Digitize Paper to Remove Cost and Inefficiency

In an ideal world, organizations could snap their fingers and replace their paper transactions with electronic ones—removing considerable cost and inefficiency from their business processes. After all, electronic transactions are typically faster, less expensive to conduct and can even be more accurate and secure than paper.

Despite such advantages however, legacy processes mean that the transition from paper to electronic processes is happening slowly in many companies. Yet organizations can still enjoy many of the benefits of e-transactions by implementing automated document and data capture technology—enabling them to digitize paper and convert its information into searchable, rapidly accessible electronic data.

Applying OCR for Data Extraction

The key to efficiently converting paper to electronic data is applying automatic recognition technology to document images—which are simply digital pictures of paper documents. Automatic recognition involves utilizing optical character recognition (OCR) to determine the letters and numbers appearing on an image, then converting that information to an electronic format that is understandable by other computer programs.

The steps in extracting information from paper documents are:

1. OCR analyzes the text and patterns of an imaged document and classifies it, for example, as an "order form";

2. Once identified, the form is routed into a field-extraction workflow that is specific to the document type. This workflow produces the proper metadata needed for integration with a specific back-end system, such as a customer relationship management (CRM) system; and

3. The image and associated metadata are then absorbed into the CRM system, where they are accessible to a wide range of users for a variety of purposes.

This scan-and-capture process is more efficient than keying data into backend systems from the paper forms.

Advantages of automated data capture.
Automated data capture can help your organization:

• Reduce labor costs related to keying data by 50% or more;
• Provide ROI in less than 18 months;
• Improve turnaround time and provide better visibility into incoming document streams;
• Increase accuracy by eliminating error-prone manual data entry;
• Reduce employee costs associated with hiring more manual labor to key in data; and
• Enable better document archiving by placing them in an enterprise content management (ECM) system for improved records management and accessibility.

Data capture use cases.
Common use cases for automated data capture include:

• Preparing documents for search and retrieval. Typically involves applying full-text OCR to help users find documents through search engines—either desktop or Web-based.
• Extracting metadata for ECM systems. Metadata enables users to perform searches on specific fields, such as name or account number. Extracting metadata can involve applying field-based OCR, or it can also be achieved through capturing bar-codes or check box marks.
• Forms processing. Involves extracting data that's typically fed into line-of-business applications including accounting, ERP and order management systems. Can be applied to structured forms by utilizing templates and OCR, or semi- and un-structured forms, or by utilizing intelligent document recognition (IDR).
• Auto-classification. Can be used to reduce document preparation costs—one of the biggest costs in the document imaging process-in areas like sorting documents and inserting cover sheets. 

---

ABBYY is headquartered in Moscow, Russia, with offices in Germany, the UK, the United States, Canada, Ukraine, Cyprus, Australia, Japan and Taiwan. ABBYY offers several products that address the automated recognition applications described above. ABBYY USA, 880 North McCarthy Boulevard, Suite 220, Milpitas, California 95035, USA; 408-457-9777; http://www.abbyy.com.