Overview

AccuRead ^TM OCR lets you use optical character recognition (OCR) in your multifunction product (MFP) to digitize documents, resulting in the following benefits:

• Improved document management by using the search and edit functions

• Increased productivity

• Fewer errors

• Faster process time

• Use of emerging technologies

Use the application to create a searchable or editable file from hard-copy documents. Compared with the traditional desktop OCR solution, AccuRead OCR combines the scan and OCR steps into a single process. The application does not require you to install TWAIN or Image and Scanner Interface Specification (ISIS) drivers or adjust scan targets.

Supported applications

• AccuRead Automate —Scan and classify documents, extract content from fields, and then send them to a network or e-mail destination.

• Scan Profile —Scan a document to a computer.

• Scan to USB —Scan a document to a flash drive.

• E-mail —Scan a document, and then send it to an e-mail address.

• FTP —Scan a document directly to a File Transfer Protocol (FTP) server.

• Scan to Network and Scan to Network Premium —Scan a document, and then send it to a network folder.

• Solution Composer —Build custom workflow solutions for MFPs running the Solution Composer Agent application.

Supported formats and languages

Output file formats

• Searchable portable document format (PDF) —A single file with multiple pages, viewable with a PDF reader.

• Text (TXT) —A simple text document that supports limited formatting options.

• Rich text format (RTF) —A text document that supports text file formatting and images within the text.

  Note:  This option is available only in some applications. For more information, see the documentation for the application.

• PDF —A single file that supports capturing and sending electronic documents in exactly the intended format.

• JPEG —A single file for compressing image files maintaining the original quality.

• TIFF —A single file to store raster graphics and image information.

• XPS —A single file that represents page layout files that are based on XML Paper Specifications created by Microsoft.

• Legacy —A single file that is an enterprise essential document stored in an obsolete file format.

Recognized languages

• Danish

• Dutch

• English

• Finnish

• French

• German

• Hungarian

• Italian

• Norwegian

• Polish

• Portuguese

• Spanish

• Swedish

OCR performance

AccuRead OCR performance is measured as the time it takes to scan a document until you receive the resulting digital output.

Lexmark reviewed test suites created by standard organizations such as the International Standards Organization (ISO) and the International Electrotechnical Commission (IEC), and then selected ISO/IEC 24735. Using this suite, testing was performed for black-and-white and color scans on an MX811 MFP with 1GB base memory and an installed hard disk.

Sample images included in the test suite

The scanning test conditions are as follows:

• All scans used 1-page, 10-page, and 25-page documents.

• Scans were repeated multiple times to ensure reproducibility.

• Black-and-white scans were set to grayscale.

• Settings for each scan included the automatic document feeder, one-sided printing, letter, and mixed text/photo type.

• Scan to USB was used with the default settings to send the files to a flash drive.

Sample documents

AccuRead OCR works best on documents with high contrast between the text and the background.

Documents with low contrast between the text and the background or that contain both light and dark text require more advanced processing. OCR accuracy can be improved by adjusting the scan settings or by using a server-based OCR solution.

Documents that are not ideal for either AccuRead OCR or server-based OCR include the following:

• Images with significant noise that is similar in color to the text

• Images with dark text on a dark background

• Light images with dot-matrix characters