks, business checks, cashier'"'"'s checks, traveler'"'"'s checks, money orders, store rebates, gift certificates, and IRS refunds.

13. The method of claim 9, wherein comparing the set of extracted features against the set of features includes performing the comparisons sequentially until one of the set of extracted features matches one of the set of stored features.

14. The method of claim 9, wherein comparing the set of extracted features against the set of features includes performing the comparisons in a series, starting with an extracted feature which requires the least computation time among the set of extracted features.

15. The method of claim 9, wherein the method further comprises configuring the set of payment document types into a category of payment document types for classifying the payment document as belonging to the category of payment document types.

16. The method of claim 9, wherein the method further comprises correcting at least one aspect of the image of the payment document to produce a corrected image.