Artificial intelligence is used to train Optical Character Recognition (OCR) systems for improved accuracy and the identification of common data elements based on context.

Can OCR be trained for specific fonts?

OCR training was once a critical part of the conversion process. After a document was read, the operator would review the results to correct mistaken characters and these corrections would be used to train the engine so the next time you read a similar document the results are improved.

Modern OCR applications no longer rely on user training for accuracy unless you have very non-standard fonts. These engines have had decades of development and billions of samples used to train their algorithms. In most cases, the introduction of user training will only diminish the results for any documents that are different than the ones being trained.

The training functions still exist for these edge cases, but they are no longer an integral part of the OCR process.

Training in modern OCR is more likely to refer to enterprise data capture applications that use AI-based learning algorithms to find the locations of data points on documents with various different formats, such as invoices.

Using Artificial Intelligence to train OCR templates

Modern Forms Processing applications have AI-based training algorithms that let users point and click on the location of data in their documents and create OCR templates automatically.

This bypasses the technical requirements of creating complex OCR templates, especially for varied documents like Invoices where the data doesn’t always appear in the same place.

But how good are these AI-based training systems?

In our experience they work well when you have:

  • Good quality scanned images
  • Clearly labeled data
  • Tables with regular columns

Point and click style training doesn’t work quite as well with:

  • Poor quality images
  • Data that appears within paragraphs
  • Tables with overlapping columns, subtotal rows, etc.

These types of documents can still be captured with OCR but they will usually require an experienced technician to manually configure the template.

For natural language data like legal documents, a new artificial intelligence technology called NLP (Natural Language Processing) is available. These work by attempting to “understand” the language used in documents to interpret the location of data points based on meaning. ABBYY FlexiCapture also supports NLP-based training for these types of documents.

Go to Top