Systems and methods for data extraction from scanned documents powered by artificial intelligence

A computer-implemented system comprising:

• a non-transitory computer readable medium configured to store instructions;
• and
• at least one processor configured to execute the instructions to perform operations comprising:
• obtaining, from at least one data store, at least one document associated with at least one entity;
• identifying, using an object detection algorithm, at least one table located on the at least one document, wherein the object detection algorithm is trained using a dataset including tables from a plurality of other documents;
• extracting, using optical character recognition, text within the identified at least one table based on predicted coordinates of the at least one table;
• reproducing the at least one table using the extracted text by:
• identifying at least one header of the at least one table, wherein the identification of the at least one header includes reverse iterating through the extracted text to identify a line containing a valid header row;
• identifying a final row of the at least one table;
• identifying, using a sliding window technique, columns of the at least one table;
• and
• presenting the extracted text in rows and columns;
• and
• storing the reproduced at least one table in a database.