FINANCIAL DOCUMENT PROCESSING BASED ON STAFF LINE AND DESCRIPTION LANGUAGE

Millions of financial transactions take place every day, Associated wi th them are documents such as bank cheques, payment slips and bills wh ich have to be processed, A great deal of time, effort and money will be saved if they can be entered into the computer and processed automa tically, According to the specific characteristics of financial docume nts, it can be concluded that it is possible to build a system for rec ognizing specific types of financial documents, instead of a complex a nd general one aiming at different kinds of documents, In this paper, a financial document recognition prototype system,which can process ba nk cheques, payment ships and bills, is presented, It consists of four major parts: (a) document image acquisition including scanning and bi narization, (b) fixed document processing subsystem based on the detec tion of staff lines, (c) flexible document processing subsystem operat ing in a form description language (FDL), and (d) character recognitio n, Numerous experimental results are presented and discussed.