ID cards strengthen market for data capture software
You know that thing where companies try to get journalists to write their name in caps by marketing themselves with an all-capitals moniker? Well, the company formerly known as ABBYY will be referred to as Abbyy for the purposes of this blog. If you’re not familiar with them (and I wasn’t), the aforementioned outfit is a provider of document recognition, data capture and linguistic software.
Why I am talking about them? Well two reasons I suppose. I think it’s really important to focus on smaller companies from time to time and not just follow the latest developments emanating from IBM (damn! caps again, they got me). Secondly, the aforementioned outfit has today released a new SDK designed specifically for data capture integration in Windows-based applications.
With its ability to extract data from forms and documents of any type and complexity, this SDK may be a good instrument for developing vertical solutions such as those intended for processing ID cards. With Manchester confirmed as the first UK city offering voluntary sign up for ID cards this morning, this type of technology may be rapidly evolving out of the back end to gain a little front end prominence then.
Purported to combine technologies for processing forms, semi-structured and unstructured documents, this is the kind of tool that would be, I imagine, typically used for data verification and data export for backend processing and archiving. Working separately on a heavily DBA-driven project as I do, you might not think this is the sexy end of the data management spectrum – but it has to be done I suppose and it’s clearly the lifeblood of some engineers.
Abbyy’s product, known as FlexiCapture Engine 8.0, is targeted at developers, ISVs and service providers. The company says that the need for data capture is continually growing and expanding into a wide number of new segments and opportunities across many vertical markets and that, “FlexiCapture Engine is designed to address this growing audience by giving developers the tools to easily customise their solutions according to vertical market needs.”
The product provides a set of core recognition technologies including IIntelligent Character Recognition (ICR) for hand-printed text, Optical Character Recognition (OCR) for printed text, barcode recognition, Optical Mark Recognition (OMR) and PDF conversion. It also includes technology to process semi-structured and unstructured documents including invoices, price lists, waybills, contracts and other documents where the location of data fields is not fixed.
Without reeling off the product specs of this technology, if you’re still reading then I wanted to also make note of the fact that this tool works by offering data validation and verification instruments such as checking captured values against databases and has a special API for manual verification. The SDK itself features more than 180 languages for OCR and over 110 languages for ICR.