Capital One Services, LLC

Aaron Attar

Gowtham Guduru

Joshua Havens

Rahul Nowlakha

Fnu Manjushri Srikanta Swamy

A system may iteratively scan a portion of a document, extract first data from the portion of the document, and determine, using a trained model, whether the first data corresponds to one or more document types based on one or more confidence thresholds. The system may repeat this process, increasing the portion of the document scanned by a predetermined amount each iteration, until the first data corresponds to the one or more document types based on the one or more confidence thresholds. Responsive to determining the first data corresponds to the one or more document types based on the one or more confidence thresholds, the system may cause a graphical user interface (GUI) of a user device to display a notification indicating a document type match.

Systems and methods for classifying documents

Disclosed embodiments may include a system for measuring document legibility. The system may automatically receive document image data from a user device. The system may then process the image data using optical character recognition to create language data containing a plurality of words. The system may then obtain an overall number by counting the plurality of words in the language data. The system may then identify and count the common words within the plurality of words by comparing the plurality of words to words in a database. A score may be obtained by dividing the common word number by the overall number. The score may then be compared to a legibility threshold. If the score is below the threshold, the system may determine the document is illegible. If the score is above the threshold, the system may determine the document is legible.

Systems and methods for measuring document legibility

Systems and methods for identifying a presence of a completed document are disclosed. The system may receive an image file from a client device associated with a first document, identify one or more image regions within the image file corresponding to a presence of one or more extractable data entries, selectively extract the one or more extractable data entries, and determine whether the one or more extractable data entries match one or more stored data entries. When the one or more extractable data entries match, the system may determine the status of the first document as completed. When the one or more extractable data entries do not match, the system may proactively replace one or more inconsistent extractable data entries with corresponding stored data entries to form a corrected first document, and generate a request for a client to verify the corrected first document.

Growing community of inventors

Dallas, TX, United States of America

Aaron Attar