Data capture, character recognition OCR ICR OMR CHR BCR, image processing, forms data capture, document indexing, automatic data extraction Data capture, character recognition OCR ICR OMR CHR BCR, image processing, forms data capture, document indexing, automatic data extraction

data capture free form module unstructured

Recogniform Free Form & Layout Analysis Engine

Description

Recogniform Free Form and Layout Analysis Engine is the optional module avaible for Recogniform Reader which allow the recognition of semistructured even unstructured forms, or with field into different position instead fix. Indispensable for the data capture of passive cicly (invoices, ddt) but also for reading other documents tipology (RIBA, bank transfer, bank contract, document unstructured, etc.) using this technology of recognition Free Form allow you to identify a field based on certain specific attributes, which for example, its label, its formatting, its graphic layout. In the case of "Partita Iva" into invoice, for example, you can recognition, then obtain the value, by simply telling the system to find a sequence of 11 numeric characters (or 2 letters + 11 numeric characters), in proximity (above, under, right, left) of the words "P.IVA" or "Partita Iva" or "Partita Iva", etc., possibly limited to a certain area of ​​the document (for example in the upper half of the image). The same can be done to find the field DATA, NUMERO DOCUMENTO, IMPONIBILE, IVA, TOTALE, PESO, COLLI, etc.

Recogniform Free Form e Layout Analysis Engine

Extracting data from heterogeneous transport documents by Recogniform Free Form and Layout Analysis Engine

In practice the way of the software reflects the human reasoning: when we have to try on a bill the fieldTOTALE DOCUMENTO we are naturally inclined to look at the bottom right of the sheet, possibly we look on a box particularly evident or marked as "prova" the words "TOTALE DOCUMENTO" o "IMPORTO FATTURA" or "TOT. FATTURA". In the same way our system works Free Form Analysis: this is obviously based on our information, that is, on the basis of the rules set by using a simple scripting language.

At the base of the functions of the free-form processing is the use of OCR full text of the document together with our sophisticated algorithm to layout analysis: the combined use of these two tools makes it possible to identify the blocks text, vertical, horizontal and text elements with their confidences, hence the possibility of verifying whether the conditions imposed by the search field on the page.

Recogniform FreeForm Engine is available as an optional module of Recogniform Reader, and is integrated in the solution for the extraction of data from invoices and DDT Recogniform Invoices.