A2iA has added a new set of solutions for handwritten and machine printed text recognition, information extraction and intelligent classification of paper documents.

Offering the ability to locate and extract handwritten and machine-printed data on documents, including complex columnar data such as text, numeric fields, dates and dollar amounts, A2iA DocumentReader is a new document classification and data extraction API.

Users can define their own set of keywords to be located, eliminating the time and cost associated with manually reviewing and sorting through stacks of mail, archives and other documents while permitting these documents to be searched. Once located and captured, A2iA DocumentReader allows the documents to be classified, looking at documents in a similar way that a human would -- based on both their geometry and content.

Organisations working with more structured forms are able to automate their forms processing application with A2iA FieldReader, a document-processing toolkit designed for structured forms.

The pages may contain machine-printed and handwritten information, including dates, dollar amounts, identification numbers, free-form fields and comb-boxes, for example. The documents can also consist of single pages, an array of pages grouped together, or a portion of a page that only contains a single field to recognise.