Content deleted Content added
Rescuing 1 sources and tagging 0 as dead. #IABot (v1.2.7.1) |
m Added definition of form types with industry references. |
||
Line 15:
Forms Processing has developed beyond basic capture of the data. Forms processing not only encompasses a recognition process but also helps manage the complete [[:wikt:life cycle|life cycle]] of documents which starts from scanning of the document to the extraction of the data, and often to delivery into a back-end system. In some cases it may also include processing or generating well formatted results through calculations and analysis. An automated forms processing system can be valuable if there is a need to process hundreds or thousands of images every day.
=== '''First Step: Assessment of the form structure''' ===
The first step in understanding automated forms processing is to analyze the type of form from which the extraction of data is desired. Forms can be classified as one of two high level categories for the purpose of extracting data. Four categories have been proposed<ref>{{Cite book|url=https://books.google.com/books?id=44arCAAAQBAJ&pg=PA425&lpg=PA425&dq=example+of+a+fixed+form+for+extraction&source=bl&ots=iD0mWE1bvT&sig=K89y_JIljSGtXC4i2jtN9JYjG3Q&hl=en&sa=X&ved=0ahUKEwjt4bHh-cTTAhVp0oMKHWAhBw4Q6AEIOTAE#v=onepage&q=example%20of%20a%20fixed%20form%20for%20extraction&f=false|title=Pattern Recognition and Machine Intelligence: 4th International Conference, PReMI 2011, Moscow, Russia, June 27 - July 1, 2011, Proceedings|last=Kuznetsov|first=Sergei O.|last2=Mandal|first2=Deba P.|last3=Kundu|first3=Malay K.|last4=Pal|first4=Sankar Kumar|date=2011-06-25|publisher=Springer|isbn=9783642217869|language=en}}</ref> however the document capture industry has settled up these two:
# Fixed forms. This type of form is defined as one in which the data to be extracted is always found in the same absolute position on a page. This allows a type of lens grid to be applied to the document and every subsequent occurrence of this document in order to extract the data. An example of a fixed form is a typical credit application form.<ref>{{Cite web|url=http://www.bfma.org/resource/resmgr/articles/05_04.pdf|title=CAPTURING SEMI-STRUCTURED FORMS AND DOCUMENTS: CHALLENGES AND AVAILABLE TECHNOLOGIES|last=Vassylyev|first=Artur|date=10 June 2008|website=|archive-url=|archive-date=|dead-url=|access-date=4 April 2017}}</ref>
# Semi-structured (or unstructured) form. This form is one in which the ___location of the data and fields holding the data vary from document to document. This type of document is perhaps most easily defined by the fact that it is not a fixed form. In the document capture industry, a semi-structured form is also called an unstructured form. Examples of these types of forms include letters, contracts, and invoices. According to a study by AIIM, about 80% of the documents in an organization fall under the semi-structured definition.<ref>{{Cite web|url=https://www.aiim.org/pdfdocuments/MIWP_Forms-Processing_2012.pdf|title=Forms Processing- user experiences of text and handwriting recognition (OCR/ICR)|last=|first=|date=|website=|archive-url=|archive-date=|dead-url=|access-date=4 April 2017}}</ref>
Although the components (described below) used for the the extraction of data from either type of form is the same the way in which these are applied varies considerably based upon the type of document.
===Components===
| |||