F1 ACCOUNTING INTELLIGENT DATA EXTRACTION OCR(from Qaiser M) on 10/22/2010 12:59:30 AM

INTELLIGENT DATA EXTRACTION SYSTEM FOR F1 ACCOUNTING I am looking for a utility where I want to scan and extract required information from various types of documents like invoices, bank statements and sales reports. Information I want to extract are DATE DDMMYYYY VENDOR NAME, INVOICE # TOTAL AMOUNT, TAX AMOUNT, MODE OF PAYMENT. ## Deliverables My Lotus Domino developer is looking for structured and consistent data format extracted from the scanned images so that he can populate the Lotus Domino base database using Lotus and Java scripts. Data can be deposited in csv format or xml format. There will be 3 main category of documents. ![][1]![][2]INVOICE 1. SCAN INVOICES 2. CAPTURE DATE (DDMMYYYY), VENDOR NAME (PEPSI - OLD DUTCH) INVOICE #, AMOUNT, GST (TAX AMOUNT), MODE OF PAYMENT (BANK, CREDIT CARD, CASH) 3. GENERATE ERRORS NOTIFICATION AND PROVIDE STEP TO FIX THOSE ERRORS 4. GENERATE XML/CSV AFTER ALL ERRORS FIXED 5. CHANGE THE NAME OF THE FILE AS CLIENT NAME-VENDOR NAME-DATE-TIME BANK 1. SCAN BANK STATEMENTS 2. CAPTURE DATE (DDMMYYYY), DESCRIPTION, DEBIT AMOUNT, CREDIT AMOUNT, BALANCE AMOUNT. 3. GENERATE ERRORS NOTIFICATION AND PROVIDE STEP TO FIX THOSE ERRORS 4. GENERATE XML/CSV AFTER ALL ERRORS FIXED 5. CHANGE THE NAME OF THE FILE AS CLIENT NAME-BANK NAME-DATE-TIME SALES REPORT 1. SCAN SALES REPORT 2. CAPTURE DATE (DDMMYYYY), NET SALES, GST (TAX), GROSS SALES - (CAPTURE FIELDS VARIES FOR EACH CLIENT. FOR EXAMPLE FOR SHELL CLIENT WE NEED TO CAPTURE MERCHANDISE SALE FUEL SALES GST EPOS DEBIT EPOS CREDIT SAFE DROPS ETC ETC SEE ATTACHED) 3. GENERATE ERRORS NOTIFICATION AND PROVIDE STEP TO FIX THOSE ERRORS 4. GENERATE XML/CSV AFTER ALL ERRORS FIXED 5. CHANGE THE NAME OF THE FILE AS CLIENT NAME-SALES REPORT NAME-DATE-TIME