Four diverse data capture technologies

Four diverse data capture technologies give AnyDoc Software products and solutions the ability to process the broadest range of document types possible. Each of these technologies can capture whatever data you need from these documents, whether it’s machine print, hand print, mark sense or bar codes.

AnyApp™ Technology

With semi-structured documents such as invoices, the placement of data fields is inconsistent. Nearly every vendor produces a unique invoice for their goods and services. As a result, the purchase order number might be located at the top right of one invoice and the top left of another. The presentation of data on a semi-structured document can vary also. Lines of data may carry over to another page, from one document to the next. The data’s font sizes can fluctuate from one document to the other as well.

That’s why AnyDoc Software developed AnyApp technology: to make the automated processing of invoices and other semi-structured documents easier and more efficient. AnyApp locates data on template-resistant forms—regardless of where it resides on the document—by searching for defined data labels, such as “amount due” and “invoice number”; data format, such as dd/mm/yyyy; data type, such as alpha, numeric or both; and/or location, such as “just look in the top half of the document for this data.”

AnyApp remembers the location of this data on the document. So, the software becomes faster each time it processes that particular document type.

QuickApp™ Technology

QuickApp technology streamlines the extraction of data from rare or seldom-seen documents – without key-from-image processing or using a document template. QuickApp is ideal to process unstructured documents such as letter and direct mail where there is no consistent format.

Users simply point and click to capture data, and QuickApp creates a profile for use in future instances of the same document type. The results are less user interaction the next time the document type is processed, and in some instances, fully automated data capture for the document.

Template-Based Processing

Structured documents are consistent. The data fields on a structured document type are always in the same location from one copy of the document to the next, such as order forms, credit applications, etc. Because of this, users can capture the data off structured document images with a template.

In the document template, users define where each data field can be found on the document, the type of data to look for (e.g., alpha-numeric), and the format of the data’s output.

Template-based OCR for AnyDoc® performs six phases of processing on each image to ensure the best possible output: image capture, quality assure, form identification, data capture, data validation and verification. The final phase allows human operators to check any characters OCR for AnyDoc flags as questionable and adds to the accuracy of your data.

Key-from-Image

With key-from-image, data entry operators view and key data off scanned document images rather than the paper documents themselves. Standard key-from-image is approximately 10% more efficient than traditional data entry methods.

OCR for AnyDoc’s key-from-image processing includes rope and expand capabilities, which allow operators to capture data with their mouse. As a result, they key in significantly less data.