Abstract: Disclosed is a system for reading contents from a document. The system includes a memory unit for storing a set of instructions, and a processing unit is coupled to the memory unit for processing the set of instruction. The set of instructions initiates with a step of rendering the document to retrieve the image of each page and retrieving the digital text and location of each word to create digital text blocks for each word. Running OCR on the images retrieved on rendering the document to an OCR location and creating OCR text blocks from the obtained OCR location of each word. Creating an empty array of text blocks, and adding the digital text blocks to the empty array. Adding one OCR text block to the corresponding empty array on confirming the location and performing the looping step on loop till the document is added with the OCR text block into each empty array.

Abstract: A system and method for deconstructing a document is described herein, where the method is an improvement over existing document deconstruction techniques. These improvements increase speed and accuracy by rapidly identifying the source in a document by splitting the document into a plurality of sections and performing a perceptual image hashing on each section. Then a hamming distance is used to compare the hash for each section with the hashes of known documents to identify the source who sent the document.

Abstract: A system and method for deconstructing a document is described herein, where the method is an improvement over existing document deconstruction techniques. These improvements increase speed and accuracy by rapidly identifying the vendor in an invoice by splitting the invoice into three regions and performing a perceptual image hashing on each section. Then a hamming distance is used to compare the hash for each section with the hashes of known invoices to identify the vendor who sent the invoice.

Abstract: A system and method for deconstructing a document is described herein, where the method is an improvement over existing document deconstruction techniques. These improvements increase speed and accuracy by rapidly identifying the vendor in an invoice by splitting the invoice into three regions and performing a perceptual image hashing on each section. Then a hamming distance is used to compare the hash for each section with the hashes of known invoices to identify the vendor who sent the invoice.