ABBYY Optical Character Recognition (OCR) Overview


Using your scanner or digital camera you can capture a picture of your document and keep it into an electronic format on your computer. However your computer cannot “see” text on such picture. Optical Character Recognition, usually abbreviated to OCR, is a technology to transform a picture of letters and words from a scanned or photographed document into electronic letters and words, which enables you to access and edit the content of the document.

Related Products

ABBYY FineReader

ABBYY FineReader

See More

ABBYY PDF Transformer

ABBYY PDF Transformer

See More

ABBYY FlexiCapture

ABBYY FlexiCapture

See More

ABBYY Recognition Server

See More


Outstanding Accuracy & Format Retention

Deliver up to 99% increase in overall OCR accuracy as well as faster document processing and demonstrate further improvements on high-quality images, significant improvements in processing documents with multiple and complex image items, documents with difficult-to-read print quality and digital images.


OCR, ICR, Checkmark and Barcode Recognition

Based on award-winning recognition technologies that deliver unprecedented accuracy in multiple languages for OCR and ICR, 1D and 2D barcodes and checkmarks can be recognized. The powerful image pre-processing functions also help to improve recognition quality.


Best Multi-lingual OCR

With constantly expanding language base, the OCR software now support up to 186 languages, including the new recognition language Korean and Yiddish, Traditional and Simplified Chinese, English, Japanese, etc.


Integration with Popular Office Applicatioth Popular Office Application

Document scanned and being processed can be exported directly to office favorite applications including Microsoft® Word, Excel®, PowerPoint®, and Adobe® Acrobat®/Reader®.


Automated Data Capture for all Document Types

Streamline business processes by automating time- and resource-consuming manual tasks, such as pre-sorting and data entry for business-critical documents, including invoices, agreements, purchase orders, registration forms and more.


Document Separation and Classification

Provide both simple separation and advanced classification of documents. Intelligent classification via multi-page document definitions enables different document types to be processed in a single stream. And with the help of built-in multi-level classifiers, the document definition matching and data extraction process is optimized for higher productivity.


Ready-made Connectors MS and Google Enterprisen

Not only acts as a standalone document capture solution, but also connects as a background OCR server to the enterprise search systems such as Google Search Appliance™ and Microsoft Office SharePoint® Server, as well as Windows® Desktop Search enabling the aforementioned systems with the ability to index and search through the content of image documents.


Redaction and Archiving

Redaction allows concealing confidential or sensitive data from certain fields. Document images can easily be prepared for archiving when converting them to Searchable PDF or PDF/A.


Invoice Processing with Line Item Extracted

You can train up the intelligent recognition engine to recognize the document pattern and extract the data you need, including invoice date, invoice number, line items, and total.


Data Verification to Increase Data Integrity

Data verification is designed to execute low-level verification tasks to check if extracted data can be matched with original document information. Verification can be achieved on a group and field level with a full-scale image review if necessary. Documents can be sent to an exception queue in case data extraction results require additional verification or testing.



• Fast deployment
• Low total cost of ownership
• Flexible integration with scanners and MFPs
• Automates invoice processing with data capture
• Simple to operate with easy interface for verification
• Increases efficiency with more resources and time freed from tedious manual data entry