ANSWER (from http://stackoverflow.com/questions/7362926/what-is-the-state-of-the-art-in-ocr-of-bank-statements-in-net)

We have first hand experience, and I have done it in two different ways in the past.

Full Page OCR First, you can take the approach of “full-page OCR” and then parse the information into your desired data format. There is a variety of Engines with .NET support, such as ABBYY Engine SDK, or even a completely free-to-start cloud-based on-demand OCR API (OCR Cloud 2.0, http://www.ocr-it.com/ocr-cloud-2-0-api). This is more of a classic approach I used for over past 10 years and up to a few years ago. OCR provides you with a complete text-based result, and you use algorithms to extract informaiton. This approach is quite static and requires heavy programming usually, especially if there are multiple variations. There are two potentially troublesome areas to look for in this approach:

A. making sure that OCR provides consistent layout and text structure so it could be parsed reliably. If there is a table without gridlines, or if there is just tabular data that could be detected as a table, then OCR may work unpredictably from document to document, which essentially breaks your parsing down the road.

B. making sure that your parsing logic can accommodate various formatting differences and multiple variations of data structures. This is pure programming that requires code changes for adjustments or updates.

Dynamic Data Capture Second, use a modern dynamic data capture system that automates template identification and data extraction. This is the approach I have been using instead of parsing for a few years now, and it is several times faster and more convenient to create and operate. In this process you would use a specialized software, such as ABBYY FlexiCapture(http://www.wisetrend.com/abbyy_flexicapture.shtml), which will take care of two aforementioned issues with variable data formats and different templates. Before processing it needs to be setup and “trained” to identify different statement types and how the data is located on those different variations. It performs all setup through User Interface and not coding, and you can plugin custom scripts if desired. If it needs to be re-trained for a new template, or trained to capture some data more reliably, it takes a few minutes without coding or programming experience. I have trained accountants to maintain and adjust their invoice templates themselves.
(see their feedback here:http://www.prweb.com/releases/2011/wisetrend_wiseinvoice/prweb4936544.htm)

NOTE: FlexiCapture is not .NET SDK, but an application with complete automation. It can be used interactively by operators, or typically I use it for 100% server-based automation. Once setup, I feed images to it for Input, and get my properly formatted text as Output in either CSV, XML, or direct export into my ODBC databases. So you could use it as ‘black box’ server based component.

I have a sample project for bank statements somewhere, so please let me know if you would like to see it yourself live.

SOURCE: OCR & Data Capture consultants with 11 years experience.

August 30, 2011 - OCR-IT LLC, a fast-growing document conversion and image processing company, today announced public availability of its newest cloud-based OCR Web API, code-named “OCR Cloud 2.0”. The platform ties together high-quality Optical Character Recognition (OCR) technologies from several leading manufacturers through a powerful HTTP POST API. The API allows developers with various backgrounds and working environments to access powerful image and picture cleanup tools and text recognition algorithms. Optical character recognition supports over 50 Latin and Cyrillic languages, provides enhanced control over text extraction and supports a wide selection of output formats.

“As today’s mobile cameras, such as in iPhone 4 and soon to be released iPhone 5, as well as Android-based phones and tablets, continue to increase picture quality, smart developers are looking for new and creative ways to combine these data-gathering resources together with this Web OCR API to create applications that excite end users,” said principals at OCR-IT. “By offering this advanced OCR API, OCR Cloud 2.0 offers developers a chance to create applications that have low costs in development and usage but can lead in innovation.”

Historically, high quality OCR has been developed for Windows platform, while other popular operating systems such as Mac OS and Linux, and mobile platforms such as iOS and Android, are left with inferior OCR technologies. OCR-IT OCR Cloud 2.0 erases these boundaries with high-quality Optical Character Recognition and accurate text extraction from any Web-enabled platform, making it truly OS-independent. Now, every developer can utilize this feature-rich powerful productivity technology to create a variety of never-seen-before applications.

The initial release of OCR Cloud was developed over two years ago by WiseTREND (http://www.wisetrend.com), a leading integrator and custom development firm for advanced OCR and data capture solutions. The API has been adopted by thousands of developers worldwide. Developers serving various industries have reported hundreds of successful implementations including internal corporate projects, the development of e-discovery processes and the creation of mobile applications, as well as for the addition of OCR support on operating systems that have no native support for OCR capabilities.

“OCR-IT LLC takes over OCR Cloud 2.0 with the creation of the second generation of capabilities,” said OCR-IT representative. “With the continued participation of the WiseTREND team, we will continue full-force development of this API so that it will fulfill its promise as one of the most powerful cloud-based OCR platforms in the marketplace today.”

Developers can sign up for a FREE development account and start integration into their applications immediately. With a few lines of code, programmers can start processing images form any Web-enabled computer or mobile device. Full documentation and comprehensive code samples in different programming languages are provided. For more information and additional documentation, visit: http://www.ocr-it.com/ocr-cloud-2-0-api

About WiseTREND (the developer and lead partner in OCR Cloud 2.0 API initiative)
WiseTREND, a power-integrator of OCR, document recognition, form processing and data capture technologies and solutions, works with a variety of organizations to successfully utilize the most powerful technologies of today and create competitive technologies of tomorrow. The company helps to solve business challenges through state-of-the-art document processing solutions, techniques, efficiency, and innovation. For additional company and product information, please visit: http://www.wisetrend.com