Systems and methods for digital document field location identification

• Main Authors: Mehrotra, Tarang, Janardhanan, Geetha, Asole, Abhishek Vasant, Kashyap, Ranganath P
• Format: Patent
• Language: English
• Published: 10.08.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

Systems and methods for identifying fields in an electronic document using classification and scale invariant template matching. The method includes receiving an electronic document having fields and processing the electronic document into digital pages. The method also includes determining, for each of the digital pages, a corresponding document type. The method further includes identifying at least one of the digital pages containing a structured field based on the document type. The method also includes extracting a structured template from a database corresponding to the document type and identifying an optimal match between the structured field and the structured template using scale invariant template matching. The method further includes determining, in response to identifying the optimal match, coordinates corresponding to the structured field.