A knowledge-based segmentation algorithm for enhanced recognition of handwritten courtesy amounts

Abstract

The Productivity From Information Technology (PROFIT) Initiative was established on October 23, 1992 by MIT President Charles Vest and Provost Mark Wrighton "to study the use of information technology in both the private and public sectors and to enhance productivity in areas ranging from finance to transportation, and from manufacturing to telecommunications." At the time of its inception, PROFIT took over the Composite Information Systems Laboratory and Handwritten Character Recognition Laboratory. These two laboratories are now involved in research related to context mediation and imaging respectively. OR[RING In addition, PROFIT has undertaken joint efforts with a number of research centers, laboratories, and programs at MIT, and the results of these efforts are documented in Discussion Papers published by PROFIT and/or the collaborating MIT entity.Correspondence can be addressed to:The Researchers at MIT have looked at the possibility of taking information directly from paper documents, especially handwritten documents, to computeraccessible media. Automated reading involves several steps as follows:Scanning of document; Location of area to be "read"; Decomposing the selected area into separate characters; Adjusting size and slant of each character; Recognizing each character; and Testing whether input has been correctly read.Based on several years of sustained research, the researchers have attained very high "reading" speed and accuracy, even in situations where the quality of the input material is poor. Patent rights for some of the new techniques have been applied for. Sponsor companies are eligible to test the new techniques in their respective environments at no charge.The work performed so far is described in a number of working papers. AbstractA knowledge based segmentation critic algorithm to enhance recognition of courtesy amounts on bank checks is proposed in this paper. This algorithm extracts the context from the handwritten material and uses a syntax parser based on a deterministic finite automaton to provide adequate feedback to enhance recognition. The segmentation critic presented is capable of handling a number of commonly used styles for courtesy amount representation. Both handwritten and machine written numeric strings were utilized to test the efficacy of the preprocessor for the check recognition system described in this paper. The substitution error fell by 1.0% in our early tests.

Segmentation Strategy of Handwritten Connected Digits (SSHCD)

“…The segmentation consists to find the best way of cutting to isolate the digits [6], [7], [9]. However, finding the best way is not straightforward because two contiguous digits can be insulated, deformed, related by one or more contact points, partially superimposed, or on the contrary written in several pieces.…”

Handwritten Bank Check Recognition of Courtesy Amounts

“…With respect to U.S. checks, a finite state automaton was proposed in 16 to segment and analyze the variety of styles found in the decimal part of these checks. In other countries the decimal part of the amount is rarely found in a style other than scientific format.…”

Reading Courtesy Amounts on Handwritten Paper Checks

“…With respect to U.S. checks, a finite state automaton was proposed in [1] and [28] to segment and analyze the variety of styles found to express cents in fraction format. In the case of Brazilian checks, the decimal part of the amount is rarely found in a style other than scientific format.…”

“…Researchers have also described or implemented systems to read courtesy amount in checks [27,30], and some of these systems are geared to a particular writing language; for example [29] has been developed for Korean checks, [37,41] for checks written in French, and [1,28] for U.S. checks. Further, some check processing systems focus on reading the legal amount [26]; see [2] for Brazilian checks, [35] for English language ones, and [37,22,23] for French and English ones.…”