Apparatus, method, and computer-readable medium for recognition of a digital document
Described herein are an apparatus, method, and computer-readable medium. The apparatus including processing circuitry configured to extract a textual content included within a digital document, perform a text search using the extracted textual content on an indexed master document database to identify one or more master documents that are similar, within a pre-determined threshold, to the digital document, generate a candidate master document list using the one or more master documents identified based on the text search, extract a plurality of features of the digital document, perform a comparison, after performing the text search, of the plurality of features of the digital document with features of the one or more master documents in the candidate master document, and identify a master document of the one or more master documents that matches the digital document based on the comparison of the features.
1. An apparatus comprising:
processing circuitry configured to
extract a plurality of features of a digital document, after performing a text search using extracted textual content from the digital document or using extracted non-textual content that is converted to a text format from the digital document, to identify one or more master documents that are similar, within a threshold, to the digital document,
perform, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the extracting of the plurality of features, a comparison of the plurality of features of the digital document with features of the one or more master documents, and
identify, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the comparison, a master document of the one or more master documents that matches the digital document based on the comparison of the features.
2. The apparatus of claim 1 , wherein the processing circuitry is further configured to
align the digital document with the identified master document, and
extract data from the digital document including typed and handwritten text.
3. The apparatus of claim 1 , wherein after determining a location of the textual content within the digital document, the text search is performed using the textual content to identify one or more master documents having similar textual content at the location or any other location of the one or more master documents.
4. The apparatus of claim 3 , wherein the location is a section within the digital document.
5. The apparatus of claim 3 , wherein the location is a Cartesian coordinate within the digital document.
6. The apparatus of claim 1 , wherein the processing circuitry performs the comparison by first converting the plurality of features to a format similar to a format of the one or more master documents and using the plurality of features in the format to compare with features in the format of the one or more master documents.
7. A method comprising:
extracting, via processing circuitry, a plurality of features of a digital document, after performing a text search using extracted textual content from the digital document or using extracted non-textual content that is converted to a text format from the digital document, to identify one or more master documents that are similar, within a threshold, to the digital document;
performing, via the processing circuitry, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the extracting of the plurality of features, a comparison of the plurality of features of the digital document with features of the one or more master documents; and
identifying, via the processing circuitry, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the comparison, a master document of the one or more master documents that matches the digital document based on the comparison of the features.
8. The method of claim 7 , further comprising:
aligning, via the processing circuitry, the digital document with the identified master document; and
extracting, via the processing circuitry, data from the digital document including typed and handwritten text.
9. The method of claim 7 , wherein after determining a location of the textual content within the digital document, the text search is performed using the textual content to identify one or more master documents having similar textual content at the location or any other location of the one or more master documents.
10. The method of claim 9 , wherein the location is a section within the digital document.
11. The method of claim 9 , wherein the location is a Cartesian coordinate within the digital document.
12. The method of claim 7 , wherein the performing of the comparison includes first converting the plurality of features to a format similar to a format of the one or more master documents and using the plurality of features in the format to compare with features in the format of the one or more master documents.
13. A non-transitory computer-readable medium storing instructions which when executed by a computer, cause the computer to perform a method, the method comprising:
extracting a plurality of features of a digital document, after performing a text search using extracted textual content from the digital document or using extracted non-textual content that is converted to a text format from the digital document, to identify one or more master documents that are similar, within a threshold, to the digital document;
performing, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the extracting of the plurality of features, a comparison of the plurality of features of the digital document with features of the one or more master documents; and
identifying, after performing the text search using the extracted textual content or the extracted non-textual content and after performing the comparison, a master document of the one or more master documents that matches the digital document based on the comparison of the features.
14. The non-transitory computer-readable medium of claim 13 , further comprising:
aligning the digital document with the identified master document; and
extracting data from the digital document including typed and handwritten text.
15. The non-transitory computer-readable medium of claim 13 , wherein after determining a location of the textual content within the digital document, the text search is performed using the textual content to identify one or more master documents having similar textual content at the location or any other location of the one or more master documents.
16. The non-transitory computer-readable medium of claim 15 , wherein the location is a section within the digital document.
17. The non-transitory computer-readable medium of claim 15 , wherein the location is a Cartesian coordinate within the digital document.
18. The non-transitory computer-readable medium of claim 13 , wherein the performing of the comparison includes first converting the plurality of features to a format similar to a format of the one or more master documents and using the plurality of features in the format to compare with features in the format of the one or more master documents.