Key Features

Classification of all Types of Paper Document
A2iA DocumentReader classifies digitized documents into “categories” (letter, identity papers, contract, etc.) based on both their geometry and their content. The software analyses the layout of items on the document.
Then, using a general dictionary and trade vocabulary, it carries out a literal transcription of the handwritten and/or typed areas. It then extracts the key words in order to determine the category of the document.

Data Extraction

A2iA DocumentReader uses 3 methods to extract data from all types of paper document:

• Extraction from predefined documents. Some documents (such as checks, bank details and envelopes) are preconfigured in A2iA DocumentReader. The software recognises their structure, the format of data to be extracted and their location on the document.
• Extraction from structured documents. A2iA DocumentReader recognises and extracts data with a fixed location in the document.
• Extraction from semi-structured documents. The layout of the document varies but the data to be extracted remain unchanged. A2iA DocumentReader locates them by their format and the proximity of key words, wherever they appear on the document.

Mail Processing
A2iA DocumentReader synthesises data extracted from different documents to identify the purpose of the mail (termination of subscription, request for assistance, change of address, etc.). A2iA DocumentReader then transmits the digital data to the classification application in order to direct the mail to the correct person.
Mail is sent to the correct person or department as soon as it arrives: processing and response times are minimised.