Back to results
US 12,243,337 B2Granted
Text extraction using optical character recognition
AssigneeCapital One Services, LLC
InventorsChris Demchalk, Ryan M. Parker, Lokesh Vijay Kumar, Brian Fromknecht
Life of this patent
Estimating the term…
Abstract
Provided herein are systems and methods for extracting text from a document. Different optical character recognition (OCR) tools are used to extract different versions of the text in the document. Metrics evaluating the quality of the extracted text are compared to identify and select higher quality extracted text. A selected portion of text is compared to a threshold to ensure minimal quality. The selected portion of text is then saved. Error correction can be applied to the selected portion of text based on errors specific to the OCR tools or the document contents.
Claims17
A method, comprising:
- extracting, by at least one processor, a first set of text from a document using a first optical character recognition (OCR) tool;
- extracting, by the at least one processor, a second set of text from the document using a second OCR tool;
- comparing, by the at least one processor, a first metric of the first set of text to a second metric of the second set of text, the first metric measuring a first level of OCR quality of the first set of text and the second metric measuring a second level of OCR quality of the second set of text;
- selecting, by the at least one processor, a first selected text from the first set of text or the second set of text based on a higher level of OCR quality;
- extracting, by the at least one processor, a third set of text from the document using a third OCR tool;
- comparing, by the at least one processor, a corresponding metric of the first selected text to a third metric of the third set of text, the third metric measuring a third level of OCR quality of the third set of text;
- determining, for the first set of text, the second set of text, and the third set of text, a fourth metric, wherein the fourth metric comprises measuring a fourth level of OCR quality based on a respective number of words in respective ones of the first set, second set, or third set of extracted texts from the document divided by a number of pages in the document;
- selecting, by the at least one processor, a second selected text from the first selected text or the third set of text based on a higher level of the third level of OCR quality or the fourth level of OCR quality;
- and
- storing, by the at least one processor, the second selected text as a final text in a searchable format.
7 more elements
A system, comprising:
- one or more processors;
- memory communicatively coupled to the one or more processors, the memory storing instructions which, when executed by the one or more processors, cause the one or more processors to:
- extract a first set of text from a document using a first optical character recognition (OCR) tool;
- extract a second set of text from the document using a second OCR tool;
- compare a first metric of the first set of text to a second metric of the second set of text, the first metric measuring a first level of OCR quality of the first set of text and the second metric measuring a second level of OCR quality of the second set of text;
- select, based on the comparing, a first selected text from the first set of text or the second set of text based on a higher level of OCR quality;
- extract a third set of text from the document using a third OCR tool;
- compare a corresponding metric of the first selected text to a third metric of the third set of text, the third metric measuring a third level of OCR quality of the third set of text;
- determine, for the first set of text, the second set of text, and the third set of text, a fourth metric, wherein the fourth metric comprises measuring a fourth level of OCR quality based on a respective number of words in respective ones of the first set, second set, or third set of extracted texts from the document divided by a number of pages in the document;
- select a second selected text from the first selected text or the third set of text based on a higher level of the third level of OCR quality or the fourth level of OCR quality;
- and
- store the second selected text as a final text in a searchable format.
9 more elements
A non-transitory computer readable storage medium having computer readable code thereon, the non-transitory computer readable storage medium including instructions configured to cause a computer system to perform operations, comprising:
- extracting a first set of text from a document using a first optical character recognition (OCR) tool;
- extracting a second set of text from the document using a second OCR tool;
- comparing a first metric of the first set of text to a second metric of the second set of text, the first metric measuring a first level of OCR quality of the first set of text and the second metric measuring a second level of OCR quality of the second set of text;
- selecting, based on the comparing, a first selected text from the first set of text or the second set of text based on a higher level of OCR quality;
- extracting a third set of text from the document using a third OCR tool;
- comparing a corresponding metric of the first selected text to a third metric of the third set of text, the third metric measuring a third level of OCR quality of the third set of text;
- determining, for the first set of text, the second set of text, and the third set of text, a fourth metric, wherein the fourth metric comprises measuring a fourth level of OCR quality based on a respective number of words in respective ones of the first set, second set, or third set of extracted texts from the document divided by a number of pages in the document;
- selecting a second selected text from the first selected text or the third set of text based on a higher level of the third level of OCR quality or the fourth level of OCR quality;
- and
- storing the second selected text as a final text in a searchable format.
7 more elements
Dependencies are inferred from the claim text.