DOCUMENT Magazine - April 2008 - (Page 28)

A I ARCHIVING & IMAGING & w ith millions of ﬁelds of data to read within a transactional enterprise, accuracy of that data is vital. The utilization of validation procedures and statistical analysis can lend a helping hand to your recognition engines to process more accurately. Recognizing Accuracy a Improve document recognition with context and statistical analysis By Arthur Gingrande and Paul Traite Any method available to a user that can inform a recognition system about the kind of documents to which it will be exposed in advance of the classiﬁcation process will produce a bias toward improved recognition performance. Today’s recognition engines are used to classify many types of data, including machine print, handprint, barcodes, cursive writing, check boxes, ﬁll-in ovals and “pay this amount” ﬁelds on checks, both numeric and legal. For purposes of discussion, although OCR and ICR data dominate the examples in this article, most of the referred-to techniques can be used to improve recognition of the remaining data types. document processing systems prior to recognition in order to make the results match the data format of the form being recognized. For example, using a menu of different options, an end user may be given a choice of applying various grammatical rules, such as “I before E except after C,” or “look for the letter U after the letter Q,” in order to improve recognition of words in an open ﬁeld on a survey form. Another device that improves accuracy is the use of various edit masks to a ﬁeld that informs the ICR engine of the alphanumeric syntax of the ﬁeld. For example, if a six-digit product code is always composed of an initial three alphabetic characters followed by two numbers and a ﬁnal alphabetic character, then the edit mask “AAANNA” may be applied to the ﬁeld. This will prohibit the letter “O” from being confused with the number zero, or the number one from being mistaken for the letter “l” or the letter “S” from being confused with the number ﬁve, to name some of the most common substitution errors. Collections of different edit masks, such as time ﬁelds, date ﬁelds, social security numbers and product codes, can be created by the user and stored in memory for later use when setting up a form for recognition. By applying a user-deﬁned, application-speciﬁc dictionary of words to a given ﬁeld, accuracy will be improved. Multiple dictionaries can be created and stored for association with different ﬁelds on a form. For example, a dictionary of patient names might be applied against the “name” ﬁeld on a medical claim submitted to an insurance company. A dictionary of medical procedures might be applied against the “procedure” ﬁeld, and so forth. However, an ordinary English dictionary, Applying the Techniques When recognition software is used to process structured forms (in which each ﬁeld position is completely predeﬁned), many of the following techniques can be applied very early in the process, often by the recognition engine itself. The same techniques can be used when processing semi-structured or unstructured forms, but they may have to be used on a post-recognition basis, i.e., after the ﬁeld data has been located and extracted from the form. Context Analysis Context analysis is the most elementary and popular way of improving document recognition accuracy. It involves programming grammatical and lexical rules, edit masks and dictionaries into the forms and 28 document april.08 www.DOCUMENTmedia.com http://www.DOCUMENTmedia.com

Table of Contents Feed for the Digital Edition of Document Magazine - April 2008

Document Magazine - April 2008 Contents Editor's View The Research Desk The Response Center BPM: Improving the Way You Process Contributing Writers Mapping Out Performance Build the Context Before You Move into the House of ECM Taking On the Big 3 The Human Connection Addressing Your Addresses Don't Call Us, We'll Call You The Mulitplying Image Recognizing Accuracy New Products Calendar Advertisers

Document Magazine - April 2008

For optimal viewing of this digital publication, please enable JavaScript and then refresh the page. If you would like to try to load the digital publication without using Flash Player detection, please click here.